244 citations · 336 across the 24 of their papers we have counts for
27 papers
CoTEvol: Self-Evolving Chain-of-Thoughts for Data Synthesis in Mathematical Reasoning
Zhuo Wang, Zhuo Zhang, Yafu Li +3
Large Language Models (LLMs) exhibit strong mathematical reasoning when trained on high-quality Chain-of-Thought (CoT) that articulates intermediate steps, yet costly CoT curation…
Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation
Song Wang, Zihan Chen, Peng Wang +5
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge sources to address their limitations in accessing up-to-date or special…
Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models
Tingchen Fu, Jiawei Gu, Yafu Li +2
Instruction-following is essential for aligning large language models (LLMs) with user intent. While recent reasoning-oriented models exhibit impressive performance on complex math…
SEE: Continual Fine-tuning with Sequential Ensemble of Experts
Zhilin Wang, Yafu Li, Xiaoye Qu +1
Continual fine-tuning of large language models (LLMs) suffers from catastrophic forgetting. Rehearsal-based methods mitigate this problem by retaining a small set of old data. Neve…
Learning to Reason under Off-Policy Guidance
Jianhao Yan, Yafu Li, Zican Hu +5
Recent advances in large reasoning models (LRMs) demonstrate that sophisticated behaviors such as multi-step reasoning and self-reflection can emerge via reinforcement learning wit…
Lost in Literalism: How Supervised Training Shapes Translationese in LLMs
Yafu Li, Ronghao Zhang, Zhilin Wang +5
Large language models (LLMs) have achieved remarkable success in machine translation, demonstrating impressive performance across diverse languages. However, translationese, charac…
A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond
Xiaoye Qu, Yafu Li, Zhao-Chen Su +15
Recent Large Reasoning Models (LRMs), such as DeepSeek-R1 and OpenAI o1, have demonstrated strong performance gains by scaling up the length of Chain-of-Thought (CoT) reasoning dur…
Multi-LLM Collaborative Search for Complex Problem Solving
Sen Yang, Yafu Li, Wai Lam +1
Large language models (LLMs) often struggle with complex reasoning tasks due to their limitations in addressing the vast reasoning space and inherent ambiguities of natural languag…
Unveiling Attractor Cycles in Large Language Models: A Dynamical Systems View of Successive Paraphrasing
Zhilin Wang, Yafu Li, Jianhao Yan +2
Dynamical systems theory provides a framework for analyzing iterative processes and evolution over time. Within such systems, repetitive transformations can lead to stable configur…
Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback
Yafu Li, Xuyang Hu, Xiaoye Qu +2
Large language models (LLMs) demonstrate impressive performance but lack the flexibility to adapt to human preferences quickly without retraining. In this work, we introduce Test-t…
From Drafts to Answers: Unlocking LLM Potential via Aggregation Fine-Tuning
Yafu Li, Zhilin Wang, Tingchen Fu +3
Scaling data and model size has been proven effective for boosting the performance of large language models. In addition to training-time scaling, recent studies have revealed that…
Keys to Robust Edits: from Theoretical Insights to Practical Advances
Jianhao Yan, Futing Wang, Yun Luo +2
Large language models (LLMs) struggle with maintaining accurate knowledge due to conflicting/outdated parametric memories. While locate-and-edit methods address this, their relianc…
LexMatcher: Dictionary-centric Data Collection for LLM-based Machine Translation
Yongjing Yin, Jiali Zeng, Yafu Li +2
The fine-tuning of open-source large language models (LLMs) for machine translation has recently received considerable attention, marking a shift towards data-centric research from…
Spotting AI's Touch: Identifying LLM-Paraphrased Spans in Text
Yafu Li, Zhilin Wang, Leyang Cui +3
AI-generated text detection has attracted increasing attention as powerful language models approach human-level generation. Limited work is devoted to detecting (partially) AI-para…
What Have We Achieved on Non-autoregressive Translation?
Yafu Li, Huajian Zhang, Jianhao Yan +2
Recent advances have made non-autoregressive (NAT) translation comparable to autoregressive methods (AT). However, their evaluation using BLEU has been shown to weakly correlate wi…
MCRanker: Generating Diverse Criteria On-the-Fly to Improve Point-wise LLM Rankers
Fang Guo, Wenyu Li, Honglei Zhuang +5
The most recent pointwise Large Language Model (LLM) rankers have achieved remarkable ranking results. However, these rankers are hindered by two major drawbacks: (1) they fail to…
Potential and Challenges of Model Editing for Social Debiasing
Jianhao Yan, Futing Wang, Yafu Li +1
Large language models (LLMs) trained on vast corpora suffer from inevitable stereotype biases. Mitigating these biases with fine-tuning could be both costly and data-hungry. Model…
Understanding In-Context Learning from Repetitions
Jianhao Yan, Jin Xu, Chiyu Song +3
This paper explores the elusive mechanism underpinning in-context learning in Large Language Models (LLMs). Our work provides a novel perspective by examining in-context learning v…
Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models
Yue Zhang, Yafu Li, Leyang Cui +13
While large language models (LLMs) have demonstrated remarkable capabilities across a range of downstream tasks, a significant concern revolves around their propensity to exhibit h…
An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning
Yun Luo, Zhen Yang, Fandong Meng +3
Catastrophic forgetting (CF) is a phenomenon that occurs in machine learning when a model forgets previously learned information while acquiring new knowledge for achieving a satis…
Revisiting Cross-Lingual Summarization: A Corpus-based Study and A New Benchmark with Improved Annotation
Yulong Chen, Huajian Zhang, Yijie Zhou +8
Most existing cross-lingual summarization (CLS) work constructs CLS corpora by simply and directly translating pre-annotated summaries from one language to another, which can conta…
Explicit Syntactic Guidance for Neural Text Generation
Yafu Li, Leyang Cui, Jianhao Yan +4
Most existing text generation models follow the sequence-to-sequence paradigm. Generative Grammar suggests that humans generate natural language texts by learning language grammar.…
MAGE: Machine-generated Text Detection in the Wild
Yafu Li, Qintong Li, Leyang Cui +6
Large language models (LLMs) have achieved human-level text generation, emphasizing the need for effective AI-generated text detection to mitigate risks like the spread of fake new…
GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective
Linyi Yang, Shuibai Zhang, Libo Qin +6
Pre-trained language models (PLMs) are known to improve the generalization performance of natural language understanding models by leveraging large amounts of data during the pre-t…