Arrow Research search

Author name cluster

Li Dong

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

37 papers
2 author rows

Possible papers

37

AAAI Conference 2026 Conference Paper

Deferred Poisoning: Making the Model More Vulnerable via Hessian Singularization

  • Yuhao He
  • Jinyu Tian
  • Xianwei Zheng
  • Li Dong
  • Yuanman Li
  • Jiantao Zhou

Recent studies have shown that deep learning models are very vulnerable to poisoning attacks. Many defense methods have been proposed to address this issue. However, traditional poisoning attacks are not as threatening as commonly believed. This is because they often cause differences in how the model performs on the training set compared to the validation set. Such inconsistency can alert defenders that their data has been poisoned, allowing them to take the necessary defensive actions. In this paper, we introduce a more threatening type of poisoning attack called the Deferred Poisoning Attack. This new attack allows the model to function normally during the training and validation phases but makes it very sensitive to evasion attacks or even natural noise. We achieve this by ensuring the poisoned model's loss function has a similar value as a normally trained model at each input sample but with a large local curvature. A similar model loss ensures that there is no obvious inconsistency between the training and validation accuracy, demonstrating high stealthiness. On the other hand, the large curvature implies that a small perturbation may cause a significant increase in model loss, leading to substantial performance degradation, which reflects a worse robustness. We fulfill this purpose by making the model have singular Hessian information at the optimal point via our proposed Singularization Regularization term. We have conducted both theoretical and empirical analyses of the proposed method and validated its effectiveness through experiments on image classification tasks. Furthermore, we have confirmed the hazards of this form of poisoning attack under more general scenarios using natural noise, offering a new perspective for research in the field of security.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Induce, Align, Predict: Zero-Shot Stance Detection via Cognitive Inductive Reasoning

  • Bowen Zhang
  • Jun Ma
  • Fuqiang Niu
  • Li Dong
  • Jinzhou Cao
  • Genan Dai

Zero-shot stance detection (ZSSD) seeks to determine the stance of text toward previously unseen targets, a task critical for analyzing dynamic and polarized online discourse with limited labeled data. While large language models (LLMs) offer zero-shot capabilities, prompting-based approaches often fall short in handling complex reasoning and lack robust generalization to novel targets. Meanwhile, LLM-enhanced methods still require substantial labeled data and struggle to move beyond instance-level patterns, limiting their interpretability and adaptability. Inspired by cognitive science, we propose the Cognitive Inductive Reasoning Framework (CIRF), a schema-driven method that bridges linguistic inputs and abstract reasoning via automatic induction and application of cognitive reasoning schemas. CIRF abstracts first-order logic patterns from raw text into multi-relational schema graphs in an unsupervised manner, and leverages a schema-enhanced graph kernel model to align input structures with schema templates for robust, interpretable zero-shot inference. Extensive experiments on SemEval-2016, VAST, and COVID-19-Stance benchmarks demonstrate that CIRF not only establishes new state-of-the-art results, but also achieves comparable performance with just 30% of the labeled data, demonstrating its strong generalization and efficiency in low-resource settings.

PDF Details DOI

JMLR Journal 2025 Journal Article

BitNet: 1-bit Pre-training for Large Language Models

  • Hongyu Wang
  • Shuming Ma
  • Lingxiao Ma
  • Lei Wang
  • Wenhui Wang
  • Li Dong
  • Shaohan Huang
  • Huaijie Wang

The increasing size of large language models (LLMs) has posed challenges for deployment and raised concerns about environmental impact due to high energy consumption. Previous research typically applies quantization after pre-training. While these methods avoid the need for model retraining, they often cause notable accuracy loss at extremely low bit-widths. In this work, we explore the feasibility and scalability of 1-bit pre-training. We introduce BitNet b1 and BitNet b1.58, the scalable and stable 1-bit Transformer architecture designed for LLMs. Specifically, we introduce BitLinear as a drop-in replacement of the nn.Linear layer in order to train 1-bit weights from scratch. Experimental results show that BitNet b1 achieves competitive performance, compared to state-of-the-art 8-bit quantization methods and FP16 Transformer baselines. With the ternary weight, BitNet b1.58 matches the half-precision Transformer LLM with the same model size and training tokens in terms of both perplexity and end-task performance, while being significantly more cost-effective in terms of latency, memory, throughput, and energy consumption. More profoundly, BitNet defines a new scaling law and recipe for training new generations of LLMs that are both high-performance and cost-effective. It enables a new computation paradigm and opens the door for designing specific hardware optimized for 1-bit LLMs. [abs] [ pdf ][ bib ] &copy JMLR 2025. ( edit, beta )

PDF Details

NeurIPS Conference 2025 Conference Paper

MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems

  • Yinsicheng Jiang
  • Yao Fu
  • Yeqi Huang
  • Ping Nie
  • Zhan Lu
  • Leyang Xue
  • Congjie He
  • Man-Kit Sit

The sparse Mixture-of-Experts (MoE) architecture is increasingly favored for scaling Large Language Models (LLMs) efficiently, but it depends on heterogeneous compute and memory resources. These factors jointly affect system Cost, Accuracy, and Performance (CAP), making trade-offs inevitable. Existing benchmarks often fail to capture these trade-offs accurately, complicating practical deployment decisions. To address this, we introduce MoE-CAP, a benchmark specifically designed for MoE systems. Our analysis reveals that achieving an optimal balance across CAP is difficult with current hardware; MoE systems typically optimize two of the three dimensions at the expense of the third—a dynamic we term the MoE-CAP trade-off. To visualize this, we propose the CAP Radar Diagram. We further introduce sparsity-aware performance metrics—Sparse Memory Bandwidth Utilization (S-MBU) and Sparse Model FLOPS Utilization (S-MFU)—to enable accurate performance benchmarking of MoE systems across diverse hardware platforms and deployment scenarios. This benchmark is available on Github: https: //github. com/sparse-generative-ai/MoE-CAP.

PDF Details

NeurIPS Conference 2025 Conference Paper

Reward Reasoning Models

  • Jiaxin Guo
  • Zewen Chi
  • Li Dong
  • Qingxiu Dong
  • Xun Wu
  • Shaohan Huang
  • Furu Wei

Reward models play a critical role in guiding large language models toward outputs that align with human expectations. However, an open challenge remains in effectively utilizing test-time compute to enhance reward model performance. In this work, we introduce Reward Reasoning Models (RRMs), which are specifically designed to execute a deliberate reasoning process before generating final rewards. Through chain-of-thought reasoning, RRMs leverage additional test-time compute for complex queries where appropriate rewards are not immediately apparent. To develop RRMs, we implement a reinforcement learning framework that fosters self-evolved reward reasoning capabilities without requiring explicit reasoning traces as training data. Experimental results demonstrate that RRMs achieve superior performance on reward modeling benchmarks across diverse domains. Notably, we show that RRMs can adaptively exploit test-time compute to further improve reward accuracy. The pretrained models are available at https: //huggingface. co/Reward-Reasoning.

PDF Details

TMLR Journal 2025 Journal Article

Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models

  • Haoran Li
  • Qingxiu Dong
  • Zhengyang Tang
  • Chaojun Wang
  • Xingxing Zhang
  • Haoyang Huang
  • Shaohan Huang
  • Xiaolong Huang

We introduce Generalized Instruction Tuning (called GLAN), a general and scalable method for instruction tuning of Large Language Models (LLMs). Unlike prior work that relies on seed examples or existing datasets to construct instruction-tuning data, GLAN exclusively utilizes a pre-curated taxonomy of human knowledge and capabilities as input and generates large-scale synthetic instruction data across all disciplines. Specifically, inspired by the systematic structure in human education system, we build the taxonomy by decomposing human knowledge and capabilities to various fields, sub-fields and ultimately, distinct disciplines semi-automatically, facilitated by LLMs. Subsequently, we generate a comprehensive list of subjects for every discipline and proceed to design a syllabus tailored to each subject, again utilizing LLMs. With the fine-grained key concepts detailed in every class session of the syllabus, we are able to generate diverse instructions with a broad coverage across the entire spectrum of human knowledge and skills. Extensive experiments on large language models (e.g., Mistral) demonstrate that GLAN excels in multiple dimensions from mathematical reasoning, coding, academic exams, logical reasoning to general instruction following without using task-specific training data of these tasks. In addition, GLAN allows for easy customization and new fields or skills can be added by simply incorporating a new node into our taxonomy. While promising, our approach may inherit biases or inaccuracies from LLM-generated data as in other synthetic data work and is primarily evaluated on exam-style benchmarks. Broader evaluations and data quality control are left for future work.

PDF Details

NeurIPS Conference 2025 Conference Paper

Think Only When You Need with Large Hybrid-Reasoning Models

  • Lingjie Jiang
  • Xun Wu
  • Shaohan Huang
  • Qingxiu Dong
  • Zewen Chi
  • Li Dong
  • Xingxing Zhang
  • Tengchao Lv

Recent Large Reasoning Models (LRMs) have shown substantially improved reasoning capabilities over traditional Large Language Models (LLMs) by incorporating extended thinking processes prior to producing final responses. However, excessively lengthy thinking introduces substantial overhead in terms of token consumption and latency, which is unnecessary for simple queries. In this work, we introduce Large Hybrid-Reasoning Models (LHRMs), the first kind of model capable of adaptively determining whether to perform reasoning based on the contextual information of user queries. To achieve this, we propose a two-stage training pipeline comprising Hybrid Fine-Tuning (HFT) as a cold start, followed by online reinforcement learning with the proposed Hybrid Group Policy Optimization (HGPO) to implicitly learn to select the appropriate reasoning mode. Furthermore, we introduce a metric called Hybrid Accuracy to quantitatively assess the model’s capability for hybrid reasoning. Extensive experimental results show that LHRMs can adaptively perform hybrid reasoning on queries of varying difficulty and type. It outperforms existing LRMs and LLMs in reasoning and general capabilities while significantly improving efficiency. Together, our work advocates for a reconsideration of the appropriate use of extended reasoning processes and provides a solid starting point for building hybrid reasoning systems.

PDF Details

NeurIPS Conference 2024 Conference Paper

Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models

  • Wenshan Wu
  • Shaoguang Mao
  • Yadong Zhang
  • Yan Xia
  • Li Dong
  • Lei Cui
  • Furu Wei

Large language models (LLMs) have exhibited impressive performance in language comprehension and various reasoning tasks. However, their abilities in spatial reasoning, a crucial aspect of human cognition, remain relatively unexplored. Human possess a remarkable ability to create mental images of unseen objects and actions through a process known as the Mind's Eye, enabling the imagination of the unseen world. Inspired by this cognitive capacity, we propose Visualization-of-Thought (VoT) prompting. VoT aims to elicit spatial reasoning of LLMs by visualizing their reasoning traces, thereby guiding subsequent reasoning steps. We employed VoT for multi-hop spatial reasoning tasks, including natural language navigation, visual navigation, and visual tiling in 2D grid worlds. Experimental results demonstrated that VoT significantly enhances the spatial reasoning abilities of LLMs. Notably, VoT outperformed existing multimodal large language models (MLLMs) in these tasks. While VoT works surprisingly well on LLMs, the ability to generate mental images to facilitate spatial reasoning resembles the mind's eye process, suggesting its potential viability in MLLMs. Please find the dataset and codes in our project page.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Multi-Head Mixture-of-Experts

  • Xun Wu
  • Shaohan Huang
  • Wenhui Wang
  • Shuming Ma
  • Li Dong
  • Furu Wei

Sparse Mixtures of Experts (SMoE) scales model capacity without significant increases in computational costs. However, it exhibits the low expert activation issue, i. e. , only a small subset of experts are activated for optimization, leading to suboptimal performance and limiting its effectiveness in learning a larger number of experts in complex tasks. In this paper, we propose Multi-Head Mixture-of-Experts (MH-MoE). MH-MoE split each input token into multiple sub-tokens, then these sub-tokens are assigned to and processed by a diverse set of experts in parallel, and seamlessly reintegrated into the original token form. The above operations enables MH-MoE to significantly enhance expert activation while collectively attend to information from various representation spaces within different experts to deepen context understanding. Besides, it's worth noting that our MH-MoE is straightforward to implement and decouples from other SMoE frameworks, making it easy to integrate with these frameworks for enhanced performance. Extensive experimental results across different parameter scales (300M to 7B) and three pre-training tasks—English-focused language modeling, multi-lingual language modeling and masked multi-modality modeling—along with multiple downstream validation tasks, demonstrate the effectiveness of MH-MoE.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

You Only Cache Once: Decoder-Decoder Architectures for Language Models

  • Yutao Sun
  • Li Dong
  • Yi Zhu
  • Shaohan Huang
  • Wenhui Wang
  • Shuming Ma
  • Quanlu Zhang
  • Jianyong Wang

We introduce a decoder-decoder architecture, YOCO, for large language models, which only caches key-value pairs once. It consists of two components, i. e. , a cross-decoder stacked upon a self-decoder. The self-decoder efficiently encodes global key-value (KV) caches that are reused by the cross-decoder via cross-attention. The overall model behaves like a decoder-only Transformer, although YOCO only caches once. The design substantially reduces GPU memory demands, yet retains global attention capability. Additionally, the computation flow enables prefilling to early exit without changing the final output, thereby significantly speeding up the prefill stage. Experimental results demonstrate that YOCO achieves favorable performance compared to Transformer in various settings of scaling up model size and number of training tokens. We also extend YOCO to 1M context length with near-perfect needle retrieval accuracy. The profiling results show that YOCO improves inference memory, prefill latency, and throughput by orders of magnitude across context lengths and model sizes.

PDF Details DOI

TMLR Journal 2023 Journal Article

A Unified View of Masked Image Modeling

  • Zhiliang Peng
  • Li Dong
  • Hangbo Bao
  • Furu Wei
  • Qixiang Ye

Masked image modeling has demonstrated great potential to eliminate the label-hungry problem of training large-scale vision Transformers, achieving impressive performance on various downstream tasks. In this work, we propose a unified view of masked image modeling after revisiting existing methods. Under the unified view, we introduce a simple yet effective method, termed as MaskDistill, which reconstructs normalized semantic features from teacher models at the masked positions, conditioning on corrupted input images. Experimental results on image classification and semantic segmentation show that MaskDistill achieves comparable or superior performance than state-of-the-art methods. When using the huge vision Transformer and pretraining 300 epochs, MaskDistill obtains 88.3% fine-tuning top-1 accuracy on ImageNet-1k (224 size) and 58.8 semantic segmentation mIoU metric on ADE20k (512 size). Code is enclosed in the supplementary materials.

PDF Details

NeurIPS Conference 2023 Conference Paper

Augmenting Language Models with Long-Term Memory

  • Weizhi Wang
  • Li Dong
  • Hao Cheng
  • Xiaodong Liu
  • Xifeng Yan
  • Jianfeng Gao
  • Furu Wei

Existing large language models (LLMs) can only afford fix-sized inputs due to the input length limit, preventing them from utilizing rich long-context information from past inputs. To address this, we propose a framework, Language Models Augmented with Long-Term Memory (LongMem), which enables LLMs to memorize long history. We design a novel decoupled network architecture with the original backbone LLM frozen as a memory encoder and an adaptive residual side-network as a memory retriever and reader. Such a decoupled memory design can easily cache and update long-term past contexts for memory retrieval without suffering from memory staleness. Enhanced with memory-augmented adaptation training, LongMem can thus memorize long past context and use long-term memory for language modeling. The proposed memory retrieval module can handle unlimited-length context in its memory bank to benefit various downstream tasks. Typically, LongMem can enlarge the long-form memory to 65k tokens and thus cache many-shot extra demonstration examples as long-form memory for in-context learning. Experiments show that our method outperforms strong long-context models on ChapterBreak, a challenging long-context modeling benchmark, and achieves remarkable improvements on memory-augmented in-context learning over LLMs. The results demonstrate that the proposed method is effective in helping language models to memorize and utilize long-form contents.

PDF Details

NeurIPS Conference 2023 Conference Paper

Extensible Prompts for Language Models on Zero-shot Language Style Customization

  • Tao Ge
  • Hu Jing
  • Li Dong
  • Shaoguang Mao
  • Yan Xia
  • Xun Wang
  • Si-Qing Chen
  • Furu Wei

We propose eXtensible Prompt (X-Prompt) for prompting a large language model (LLM) beyond natural language (NL). X-Prompt instructs an LLM with not only NL but also an extensible vocabulary of imaginary words. Registering new imaginary words allows us to instruct the LLM to comprehend concepts that are difficult to describe with NL words, thereby making a prompt more descriptive. Also, these imaginary words are designed to be out-of-distribution (OOD) robust so that they can be (re)used like NL words in various prompts, distinguishing X-Prompt from soft prompt that is for fitting in-distribution data. We propose context-augmented learning (CAL) to learn imaginary words for general usability, enabling them to work properly in OOD (unseen) prompts. We experiment X-Prompt for zero-shot language style customization as a case study. The promising results of X-Prompt demonstrate its potential to facilitate advanced interaction beyond the natural language interface, bridging the communication gap between humans and LLMs.

PDF Details

NeurIPS Conference 2023 Conference Paper

Language Is Not All You Need: Aligning Perception with Language Models

  • Shaohan Huang
  • Li Dong
  • Wenhui Wang
  • Yaru Hao
  • Saksham Singhal
  • Shuming Ma
  • Tengchao Lv
  • Lei Cui

A big convergence of language, multimodal perception, action, and world modeling is a key step toward artificial general intelligence. In this work, we introduce KOSMOS-1, a Multimodal Large Language Model (MLLM) that can perceive general modalities, learn in context (i. e. , few-shot), and follow instructions (i. e. , zero-shot). Specifically, we train KOSMOS-1 from scratch on web-scale multi-modal corpora, including arbitrarily interleaved text and images, image-caption pairs, and text data. We evaluate various settings, including zero-shot, few-shot, and multimodal chain-of-thought prompting, on a wide range of tasks without any gradient updates or finetuning. Experimental results show that KOSMOS-1 achieves impressive performance on (i) language understanding, generation, and even OCR-free NLP (directly fed with document images), (ii) perception-language tasks, including multimodal dialogue, image captioning, visual question answering, and (iii) vision tasks, such as image recognition with descriptions (specifying classification via text instructions). We also show that MLLMs can benefit from cross-modal transfer, i. e. , transfer knowledge from language to multimodal, and from multimodal to language. In addition, we introduce a dataset of Raven IQ test, which diagnoses the nonverbal reasoning capability of MLLMs.

PDF Details

NeurIPS Conference 2023 Conference Paper

Optimizing Prompts for Text-to-Image Generation

  • Yaru Hao
  • Zewen Chi
  • Li Dong
  • Furu Wei

Well-designed prompts can guide text-to-image models to generate amazing images. However, the performant prompts are often model-specific and misaligned with user input. Instead of laborious human engineering, we propose prompt adaptation, a general framework that automatically adapts original user input to model-preferred prompts. Specifically, we first perform supervised fine-tuning with a pretrained language model on a small collection of manually engineered prompts. Then we use reinforcement learning to explore better prompts. We define a reward function that encourages the policy to generate more aesthetically pleasing images while preserving the original user intentions. Experimental results on Stable Diffusion show that our method outperforms manual prompt engineering in terms of both automatic metrics and human preference ratings. Moreover, reinforcement learning further boosts performance, especially on out-of-domain prompts.

PDF Details

ICML Conference 2023 Conference Paper

Semi-Offline Reinforcement Learning for Optimized Text Generation

  • Changyu Chen
  • Xiting Wang
  • Yiqiao Jin
  • Victor Ye Dong
  • Li Dong
  • Jie Cao
  • Yi Liu
  • Rui Yan 0001

Existing reinforcement learning (RL) mainly utilize online or offline settings. The online methods explore the environment with expensive time cost, and the offline methods efficiently obtain reward signals by sacrificing the exploration capability. We propose semi-offline RL, a novel paradigm that can smoothly transit from the offline setting to the online setting, balances the exploration capability and training cost, and provides a theoretical foundation for comparing different RL settings. Based on the semi-offline MDP formulation, we present the RL setting that is optimal in terms of optimization cost, asymptotic error, and overfitting error bound. Extensive experiments show that our semi-offline RL approach is effective in various text generation tasks and datasets, and yields comparable or usually better performance compared with the state-of-the-art methods.

Details

NeurIPS Conference 2022 Conference Paper

On the Representation Collapse of Sparse Mixture of Experts

  • Zewen Chi
  • Li Dong
  • Shaohan Huang
  • Damai Dai
  • Shuming Ma
  • Barun Patra
  • Saksham Singhal
  • Payal Bajaj

Sparse mixture of experts provides larger model capacity while requiring a constant computational overhead. It employs the routing mechanism to distribute input tokens to the best-matched experts according to their hidden representations. However, learning such a routing mechanism encourages token clustering around expert centroids, implying a trend toward representation collapse. In this work, we propose to estimate the routing scores between tokens and experts on a low-dimensional hypersphere. We conduct extensive experiments on cross-lingual language model pre-training and fine-tuning on downstream tasks. Experimental results across seven multilingual benchmarks show that our method achieves consistent gains. We also present a comprehensive analysis on the representation and routing behaviors of our models. Our method alleviates the representation collapse issue and achieves more consistent routing than the baseline mixture-of-experts methods.

PDF Details

NeurIPS Conference 2022 Conference Paper

VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts

  • Hangbo Bao
  • Wenhui Wang
  • Li Dong
  • Qiang Liu
  • Owais Khan Mohammed
  • Kriti Aggarwal
  • Subhojit Som
  • Songhao Piao

We present a unified Vision-Language pretrained Model (VLMo) that jointly learns a dual encoder and a fusion encoder with a modular Transformer network. Specifically, we introduce Multiway Transformer, where each block contains a pool of modality-specific experts and a shared self-attention layer. Because of the modeling flexibility of Multiway Transformer, pretrained VLMo can be fine-tuned as a fusion encoder for vision-language classification tasks, or used as a dual encoder for efficient image-text retrieval. Moreover, we propose a stagewise pre-training strategy, which effectively leverages large-scale image-only and text-only data besides image-text pairs. Experimental results show that VLMo achieves state-of-the-art results on various vision-language tasks, including VQA, NLVR2 and image-text retrieval.

PDF Details

AAAI Conference 2021 Conference Paper

Self-Attention Attribution: Interpreting Information Interactions Inside Transformer

  • Yaru Hao
  • Li Dong
  • Furu Wei
  • Ke Xu

The great success of Transformer-based models benefits from the powerful multi-head self-attention mechanism, which learns token dependencies and encodes contextual information from the input. Prior work strives to attribute model decisions to individual input features with different saliency measures, but they fail to explain how these input features interact with each other to reach predictions. In this paper, we propose a self-attention attribution method to interpret the information interactions inside Transformer. We take BERT as an example to conduct extensive studies. Firstly, we apply selfattention attribution to identify the important attention heads, while others can be pruned with marginal performance degradation. Furthermore, we extract the most salient dependencies in each layer to construct an attribution tree, which reveals the hierarchical interactions inside Transformer. Finally, we show that the attribution results can be used as adversarial patterns to implement non-targeted attacks towards BERT.

PDF Details

JBHI Journal 2021 Journal Article

Self-Ensembling Co-Training Framework for Semi-Supervised COVID-19 CT Segmentation

  • Caizi Li
  • Li Dong
  • Qi Dou
  • Fan Lin
  • Kebao Zhang
  • Zuxin Feng
  • Weixin Si
  • Xuesong Deng

The coronavirus disease 2019 (COVID-19) has become a severe worldwide health emergency and is spreading at a rapid rate. Segmentation of COVID lesions from computed tomography (CT) scans is of great importance for supervising disease progression and further clinical treatment. As labeling COVID-19 CT scans is labor-intensive and time-consuming, it is essential to develop a segmentation method based on limited labeled data to conduct this task. In this paper, we propose a self-ensembled co-training framework, which is trained by limited labeled data and large-scale unlabeled data, to automatically extract COVID lesions from CT scans. Specifically, to enrich the diversity of unsupervised information, we build a co-training framework consisting of two collaborative models, in which the two models teach each other during training by using their respective predicted pseudo-labels of unlabeled data. Moreover, to alleviate the adverse impacts of noisy pseudo-labels for each model, we propose a self-ensembling strategy to perform consistency regularization for the up-to-date predictions of unlabeled data, in which the predictions of unlabeled data are gradually ensembled via moving average at the end of every training epoch. We evaluate our framework on a COVID-19 dataset containing 103 CT scans. Experimental results show that our proposed method achieves better performance in the case of only 4 labeled CT scans compared to the state-of-the-art semi-supervised segmentation networks.

Details DOI

AAAI Conference 2020 Conference Paper

Cross-Lingual Natural Language Generation via Pre-Training

  • Zewen Chi
  • Li Dong
  • Furu Wei
  • Wenhui Wang
  • Xian-Ling Mao
  • Heyan Huang

In this work we focus on transferring supervision signals of natural language generation (NLG) tasks between multiple languages. We propose to pretrain the encoder and the decoder of a sequence-to-sequence model under both monolingual and cross-lingual settings. The pre-training objective encourages the model to represent different languages in the shared space, so that we can conduct zero-shot cross-lingual transfer. After the pre-training procedure, we use monolingual data to fine-tune the pre-trained model on downstream NLG tasks. Then the sequence-to-sequence model trained in a single language can be directly evaluated beyond that language (i. e. , accepting multi-lingual input and producing multi-lingual output). Experimental results on question generation and abstractive summarization show that our model outperforms the machine-translation-based pipeline methods for zero-shot cross-lingual generation. Moreover, crosslingual transfer improves NLG performance of low-resource languages by leveraging rich-resource language data. Our implementation and data are available at https: //github. com/ CZWin32768/xnlg.

PDF Details

NeurIPS Conference 2020 Conference Paper

MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers

  • Wenhui Wang
  • Furu Wei
  • Li Dong
  • Hangbo Bao
  • Nan Yang
  • Ming Zhou

Pre-trained language models (e. g. , BERT (Devlin et al. , 2018) and its variants) have achieved remarkable success in varieties of NLP tasks. However, these models usually consist of hundreds of millions of parameters which brings challenges for fine-tuning and online serving in real-life applications due to latency and capacity constraints. In this work, we present a simple and effective approach to compress large Transformer (Vaswani et al. , 2017) based pre-trained models, termed as deep self-attention distillation. The small model (student) is trained by deeply mimicking the self-attention module, which plays a vital role in Transformer networks, of the large model (teacher). Specifically, we propose distilling the self-attention module of the last Transformer layer of the teacher, which is effective and flexible for the student. Furthermore, we introduce the scaled dot-product between values in the self-attention module as the new deep self-attention knowledge, in addition to the attention distributions (i. e. , the scaled dot-product of queries and keys) that have been used in existing works. Moreover, we show that introducing a teacher assistant (Mirzadeh et al. , 2019) also helps the distillation of large pre-trained Transformer models. Experimental results demonstrate that our monolingual model outperforms state-of-the-art baselines in different parameter size of student models. In particular, it retains more than 99% accuracy on SQuAD 2. 0 and several GLUE benchmark tasks using 50% of the Transformer parameters and computations of the teacher model. We also obtain competitive results in applying deep self-attention distillation to multilingual pre-trained models.

PDF Details

AAAI Conference 2019 Conference Paper

Data-to-Text Generation with Content Selection and Planning

  • Ratish Puduppully
  • Li Dong
  • Mirella Lapata

Recent advances in data-to-text generation have led to the use of large-scale datasets and neural network models which are trained end-to-end, without explicitly modeling what to say and in what order. In this work, we present a neural network architecture which incorporates content selection and planning without sacrificing end-to-end training. We decompose the generation task into two stages. Given a corpus of data records (paired with descriptive documents), we first generate a content plan highlighting which information should be mentioned and in which order and then generate the document while taking the content plan into account. Automatic and human-based evaluation experiments show that our model1 outperforms strong baselines improving the state-of-the-art on the recently released ROTOWIRE dataset.

PDF Details

NeurIPS Conference 2019 Conference Paper

Unified Language Model Pre-training for Natural Language Understanding and Generation

  • Li Dong
  • Nan Yang
  • Wenhui Wang
  • Furu Wei
  • Xiaodong Liu
  • Yu Wang
  • Jianfeng Gao
  • Ming Zhou

This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks. The model is pre-trained using three types of language modeling tasks: unidirectional, bidirectional, and sequence-to-sequence prediction. The unified modeling is achieved by employing a shared Transformer network and utilizing specific self-attention masks to control what context the prediction conditions on. UniLM compares favorably with BERT on the GLUE benchmark, and the SQuAD 2. 0 and CoQA question answering tasks. Moreover, UniLM achieves new state-of-the-art results on five natural language generation datasets, including improving the CNN/DailyMail abstractive summarization ROUGE-L to 40. 51 (2. 04 absolute improvement), the Gigaword abstractive summarization ROUGE-L to 35. 75 (0. 86 absolute improvement), the CoQA generative question answering F1 score to 82. 5 (37. 1 absolute improvement), the SQuAD question generation BLEU-4 to 22. 12 (3. 75 absolute improvement), and the DSTC7 document-grounded dialog response generation NIST-4 to 2. 67 (human performance is 2. 65). The code and pre-trained models are available at https: //github. com/microsoft/unilm.

PDF Details

IJCAI Conference 2016 Conference Paper

Unsupervised Word and Dependency Path Embeddings for Aspect Term Extraction

  • Yichun Yin
  • Furu Wei
  • Li Dong
  • Kaimeng Xu
  • Ming Zhang
  • Ming Zhou

In this paper, we develop a novel approach to aspect term extraction based on unsupervised learning of distributed representations of words and dependency paths. The basic idea is to connect two words (w1 and w2) with the dependency path (r) between them in the embedding space. Specifically, our method optimizes the objective w1 + r ≈ w2 in the low-dimensional space, where the multi-hop dependency paths are treated as a sequence of grammatical relations and modeled by a recurrent neural network. Then, we design the embedding features that consider linear context and dependency context information, for the conditional random field (CRF) based aspect term extraction. Experimental results on the SemEval datasets show that, (1) with only embedding features, we can achieve state-of-the-art results; (2) our embedding method which incorporates the syntactic information among words yields better performance than other representative ones in aspect term extraction.

PDF Details

IJCAI Conference 2015 Conference Paper

A Hybrid Neural Model for Type Classification of Entity Mentions

  • Li Dong
  • Furu Wei
  • Hong Sun
  • Ming Zhou
  • Ke Xu

The semantic class (i. e. , type) of an entity plays a vital role in many natural language processing tasks, such as question answering. However, most of existing type classification systems extensively rely on hand-crafted features. This paper introduces a hybrid neural model which classifies entity mentions to a wide-coverage set of 22 types derived from DBpedia. It consists of two parts. The mention model uses recurrent neural networks to recursively obtain the vector representation of an entity mention from the words it contains. The context model, on the other hand, employs multilayer perceptrons to obtain the hidden representation for contextual information of a mention. Representations obtained by the two parts are used together to predict the type distribution. Using automatically generated data, these two parts are jointly learned. Experimental studies illustrate that the proposed approach outperforms baseline methods. Moreover, when type information provided by our method is used in a question answering system, we observe a 14. 7% relative improvement for the top-1 accuracy of answers.

PDF Details

AAAI Conference 2015 Conference Paper

Ranking with Recursive Neural Networks and Its Application to Multi-Document Summarization

  • Ziqiang Cao
  • Furu Wei
  • Li Dong
  • Sujian Li
  • Ming Zhou

We develop a Ranking framework upon Recursive Neural Networks (R2N2) to rank sentences for multi-document summarization. It formulates the sentence ranking task as a hierarchical regression process, which simultaneously measures the salience of a sentence and its constituents (e. g. , phrases) in the parsing tree. This enables us to draw on word-level to sentence-level supervisions derived from reference summaries. In addition, recursive neural networks are used to automatically learn ranking features over the tree, with hand-crafted feature vectors of words as inputs. Hierarchical regressions are then conducted with learned features concatenating raw features. Ranking scores of sentences and words are utilized to effectively select informative and nonredundant sentences to generate summaries. Experiments on the DUC 2001, 2002 and 2004 multi-document summarization datasets show that R2N2 outperforms state-of-the-art extractive summarization approaches.

PDF Details

AAAI Conference 2014 Conference Paper

Adaptive Multi-Compositionality for Recursive Neural Models with Applications to Sentiment Analysis

  • Li Dong
  • Furu Wei
  • Ming Zhou
  • Ke Xu

Recursive neural models have achieved promising results in many natural language processing tasks. The main difference among these models lies in the composition function, i. e. , how to obtain the vector representation for a phrase or sentence using the representations of words it contains. This paper introduces a novel Adaptive Multi-Compositionality (AdaMC) layer to recursive neural models. The basic idea is to use more than one composition functions and adaptively select them depending on the input vectors. We present a general framework to model each semantic composition as a distribution over these composition functions. The composition functions and parameters used for adaptive selection are learned jointly from data. We integrate AdaMC into existing recursive neural models and conduct extensive experiments on the Stanford Sentiment Treebank. The results illustrate that AdaMC significantly outperforms state-of-the-art sentiment classification methods. It helps push the best accuracy of sentence-level negative/positive classification from 85. 4% up to 88. 5%.

PDF Details

AAAI Conference 2013 Conference Paper

The Automated Acquisition of Suggestions from Tweets

  • Li Dong
  • Furu Wei
  • Yajuan Duan
  • Xiaohua Liu
  • Ming Zhou
  • Ke Xu

This paper targets at automatically detecting and classifying user’s suggestions from tweets. The short and informal nature of tweets, along with the imbalanced characteristics of suggestion tweets, makes the task extremely challenging. To this end, we develop a classification framework on Factorization Machines, which is effective and efficient especially in classification tasks with feature sparsity settings. Moreover, we tackle the imbalance problem by introducing cost-sensitive learning techniques in Factorization Machines. Extensively experimental studies on a manually annotated real-life data set show that the proposed approach significantly improves the baseline approach, and yields the precision of 71. 06% and recall of 67. 86%. We also investigate the reason why Factorization Machines perform better. Finally, we introduce the first manually annotated dataset for suggestion classification.

PDF Details

IROS Conference 2007 Conference Paper

An algorithm for extrinsic parameters calibration of a camera and a laser range finder using line features

  • Ganhua Li
  • Yun-Hui Liu 0001
  • Li Dong
  • Xuanping Cai
  • Dongxiang Zhou

This paper presents an effective algorithm for calibrating the extrinsic parameters between a camera and a laser range finder whose trace is invisible. On the basis of an analysis of three possible features, we propose to design a right-angled triangular checkerboard and to employ the invisible intersection points of the laser range finder’s slice plane with the edges of the checkerboard to set up the constraints equations. The extrinsic parameters are then calibrated by minimizing the algebraic errors between the measured intersections points and their corresponding projections on the image plane of the camera. We compared our algorithm with the existing methods by both simulations and the real data of a stereo measurement system. The simulation and experimental results confirmed that the proposed algorithm can yield more accurate results.

Details