Dong Yu

AAAI Conference 2026 Conference Paper

Audio-Thinker: Guiding Large Audio Language Model When and How to Think via Reinforcement Learning

• Shu Wu
• Chenxing Li
• Wenfu Wang
• Hao Zhang
• Hualei Wang
• Meng Yu
• Dong Yu

Recent advancements in large language models, multimodal large language models, and large audio language models (LALMs) have significantly improved their reasoning capabilities through reinforcement learning utilizing rule-based rewards. However, the explicit reasoning process has not yet yielded substantial benefits for audio question answering, and effectively leveraging deep reasoning remains an open challenge, with LALMs still falling short of achieving human-level auditory-language reasoning. To address these limitations, we propose Audio-Thinker, a reinforcement learning framework designed to enhance the reasoning capabilities of LALMs through improved adaptability, consistency, and effectiveness. Our approach introduces an adaptive think accuracy reward, enabling the model to adjust its reasoning strategies based on task complexity. Furthermore, we incorporate an external reward model to evaluate the overall consistency and quality of the reasoning process, complemented by think-based rewards that assist the model in distinguishing between valid and flawed reasoning paths during training. Experimental results demonstrate that Audio-Thinker models outperform existing reasoning-oriented LALMs across various benchmark tasks, exhibiting superior reasoning and generalization capabilities.

AAAI Conference 2026 Conference Paper

Beyond Euclidean Assumptions: Geometry-Aware Adaptive Routing for Remote Sensing Segmentation

• Jie Qiu
• Dizuo Cao
• Linwei Dai
• Xin Li
• Fan Yang
• Dong Yu
• Changying Wang
• Zongheng Wen

Remote sensing imagery poses a distinct challenge for semantic segmentation due to its inherent fractal complexity and the diversity of geometric structures present in real-world geospatial scenes. Euclidean-based models typically assume spatial uniformity; however, such assumptions often break down when confronted with objects exhibiting markedly different structural characteristics—such as roads versus vegetation—thereby complicating the feature representation process. Hyperbolic space offers a theoretically grounded alternative for modeling such hierarchical and heterogeneous patterns, yet fully replacing Euclidean geometry incurs significant computational overhead. We therefore introduce Geometry-Aware Adaptive Routing (GAAR), a novel module that facilitates geometry-aware routing by dynamically allocating high-level features to either Euclidean or Hyperbolic subspaces through a learnable binary gating mechanism, informed by structural priors learned during training. To further promote routing stability and geometric consistency, we introduce Geometry-Aware Deterministic Regularization (GADR), a regularization strategy that encourages confident, structure-aligned assignments. GAAR is plug-and-play and integrates seamlessly into existing segmentation architectures. Experiments on three challenging Remote Sensing Image Semantic Segmentation (RSISS) benchmarks demonstrate that our approach consistently outperforms state-of-the-art (SOTA) methods, particularly in geometrically complex regions, offering a scalable and effective solution to the limitations of purely Euclidean modeling.

AAAI Conference 2026 Conference Paper

DegVoC: Revisiting Neural Vocoder from a Degradation Perspective

• Andong Li
• Tong Lei
• Lingling Dai
• Kai Li
• Rilin Chen
• Meng Yu
• Xiaodong Li
• Dong Yu

Existing neural vocoders have demonstrated promising performance by leveraging Mel-spectrum as an acoustic feature for conditional audio generation. Nonetheless, they remain constrained by an inherent ``performance-cost'' dilemma that significantly hinders the development of this field. This paper revisits this foundational task from a novel degradation perspective, where Mel-spectrum is regarded as a special signal degradation process from the target spectrum. Drawing inspiration from traditional sparse signal recovery problems, we propose DegVoC, a GAN-based neural vocoder with a two-step solution procedure. First, by exploiting degradation priors, we attempt to retrieve the initial spectral structure from Mel-domain representations as an initial solution via a simple linear transformation. Based on that, we introduce a deep prior solver that accounts for the heterogeneous distribution of sub-bands in the time-frequency domain. A convolution-style attention module with a large kernel size is specially devised for efficient inter-frame and inter-band contextual modeling. With 3.89 M parameters and substantially reduced inference complexity, DegVoC achieves state-of-the-art performance across objective and subjective evaluations, outperforming existing GAN-, DDPM- and flow-matching-based baselines.

AAAI Conference 2026 Conference Paper

Enhancing Stability and Fidelity for Zero-Shot TTS with a Multi-Level Evaluator

• Hualei Wang
• Na Li
• Chuke Wang
• Shu Wu
• Zhifeng Li
• Dong Yu

Recent advances in zero-shot text-to-speech (TTS), driven by language models, diffusion models and masked generation, have achieved impressive naturalness in speech synthesis. Nevertheless, stability and fidelity remain key challenges, manifesting as mispronunciations, audible noise, and quality degradation. To address these issues, we introduce Vox-Evaluator, a multi-level evaluator designed to guide the correction of erroneous speech segments and preference alignment for TTS systems. It is capable of identifying the temporal boundaries of erroneous segments and providing a holistic quality assessment of the generated speech. Specifically, to refine erroneous segments and enhance the robustness of the zero-shot TTS model, we propose to automatically identify acoustic errors with the evaluator, mask the erroneous segments, and finally regenerate speech conditioning on the correct portions. In addition, the fine-gained information obtained from Vox-Evaluator can guide the preference alignment for TTS model, thereby reducing the bad cases in speech synthesize. Due to the lack of suitable training datasets for the Vox-Evaluator, we also constructed a synthesized text-speech dataset annotated with fine-grained pronunciation errors or audio quality issues. The experimental results demonstrate the effectiveness of the proposed Vox-Evaluator in enhancing the stability and fidelity of TTS systems through the speech correction mechanism and preference optimization.

TIST Journal 2026 Journal Article

TencentLLMEval: A Hierarchical Evaluation of Real-World Capabilities for Human-Aligned LLMs

• Shuyi Xie
• Wenlin Yao
• Yong Dai
• Shaobo Wang
• Zishan Xu
• Fan Lin
• Donglin Zhou
• Lifeng Jin

Large language models (LLMs) have shown impressive capabilities across various natural language tasks. However, evaluating their alignment with human preferences remains a challenge. To this end, we propose a comprehensive human evaluation framework to assess LLMs’ proficiency in following instructions on diverse real-world tasks. We construct a hierarchical task tree encompassing seven major areas covering over 200 categories and over 800 tasks, which covers diverse capabilities such as question answering, reasoning, multi-turn dialogue, and text generation, to evaluate LLMs in a comprehensive and in-depth manner. We also design detailed evaluation standards and processes to facilitate consistent, unbiased judgments from human evaluators. A test set of over 3,000 instances is released, spanning different difficulty levels and knowledge domains. Our work provides a standardized methodology to evaluate human alignment in LLMs for both English and Chinese. We also analyze the feasibility of automating parts of evaluation with a strong LLM (GPT-4). Our framework supports a thorough assessment of LLMs as they are integrated into real-world applications. We have made publicly available the task tree, TencentLLMEval dataset, and evaluation methodology which have been demonstrated as effective in assessing the performance of Tencent Hunyuan LLMs. By doing so, we aim to facilitate the benchmarking of advances in the development of safe and human-aligned LLMs.

AAAI Conference 2026 Conference Paper

UniCUE: Unified Recognition and Generation Framework for Chinese Cued Speech Video-to-Speech Generation

• Jinting Wang
• Shan Yang
• Chenxing Li
• Dong Yu
• Li Liu

Cued Speech (CS) enhances lipreading via hand coding, offering visual phonemic cues that support precise speech perception for the hearing-impaired. The task of CS Video-to-Speech generation (CSV2S) aims to convert CS videos into intelligible speech signals. Most existing research focuses on CS Recognition (CSR), which transcribes video content into text. Consequently, a common solution for CSV2S is to integrate CSR with a text-to-speech (TTS) system. However, this pipeline relies on text as an intermediate medium, which may lead to error propagation and temporal misalignment between speech and CS video dynamics. In contrast, directly generating audio speech from CS video (direct CSV2S) often suffer from the inherent multimodal complexity and the limited availability of CS data. To address these challenges, we propose UniCUE, the first unified framework for CSV2S that directly generates speech from CS videos without relying on intermediate text. The core innovation of UniCUE lies in integrating a understanding task (CSR) that provides fine-grained CS visual-semantic cues to to guide the speech generation. Specifically, UniCUE incorporates a pose-aware visual processor, a semantic alignment pool that enables precise visual–semantic mapping, and a VisioPhonetic adapter to bridge the understanding and generation tasks within a unified architecture. To support this framework, we construct UniCUE-HI, a large-scale Mandarin CS dataset containing 11,282 videos from 14 cuers, including both hearing-impaired and normal-hearing individuals. Extensive experiments conducted on this dataset demonstrate that UniCUE achieves state-of-the-art (SOTA) performance across multiple evaluation metrics.

TMLR Journal 2026 Journal Article

VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models

• Ce Zhang
• Kaixin Ma
• Tianqing Fang
• Wenhao Yu
• Hongming Zhang
• Zhisong Zhang
• Haitao Mi
• Dong Yu

Recent Large Vision-Language Models (LVLMs) have advanced multi-modal understanding by incorporating finer-grained visual perception and encoding. However, such methods incur significant computational costs due to longer visual token sequences, posing challenges for real-time deployment. To mitigate this, prior studies have explored pruning unimportant visual tokens either at the output layer of the visual encoder or at the early layers of the language model. In this work, we revisit these design choices and reassess their effectiveness through comprehensive empirical studies of how visual tokens are processed throughout the visual encoding and language decoding stages. Guided by these insights, we propose VScan, a two-stage visual token reduction framework that addresses token redundancy by: (1) integrating complementary global and local scans with token merging during visual encoding, and (2) introducing pruning at intermediate layers of the language model. Extensive experimental results across four LVLMs validate the effectiveness of VScan in accelerating inference and demonstrate its superior performance over current state-of-the-arts on sixteen benchmarks. Notably, when applied to LLaVA-NeXT-7B, VScan achieves a 2.91$\times$ speedup in prefilling and a 10$\times$ reduction in FLOPs, while retaining 95.4\% of the original performance. Code will be made publicly available upon acceptance.

IJCAI Conference 2025 Conference Paper

BridgeVoC: Neural Vocoder with Schrödinger Bridge

• Tong Lei
• Zhiyu Zhang
• Rilin Chen
• Meng Yu
• Jing Lu
• Chengshi Zheng
• Dong Yu
• Andong Li

While previous diffusion-based neural vocoders typically follow a noise-to-data generation pipe-line, the linear-degradation prior of the mel-spectrogram is often neglected, resulting in limited generation quality. By revisiting the vocoding task and excavating its connection with the signal restoration task, this paper proposes a time-frequency (T-F) domain-based neural vocoder with the Schrödinger Bridge, called BridgeVoC, which is the first to follow the data-to-data generation paradigm. Specifically, the mel-spectrogram can be projected into the target linear-scale domain and regarded as a degraded spectral representation with a deficient rank distribution. Based on this, the Schrödinger Bridge is leveraged to establish a connection between the degraded and target data distributions. During the inference stage, starting from the degraded representation, the target spectrum can be gradually restored rather than generated from a Gaussian noise process. Quantitative experiments on LJSpeech and LibriTTS show that BridgeVoC achieves faster inference and surpasses existing diffusion-based vocoder baselines, while also matching or exceeding non-diffusion state-of-the-art methods across evaluation metrics.

NeurIPS Conference 2025 Conference Paper

Improving LLM General Preference Alignment via Optimistic Online Mirror Descent

• Yuheng Zhang
• Dian Yu
• Tao Ge
• Linfeng Song
• Zhichen Zeng
• Haitao Mi
• Nan Jiang
• Dong Yu

Reinforcement learning from human feedback (RLHF) has demonstrated remarkable effectiveness in aligning large language models (LLMs) with human preferences. Many existing alignment approaches rely on the Bradley-Terry (BT) model assumption, which assumes the existence of a ground-truth reward for each prompt-response pair. However, this assumption can be overly restrictive when modeling complex human preferences. In this paper, we drop the BT model assumption and study LLM alignment under general preferences, formulated as a two-player game. Drawing on theoretical insights from learning in games, we integrate optimistic online mirror descent into our alignment framework to approximate the Nash policy. Theoretically, we demonstrate that our approach achieves an $\mathcal{O}(T^{-1})$ bound on the duality gap, improving upon the previous $\mathcal{O}(T^{-1/2})$ result. Meanwhile, it enjoys a linear convergence rate in the last iterate, a property not achieved by previous methods. More importantly, we implement our method and show through experiments that it outperforms state-of-the-art RLHF algorithms across multiple representative benchmarks.

TMLR Journal 2025 Journal Article

Leopard: A Vision Language Model for Text-Rich Multi- Image Tasks

• Mengzhao Jia
• Wenhao Yu
• Kaixin Ma
• Tianqing Fang
• Zhihan Zhang
• Siru Ouyang
• Hongming Zhang
• Dong Yu

Text-rich images, where text serves as the central visual element guiding the overall understanding, are prevalent in real-world applications, such as presentation slides, scanned documents, and webpage snapshots. Tasks involving multiple text-rich images are especially challenging, as they require not only understanding the content of individual images but reasoning about inter-relationships and logical flows across multiple visual inputs. Despite the importance of these scenarios, current multimodal large language models (MLLMs) struggle to handle such tasks due to two key challenges: (1) the scarcity of high-quality instruction tuning datasets for text-rich multi-image scenarios, and (2) the difficulty in balancing image resolution with visual feature sequence length. To address these challenges, we propose Leopard, a MLLM designed specifically for handling vision-language tasks involving multiple text-rich images. First, we curated about one million high-quality multimodal instruction-tuning data, tailored to text-rich, multi-image scenarios. Second, we proposed an adaptive high-resolution multi-image encoding module to dynamically optimize the allocation of visual sequence length based on the original aspect ratios and resolutions of images. Experiments on a diverse set of benchmarks reveal that our model consistently outperforms state-of-the-art systems, such as Llama-3.2 and Qwen2-VL, in challenging text-rich, multi-image evaluations. Remarkably, our approach achieves outstanding performance using only 1.2M fully open-sourced training instances, outperforming models that rely on large-scale in-house data, highlighting its efficiency and effectiveness. Our code and data are available at https://anonymous.4open.science/r/Leopard-908F.

NeurIPS Conference 2025 Conference Paper

LeVo: High-Quality Song Generation with Multi-Preference Alignment

• Shun Lei
• Yaoxun Xu
• Huaicheng Zhang
• Wei Tan
• Hangting Chen
• Yixuan Zhang
• Chenyu Yang
• Haina Zhu

Recent advances in large language models (LLMs) and audio language models have significantly improved music generation, particularly in lyrics-to-song generation. However, existing approaches still struggle with the complex composition of songs and the scarcity of high-quality data, leading to limitations in audio quality, musicality, instruction following, and vocal-instrument harmony. To address these challenges, we introduce LeVo, a language model based framework consisting of LeLM and Music Codec. LeLM is capable of parallel modeling of two types of tokens: mixed tokens, which represent the combined audio of vocals and accompaniment to achieve better vocal-instrument harmony, and dual-track tokens, which separately encode vocals and accompaniment for high-quality song generation. It employs two decoder-only transformers and a modular extension training strategy to prevent interference between different token types. To further enhance musicality and instruction following ability, we introduce a multi-preference alignment method based on Direct Preference Optimization (DPO). This method handles diverse human preferences through a semi-automatic data construction process and post-training. Experimental results demonstrate that LeVo significantly outperforms existing open-source methods in both objective and subjective metrics, while performing competitively with industry systems. Ablation studies further justify the effectiveness of our designs. Audio examples and source code are available at https: //levo-demo. github. io and https: //github. com/tencent-ailab/songgeneration.

AAAI Conference 2025 Conference Paper

LiteSearch: Efficient Tree Search with Dynamic Exploration Budget for Math Reasoning

• Ante Wang
• Linfeng Song
• Ye Tian
• Baolin Peng
• Dian Yu
• Haitao Mi
• Jinsong Su
• Dong Yu

Recent research suggests that tree search algorithms (e.g. Monte Carlo Tree Search) can dramatically boost LLM performance on complex mathematical reasoning tasks. However, they often require more than 10 times the computational resources of greedy decoding due to wasteful search strategies, making them difficult to be deployed in practical applications. This study introduces a novel guided tree search algorithm with a goal-directed heuristic function and node-level exploration budget (maximum number of children) calculation to tackle this issue. By considering the search progress towards the final answer (history) and the guidance from a value network (future) trained without any step-wise annotations, our algorithm iteratively selects the most promising tree node before expanding it within the boundaries of the allocated computational budget. Experiments conducted on the GSM8K, TabMWP, and MATH datasets demonstrate that our method not only offers competitive performance but also enjoys significantly lower computational costs compared to baseline methods.

NeurIPS Conference 2025 Conference Paper

MPS-Prover: Advancing Stepwise Theorem Proving by Multi-Perspective Search and Data Curation

• Zhenwen Liang
• Linfeng Song
• Yang Li
• Tao Yang
• Haitao Mi
• Dong Yu

Automated Theorem Proving (ATP) in formal languages remains a formidable challenge in AI, demanding rigorous logical deduction and navigating vast search spaces. While large language models (LLMs) have shown promising performance, existing stepwise provers often suffer from biased search guidance, leading to inefficiencies and suboptimal proof strategies. This paper introduces the Multi-Perspective Search Prover (MPS-Prover), a novel stepwise ATP system designed to overcome these limitations. MPS-Prover incorporates two key innovations: a highly effective post-training data curation strategy that prunes approximately 40\% of redundant training data without sacrificing performance, and a multi-perspective tree search mechanism. This search integrates a learned critic model with strategically designed heuristic rules to diversify tactic selection, prevent getting trapped in unproductive states, and enhance search robustness. Extensive evaluations demonstrate that MPS-Prover achieves state-of-the-art performance on multiple challenging benchmarks, including miniF2F and ProofNet, outperforming prior 7B parameter models. Furthermore, our analyses reveal that MPS-Prover generates significantly shorter and more diverse proofs compared to existing stepwise and whole-proof methods, highlighting its efficiency and efficacy. Our work advances the capabilities of LLM-based formal reasoning and offers a robust framework and a comprehensive analysis for developing more powerful theorem provers.

NeurIPS Conference 2025 Conference Paper

The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models

• Ke Ji
• Jiahao Xu
• Tian Liang
• Qiuzhi Liu
• Zhiwei He
• Xiaoyuan Liu
• Xingyu Chen
• Junying Chen

Improving the reasoning capabilities of large language models (LLMs) typically requires supervised fine-tuning with labeled data or computationally expensive sampling. We introduce Unsupervised Prefix Fine-Tuning (UPFT), which leverages the observation of Prefix Self-Consistency -- the shared initial reasoning steps across diverse solution trajectories -- to enhance LLM reasoning efficiency. By training exclusively on the initial prefix substrings (as few as 8 tokens), UPFT removes the need for labeled data or exhaustive sampling. Experiments on reasoning benchmarks show that UPFT matches the performance of supervised methods such as Rejection Sampling Fine-Tuning, while reducing training time by 75\% and sampling cost by 99\%. Further analysis reveals that errors tend to appear in later stages of the reasoning process and that prefix-based training preserves the model’s structural knowledge. This work demonstrates how minimal unsupervised fine-tuning can unlock substantial reasoning gains in LLMs, offering a scalable and resource-efficient alternative to conventional approaches.

NeurIPS Conference 2025 Conference Paper

Thoughts Are All Over the Place: On the Underthinking of Long Reasoning Models

• Yue Wang
• Qiuzhi Liu
• Jiahao Xu
• Tian Liang
• Xingyu Chen
• Zhiwei He
• Linfeng Song
• Dian Yu

Long reasoning models (LRMs) such as OpenAI's o1 and DeepSeek's R1 have demonstrated remarkable abilities in complex reasoning tasks by scaling test-time compute and exhibiting human-like deep thinking. However, we identify a phenomenon we term underthinking, where LRMs frequently switch between different reasoning thoughts without sufficiently exploring promising paths to reach a correct solution. This behavior leads to inadequate depth of reasoning and decreased performance, particularly on challenging mathematical problems. To systematically analyze this issue, we conduct experiments on three challenging test sets and two representative open-source LRMs, revealing that frequent thought switching correlates with incorrect responses. We introduce a novel metric to quantify underthinking by measuring token efficiency in incorrect answers. To address underthinking, we propose a decoding strategy with thought switching penalty (Tip) that discourages premature transitions between thoughts, encouraging deeper exploration of each reasoning path. Experimental results demonstrate that our approach improves accuracy across challenging datasets without requiring model fine-tuning. Our findings contribute to understanding reasoning inefficiencies in LRMs and offer a practical solution to enhance their problem-solving capabilities. Our code is open-source and available at https: //github. com/wangyuenlp/underthinking.

NeurIPS Conference 2025 Conference Paper

Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards

• Xiaoyuan Liu
• Tian Liang
• Zhiwei He
• Jiahao Xu
• Wenxuan Wang
• Pinjia He
• Zhaopeng Tu
• Haitao Mi

Large Language Models (LLMs) show great promise in complex reasoning, with Reinforcement Learning with Verifiable Rewards (RLVR) being a key enhancement strategy. However, a prevalent issue is ``superficial self-reflection'', where models fail to robustly verify their own outputs. We introduce RISE (Reinforcing Reasoning with Self-Verification), a novel online RL framework designed to tackle this. RISE explicitly and simultaneously trains an LLM to improve both its problem-solving and self-verification abilities within a single, integrated RL process. The core mechanism involves leveraging verifiable rewards from an outcome verifier to provide on-the-fly feedback for both solution generation and self-verification tasks. In each iteration, the model generates solutions, then critiques its own on-policy generated solutions, with both trajectories contributing to the policy update. Extensive experiments on diverse mathematical reasoning benchmarks show that RISE consistently improves model's problem-solving accuracy while concurrently fostering strong self-verification skills. Our analyses highlight the advantages of online verification and the benefits of increased verification compute. Additionally, RISE models exhibit more frequent and accurate self-verification behaviors during reasoning. These advantages reinforce RISE as a flexible and effective path towards developing more robust and self-aware reasoners.

NeurIPS Conference 2025 Conference Paper

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training

• Mengru Wang
• Xingyu Chen
• Yue Wang
• Zhiwei He
• Jiahao Xu
• Tian Liang
• Qiuzhi Liu
• Yunzhi Yao

Mixture-of-Experts (MoE) architectures within Large Reasoning Models (LRMs) have achieved impressive reasoning capabilities by selectively activating experts to facilitate structured cognitive processes. Despite notable advances, existing reasoning models often suffer from cognitive inefficiencies like overthinking and underthinking. To address these limitations, we introduce a novel inference-time steering methodology called Reinforcing Cognitive Experts (RICE), designed to improve reasoning depth and efficiency without additional training or complex heuristics. Leveraging normalized Pointwise Mutual Information (nPMI), we systematically identify specialized experts, termed cognitive experts that orchestrate meta-level reasoning operations characterized by tokens like. Empirical evaluations with leading MoE-based LRMs (DeepSeek-R1 and Qwen3-235B) on rigorous quantitative and scientific reasoning benchmarks (AIME and GPQA Diamond) demonstrate noticeable and consistent improvements in reasoning accuracy, cognitive efficiency, and cross-domain generalization. Crucially, our lightweight approach substantially outperforms prevalent reasoning-steering techniques, such as prompt design and decoding constraints, while preserving the model's general instruction-following skills. These results highlight reinforcing cognitive experts as a promising, practical, and interpretable direction to enhance cognitive efficiency within advanced reasoning models.

NeurIPS Conference 2025 Conference Paper

UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression

• Chenlong Deng
• Zhisong Zhang
• Kelong Mao
• Shuaiyi Li
• Tianqing Fang
• Hongming Zhang
• Haitao Mi
• Dong Yu

Large language models are increasingly capable of handling long-context inputs, but the memory overhead of KV cache remains a major bottleneck for general-purpose deployment. While many compression strategies have been explored, sequence-level compression is particularly challenging due to its tendency to lose important details. We present UniGist, a gist token-based long context compression framework that removes the need for chunk-wise training, enabling the model to learn how to compress and utilize long-range context during training. To fully exploit the sparsity, we introduce a gist shift trick that transforms the attention layout into a right-aligned block structure and develop a block-table-free sparse attention kernel based on it. UniGist further supports one-pass training and flexible chunk sizes during inference, allowing efficient and adaptive context processing. Experiments across multiple long-context tasks show that UniGist significantly improves compression quality, with especially strong performance in recalling details and long-range dependency modeling.

NeurIPS Conference 2024 Conference Paper

Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing

• Ye Tian
• Baolin Peng
• Linfeng Song
• Lifeng Jin
• Dian Yu
• Lei Han
• Haitao Mi
• Dong Yu

Despite the impressive capabilities of Large Language Models (LLMs) on various tasks, they still struggle with scenarios that involves complex reasoning and planning. Self-correction and self-learning emerge as viable solutions, employing strategies that allow LLMs to refine their outputs and learn from self-assessed rewards. Yet, the efficacy of LLMs in self-refining its response, particularly in complex reasoning and planning task, remains dubious. In this paper, we introduce AlphaLLM for the self-improvements of LLMs, which integrates Monte Carlo Tree Search (MCTS) with LLMs to establish a self-improving loop, thereby enhancing the capabilities of LLMs without additional annotations. Drawing inspiration from the success of AlphaGo, AlphaLLM addresses the unique challenges of combining MCTS with LLM for self-improvement, including data scarcity, the vastness search spaces of language tasks, and the subjective nature of feedback in language tasks. AlphaLLM is comprised of prompt synthesis component, an efficient MCTS approach tailored for language tasks, and a trio of critic models for precise feedback. Our experimental results in mathematical reasoning tasks demonstrate that AlphaLLM significantly enhances the performance of LLMs without additional annotations, showing the potential for self-improvement in LLMs.

AIJ Journal 2023 Journal Article

Search-engine-augmented dialogue response generation with cheaply supervised query production

• Ante Wang
• Linfeng Song
• Qi Liu
• Haitao Mi
• Longyue Wang
• Zhaopeng Tu
• Jinsong Su
• Dong Yu

NeurIPS Conference 2023 Conference Paper

Thrust: Adaptively Propels Large Language Models with External Knowledge

• Xinran Zhao
• Hongming Zhang
• Xiaoman Pan
• Wenlin Yao
• Dong Yu
• Jianshu Chen

Although large-scale pre-trained language models (PTLMs) are shown to encode rich knowledge in their model parameters, the inherent knowledge in PTLMs can be opaque or static, making external knowledge necessary. However, the existing information retrieval techniques could be costly and may even introduce noisy and sometimes misleading knowledge. To address these challenges, we propose the instance-level adaptive propulsion of external knowledge (IAPEK), where we only conduct the retrieval when necessary. To achieve this goal, we propose to model whether a PTLM contains enough knowledge to solve an instance with a novel metric, Thrust, which leverages the representation distribution of a small amount of seen instances. Extensive experiments demonstrate that Thrust is a good measurement of models' instance-level knowledgeability. Moreover, we can achieve higher cost-efficiency with the Thrust score as the retrieval indicator than the naive usage of external knowledge on 88% of the evaluated tasks with 26% average performance improvement. Such findings shed light on the real-world practice of knowledge-enhanced LMs with a limited budget for knowledge seeking due to computation latency or costs.

IJCAI Conference 2022 Conference Paper

FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis

• Rongjie Huang
• Max W. Y. Lam
• Jun Wang
• Dan Su
• Dong Yu
• Yi Ren
• Zhou Zhao

Denoising diffusion probabilistic models (DDPMs) have recently achieved leading performances in many generative tasks. However, the inherited iterative sampling process costs hindered their applications to speech synthesis. This paper proposes FastDiff, a fast conditional diffusion model for high-quality speech synthesis. FastDiff employs a stack of time-aware location-variable convolutions of diverse receptive field patterns to efficiently model long-term time dependencies with adaptive conditions. A noise schedule predictor is also adopted to reduce the sampling steps without sacrificing the generation quality. Based on FastDiff, we design an end-to-end text-to-speech synthesizer, FastDiff-TTS, which generates high-fidelity speech waveforms without any intermediate feature (e. g. , Mel-spectrogram). Our evaluation of FastDiff demonstrates the state-of-the-art results with higher-quality (MOS 4. 28) speech samples. Also, FastDiff enables a sampling speed of 58x faster than real-time on a V100 GPU, making diffusion models practically applicable to speech synthesis deployment for the first time. We further show that FastDiff generalized well to the mel-spectrogram inversion of unseen speakers, and FastDiff-TTS outperformed other competing methods in end-to-end text-to-speech synthesis. Audio samples are available at https: //FastDiff. github. io/.

AAAI Conference 2022 Conference Paper

Hierarchical Context Tagging for Utterance Rewriting

• Lisa Jin
• Linfeng Song
• Lifeng Jin
• Dong Yu
• Daniel Gildea

Utterance rewriting aims to recover coreferences and omitted information from the latest turn of a multi-turn dialogue. Recently, methods that tag rather than linearly generate sequences have proven stronger in both in- and out-of-domain rewriting settings. This is due to a tagger’s smaller search space as it can only copy tokens from the dialogue context. However, these methods may suffer from low coverage when phrases that must be added to a source utterance cannot be covered by a single context span. This can occur in languages like English that introduce tokens such as prepositions into the rewrite for grammaticality. We propose a hierarchical context tagger (HCT) that mitigates this issue by predicting slotted rules (e. g. , “besides ”) whose slots are later filled with context spans. HCT (i) tags the source string with token-level edit actions and slotted rules and (ii) fills in the resulting rule slots with spans from the dialogue context. This rule tagging allows HCT to add out-of-context tokens and multiple spans at once; we further cluster the rules to truncate the long tail of the rule distribution. Experiments on several benchmarks show that HCT can outperform state-of-the-art rewriting systems by ∼2 BLEU points.

AAAI Conference 2021 Conference Paper

NaturalConv: A Chinese Dialogue Dataset Towards Multi-turn Topic-driven Conversation

• Xiaoyang Wang
• Chen Li
• Jianqiao Zhao
• Dong Yu

In this paper, we propose a Chinese multi-turn topic-driven conversation dataset, NaturalConv, which allows the participants to chat anything they want as long as any element from the topic is mentioned and the topic shift is smooth. Our corpus contains 19. 9K conversations from six domains, and 400K utterances with an average turn number of 20. 1. These conversations contain in-depth discussions on related topics or widely natural transition between multiple topics. We believe either way is normal for human conversation. To facilitate the research on this corpus, we provide results of several benchmark models. Comparative results show that for this dataset, our current models are not able to provide significant improvement by introducing background knowledge/topic. Therefore, the proposed dataset should be a good benchmark for further research to evaluate the validity and naturalness of multi-turn conversation systems. Our dataset is available at https: //ai. tencent. com/ailab/nlp/dialogue/#datasets.

AAAI Conference 2021 Conference Paper

Tune-In: Training Under Negative Environments with Interference for Attention Networks Simulating Cocktail Party Effect

• Jun Wang
• Max W. Y. Lam
• Dan Su
• Dong Yu

We study the cocktail party problem and propose a novel attention network called Tune-In, abbreviated for training under negative environments with interference. It firstly learns two separate spaces of speaker-knowledge and speech-stimuli based on a shared feature space, where a new block structure is designed as the building block for all spaces, and then cooperatively solves different tasks. Between the two spaces, information is cast towards each other via a novel cross- and dual-attention mechanism, mimicking the bottom-up and topdown processes of a human’s cocktail party effect. It turns out that substantially discriminative and generalizable speaker representations can be learnt in severely interfered conditions via our self-supervised training. The experimental results verify this seeming paradox. The learnt speaker embedding has superior discriminative power than a standard speaker verification method; meanwhile, Tune-In achieves remarkably better speech separation performances in terms of SI-SNRi and SDRi consistently in all test modes, and especially at lower memory and computational consumption, than state-of-the-art benchmark systems.

AAAI Conference 2020 Conference Paper

Coordinated Reasoning for Cross-Lingual Knowledge Graph Alignment

• Kun Xu
• Linfeng Song
• Yansong Feng
• Yan Song
• Dong Yu

Existing entity alignment methods mainly vary on the choices of encoding the knowledge graph, but they typically use the same decoding method, which independently chooses the local optimal match for each source entity. This decoding method may not only cause the “many-to-one” problem but also neglect the coordinated nature of this task, that is, each alignment decision may highly correlate to the other decisions. In this paper, we introduce two coordinated reasoning methods, i. e. , the Easy-to-Hard decoding strategy and joint entity alignment algorithm. Specifically, the Easy-to- Hard strategy first retrieves the model-confident alignments from the predicted results and then incorporates them as additional knowledge to resolve the remaining model-uncertain alignments. To achieve this, we further propose an enhanced alignment model that is built on the current state-of-the-art baseline. In addition, to address the many-to-one problem, we propose to jointly predict entity alignments so that the oneto-one constraint can be naturally incorporated into the alignment prediction. Experimental results show that our model achieves the state-of-the-art performance and our reasoning methods can also significantly improve existing baselines.

AAAI Conference 2020 Conference Paper

Joint Parsing and Generation for Abstractive Summarization

• Kaiqiang Song
• Logan Lebanoff
• Qipeng Guo
• Xipeng Qiu
• Xiangyang Xue
• Chen Li
• Dong Yu
• Fei Liu

Sentences produced by abstractive summarization systems can be ungrammatical and fail to preserve the original meanings, despite being locally fluent. In this paper we propose to remedy this problem by jointly generating a sentence and its syntactic dependency parse while performing abstraction. If generating a word can introduce an erroneous relation to the summary, the behavior must be discouraged. The proposed method thus holds promise for producing grammatical sentences and encouraging the summary to stay true-to-original. Our contributions of this work are twofold. First, we present a novel neural architecture for abstractive summarization that combines a sequential decoder with a tree-based decoder in a synchronized manner to generate a summary sentence and its syntactic parse. Secondly, we describe a novel human evaluation protocol to assess if, and to what extent, a summary remains true to its original meanings. We evaluate our method on a number of summarization datasets and demonstrate competitive results against strong baselines.

AAAI Conference 2020 Conference Paper

Modeling Fluency and Faithfulness for Diverse Neural Machine Translation

• Yang Feng
• Wanying Xie
• Shuhao Gu
• Chenze Shao
• Wen Zhang
• Zhengxin Yang
• Dong Yu

Neural machine translation models usually adopt the teacher forcing strategy for training which requires the predicted sequence matches ground truth word by word and forces the probability of each prediction to approach a 0-1 distribution. However, the strategy casts all the portion of the distribution to the ground truth word and ignores other words in the target vocabulary even when the ground truth word cannot dominate the distribution. To address the problem of teacher forcing, we propose a method to introduce an evaluation module to guide the distribution of the prediction. The evaluation module accesses each prediction from the perspectives of fluency and faithfulness to encourage the model to generate the word which has a fluent connection with its past and future translation and meanwhile tends to form a translation equivalent in meaning to the source. The experiments on multiple translation tasks show that our method can achieve significant improvements over strong baselines.

AAAI Conference 2020 Conference Paper

Relation Extraction Exploiting Full Dependency Forests

• Lifeng Jin
• Linfeng Song
• Yue Zhang
• Kun Xu
• Wei-Yun Ma
• Dong Yu

Dependency syntax has long been recognized as a crucial source of features for relation extraction. Previous work considers 1-best trees produced by a parser during preprocessing. However, error propagation from the out-of-domain parser may impact the relation extraction performance. We propose to leverage full dependency forests for this task, where a full dependency forest encodes all possible trees. Such representations of full dependency forests provide a differentiable connection between a parser and a relation extraction model, and thus we are also able to study adjusting the parser parameters based on end-task loss. Experiments on three datasets show that full dependency forests and parser adjustment give significant improvements over carefully designed baselines, showing state-of-the-art or competitive performances on biomedical or newswire benchmarks.

IJCAI Conference 2019 Conference Paper

Unsupervised Neural Aspect Extraction with Sememes

• Ling Luo
• Xiang Ao
• Yan Song
• Jinyao Li
• Xiaopeng Yang
• Qing He
• Dong Yu

Aspect extraction relies on identifying aspects by discovering coherence among words, which is challenging when word meanings are diversified and processing on short texts. To enhance the performance on aspect extraction, leveraging lexical semantic resources is a possible solution to such challenge. In this paper, we present an unsupervised neural framework that leverages sememes to enhance lexical semantics. The overall framework is analogous to an autoenoder which reconstructs sentence representations and learns aspects by latent variables. Two models that form sentence representations are proposed by exploiting sememes via (1) a hierarchical attention; (2) a context-enhanced attention. Experiments on two real-world datasets demonstrate the validity and the effectiveness of our models, which significantly outperforms existing baselines.