Author name cluster

Baosong Yang

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.

11 papers

2 author rows

ICML Conference 2025 Conference Paper

ConText: Driving In-context Learning for Text Removal and Segmentation

Fei Zhang 0016
Pei Zhang 0011
Baosong Yang
Fei Huang 0002
Yanfeng Wang 0001
Ya Zhang 0002

This paper presents the first study on adapting the visual in-context learning (V-ICL) paradigm to optical character recognition tasks, specifically focusing on text removal and segmentation. Most existing V-ICL generalists employ a reasoning-as-reconstruction approach: they turn to using a straightforward image-label compositor as the prompt and query input, and then masking the query label to generate the desired output. This direct prompt confines the model to a challenging single-step reasoning process. To address this, we propose a task-chaining compositor in the form of image-removal-segmentation, providing an enhanced prompt that elicits reasoning with enriched intermediates. Additionally, we introduce context-aware aggregation, integrating the chained prompt pattern into the latent query representation, thereby strengthening the model’s in-context reasoning. We also consider the issue of visual heterogeneity, which complicates the selection of homogeneous demonstrations in text recognition. Accordingly, this is effectively addressed through a simple self-prompting strategy, preventing the model’s in-context learnability from devolving into specialist-like, context-free inference. Collectively, these insights culminate in our ConText model, which achieves new state-of-the-art across both in- and out-of-domain benchmarks. The code is available at https: //github. com/Ferenas/ConText.

Details

ICLR Conference 2025 Conference Paper

Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation

Yiming Wang 0011
Pei Zhang 0011
Baosong Yang
Derek F. Wong
Rui Wang 0015

LLM self-evaluation relies on the LLM's own ability to estimate response correctness, which can greatly improve its deployment reliability. In this research track, we propose the Chain-of-Embedding (CoE) in the latent space to enable LLMs to perform output-free self-evaluation. CoE consists of all progressive hidden states produced during the inference time, which can be treated as the latent thinking path of LLMs. We find that when LLMs respond correctly and incorrectly, their CoE features differ, these discrepancies assist us in estimating LLM response correctness. Experiments in four diverse domains and seven LLMs fully demonstrate the effectiveness of our method. Meanwhile, its label-free design intent without any training and millisecond-level computational cost ensure real-time feedback in large-scale scenarios. More importantly, we provide interesting insights into LLM response correctness from the perspective of hidden state changes inside LLMs.

Details

NeurIPS Conference 2025 Conference Paper

PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts

Yiming Wang
Pei Zhang
Jialong Tang
Hao-Ran Wei
Baosong Yang
Rui Wang
Chenshu Sun
Feitong Sun

In this paper, we introduce PolyMath, a multilingual mathematical reasoning benchmark covering 18 languages and 4 easy-to-hard difficulty levels. Our benchmark ensures difficulty comprehensiveness, language diversity, and high-quality translation, making it a highly discriminative multilingual mathematical benchmark in the era of reasoning LLMs. We conduct a comprehensive evaluation for advanced LLMs and find that even Qwen-3-235B-A22B-Thinking and Gemini-2. 5-pro, achieve only 54. 6 and 52. 2 benchmark scores, with about 40% accuracy under the highest level. From a language perspective, our benchmark reveals several key challenges of LLMs in multilingual reasoning: (1) Reasoning performance varies widely across languages for current LLMs; (2) Input-output language consistency is low in reasoning LLMs and may be correlated with performance; (3) The thinking length differs significantly by language for current LLMs. Additionally, we demonstrate that controlling the output language in the instructions has the potential to affect reasoning performance, especially for some low-resource languages, suggesting a promising direction for improving multilingual capabilities in LLMs.

PDF Details

NeurIPS Conference 2025 Conference Paper

Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding

Yiming Wang
Pei Zhang
Siyuan Huang
Baosong Yang
Zhuosheng Zhang
Fei Huang
Rui Wang

Test-time scaling enhances large language model performance by allocating additional compute resources during decoding. Best-of-$N$ (BoN) sampling serves as a common sampling-based scaling technique, broadening the search space in parallel to find better solutions from the model distribution. However, its cost–performance trade-off is still underexplored. Two main challenges limit the efficiency of BoN sampling: (1) Generating $N$ full samples consumes substantial GPU memory, reducing inference capacity under limited resources. (2) Reward models add extra memory and latency overhead, and training strong reward models introduces potential training data costs. Although some studies have explored efficiency improvements, none have addressed both challenges at once. To address this gap, we propose **Self-Truncation Best-of-$N$ (ST-BoN)**, a decoding method that avoids fully generating all $N$ samples and eliminates the need for reward models. It leverages early sampling consistency in the model’s internal states to identify the most promising path and truncate suboptimal ones. In terms of cost, ST-BoN reduces dynamic GPU memory usage by over 80% and inference latency by 50%. In terms of cost–performance trade-off, ST-BoN achieves the same performance as Full-BoN while saving computational cost by 70%–80%, and under the same cost, it can improve accuracy by 3–4 points.

PDF Details

NeurIPS Conference 2024 Conference Paper

Embedding Trajectory for Out-of-Distribution Detection in Mathematical Reasoning

Yiming Wang
Pei Zhang
Baosong Yang
Derek F. Wong
Zhuosheng Zhang
Rui Wang

Real-world data deviating from the independent and identically distributed (\textit{i. i. d. }) assumption of in-distribution training data poses security threats to deep networks, thus advancing out-of-distribution (OOD) detection algorithms. Detection methods in generative language models (GLMs) mainly focus on uncertainty estimation and embedding distance measurement, with the latter proven to be most effective in traditional linguistic tasks like summarization and translation. However, another complex generative scenario mathematical reasoning poses significant challenges to embedding-based methods due to its high-density feature of output spaces, but this feature causes larger discrepancies in the embedding shift trajectory between different samples in latent spaces. Hence, we propose a trajectory-based method TV score, which uses trajectory volatility for OOD detection in mathematical reasoning. Experiments show that our method outperforms all traditional algorithms on GLMs under mathematical reasoning scenarios and can be extended to more applications with high-density features in output spaces, such as multiple-choice questions.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

EMMA-X: An EM-like Multilingual Pre-training Algorithm for Cross-lingual Representation Learning

Ping Guo
Xiangpeng Wei
Yue Hu
Baosong Yang
Dayiheng Liu
Fei Huang
Jun Xie

Expressing universal semantics common to all languages is helpful to understand the meanings of complex and culture-specific sentences. The research theme underlying this scenario focuses on learning universal representations across languages with the usage of massive parallel corpora. However, due to the sparsity and scarcity of parallel data, there is still a big challenge in learning authentic ``universals'' for any two languages. In this paper, we propose Emma-X: an EM-like Multilingual pre-training Algorithm, to learn Cross-lingual universals with the aid of excessive multilingual non-parallel data. Emma-X unifies the cross-lingual representation learning task and an extra semantic relation prediction task within an EM framework. Both the extra semantic classifier and the cross-lingual sentence encoder approximate the semantic relation of two sentences, and supervise each other until convergence. To evaluate Emma-X, we conduct experiments on xrete, a newly introduced benchmark containing 12 widely studied cross-lingual tasks that fully depend on sentence-level representations. Results reveal that Emma-X achieves state-of-the-art performance. Further geometric analysis of the built representation space with three requirements demonstrates the superiority of Emma-X over advanced models.

PDF Details

AAAI Conference 2022 Conference Paper

Frequency-Aware Contrastive Learning for Neural Machine Translation

Tong Zhang
Wei Ye
Baosong Yang
Long Zhang
Xingzhang Ren
Dayiheng Liu
Jinan Sun
Shikun Zhang

Low-frequency word prediction remains a challenge in modern neural machine translation (NMT) systems. Recent adaptive training methods promote the output of infrequent words by emphasizing their weights in the overall training objectives. Despite the improved recall of low-frequency words, their prediction precision is unexpectedly hindered by the adaptive objectives. Inspired by the observation that lowfrequency words form a more compact embedding space, we tackle this challenge from a representation learning perspective. Specifically, we propose a frequency-aware tokenlevel contrastive learning method, in which the hidden state of each decoding step is pushed away from the counterparts of other target words, in a soft contrastive way based on the corresponding word frequencies. We conduct experiments on widely used NIST Chinese-English and WMT14 English- German translation tasks. Empirical results show that our proposed methods can not only significantly improve the translation quality but also enhance lexical diversity and optimize word representation space. Further investigation reveals that, comparing with related adaptive training strategies, the superiority of our method on low-frequency word prediction lies in the robustness of token-level recall across different frequencies without sacrificing precision.

PDF Details

AAAI Conference 2022 Conference Paper

KGR4: Retrieval, Retrospect, Refine and Rethink for Commonsense Generation

Xin Liu
Dayiheng Liu
Baosong Yang
Haibo Zhang
Junwei Ding
Wenqing Yao
Weihua Luo
Haiying Zhang

Generative commonsense reasoning requires machines to generate sentences describing an everyday scenario given several concepts, which has attracted much attention recently. However, existing models cannot perform as well as humans, since sentences they produce are often implausible and grammatically incorrect. In this paper, inspired by the process of humans creating sentences, we propose a novel Knowledgeenhanced Commonsense Generation framework, termed KGR4, consisting of four stages: Retrieval, Retrospect, Refine, Rethink. Under this framework, we first perform retrieval to search for relevant sentences from external corpus as the prototypes. Then, we train the generator that either edits or copies these prototypes to generate candidate sentences, of which potential errors will be fixed by an autoencoderbased refiner. Finally, we select the output sentence from candidate sentences produced by generators with different hyper-parameters. Experimental results and in-depth analysis on the CommonGen benchmark strongly demonstrate the effectiveness of our framework. Particularly, KGR4 obtains 33. 56 SPICE points in the official leaderboard, outperforming the previously-reported best result by 2. 49 SPICE points and achieving state-of-the-art performance. We release the code at https: //github. com/DeepLearnXMU/KGR-4.

PDF Details

AAAI Conference 2020 Conference Paper

Neuron Interaction Based Representation Composition for Neural Machine Translation

Jian Li
Xing Wang
Baosong Yang
Shuming Shi
Michael R. Lyu
Zhaopeng Tu

Recent NLP studies reveal that substantial linguistic information can be attributed to single neurons, i. e. , individual dimensions of the representation vectors. We hypothesize that modeling strong interactions among neurons helps to better capture complex information by composing the linguistic properties embedded in individual neurons. Starting from this intuition, we propose a novel approach to compose representations learned by different components in neural machine translation (e. g. , multi-layer networks or multihead attention), based on modeling strong interactions among neurons in the representation vectors. Speciﬁcally, we leverage bilinear pooling to model pairwise multiplicative interactions among individual neurons, and a low-rank approximation to make the model computationally feasible. We further propose extended bilinear pooling to incorporate ﬁrst-order representations. Experiments on WMT14 English⇒German and English⇒French translation tasks show that our model consistently improves performances over the SOTA TRANS- FORMER baseline. Further analyses demonstrate that our approach indeed captures more syntactic and semantic information as expected.

PDF Details

AAAI Conference 2020 Conference Paper

Unsupervised Neural Dialect Translation with Commonality and Diversity Modeling

Yu Wan
Baosong Yang
Derek F. Wong
Lidia S. Chao
Haihua Du
Ben C.H. Ao

As a special machine translation task, dialect translation has two main characteristics: 1) lack of parallel training corpus; and 2) possessing similar grammar between two sides of the translation. In this paper, we investigate how to exploit the commonality and diversity between dialects thus to build unsupervised translation models merely accessing to monolingual data. Speciﬁcally, we leverage pivot-private embedding, layer coordination, as well as parameter sharing to sufﬁciently model commonality and diversity among source and target, ranging from lexical, through syntactic, to semantic levels. In order to examine the effectiveness of the proposed models, we collect 20 million monolingual corpus for each of Mandarin and Cantonese, which are ofﬁcial language and the most widely used dialect in China. Experimental results reveal that our methods outperform rule-based simpli- ﬁed and traditional Chinese conversion and conventional unsupervised translation models over 12 BLEU scores.

PDF Details

AAAI Conference 2019 Conference Paper

Context-Aware Self-Attention Networks

Baosong Yang
Jian Li
Derek F. Wong
Lidia S. Chao
Xing Wang
Zhaopeng Tu

Self-attention model has shown its flexibility in parallel computation and the effectiveness on modeling both long- and short-term dependencies. However, it calculates the dependencies between representations without considering the contextual information, which has proven useful for modeling dependencies among neural representations in various natural language tasks. In this work, we focus on improving self-attention networks through capturing the richness of context. To maintain the simplicity and flexibility of the selfattention networks, we propose to contextualize the transformations of the query and key layers, which are used to calculate the relevance between elements. Specifically, we leverage the internal representations that embed both global and deep contexts, thus avoid relying on external resources. Experimental results on WMT14 English⇒German and WMT17 Chinese⇒English translation tasks demonstrate the effectiveness and universality of the proposed methods. Furthermore, we conducted extensive analyses to quantify how the context vectors participate in the self-attention model.

PDF Details