Papers by Yukun Li
RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework (2025.acl-long)
Copied to clipboard
Kunlun Zhu, Yifan Luo, Dingling Xu, Yukun Yan, Zhenghao Liu, Shi Yu, Ruobing Wang, Shuo Wang, Yishan Li, Nan Zhang, Xu Han, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing evaluation metrics for RAG systems are lacking due to high costs of data construction and lack of factual accuracy. |
| Approach: | They propose a framework to evaluate RAG systems in specialized scenarios . they propose three new metrics to evaluate LLM-generated responses . |
| Outcome: | The proposed framework outperforms zero-shot and one-shot methods in terms of clarity, safety, conformity, and richness of generated samples. |
Judge as A Judge: Improving the Evaluation of Retrieval-Augmented Generation through the Judge-Consistency of Large Language Models (2025.findings-acl)
Copied to clipboard
Shuliang Liu, Xinze Li, Zhenghao Liu, Yukun Yan, Cheng Yang, Zheni Zeng, Zhiyuan Liu, Maosong Sun, Ge Yu
| Challenge: | Existing evaluation metrics cannot fairly evaluate the outputs of RAG models during training and evaluation. |
| Approach: | They propose a method which prompts LLMs to generate different judgments based on various combinations of judgment dimensions and utilizes the judge-consistency to evaluate these judgments. |
| Outcome: | The proposed method generates more accurate evaluations for RAG models across different RAG model and datasets. |
How to Contextualize Empirical Data for Risk Analysis with LLMs: A Case Study of Power Outages (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly being considered for high-stakes decision-making, yet their application in statistical risk analysis remains largely underexplored. |
| Approach: | They propose a method for extracting key information from raw data and translating it into structured contextual input within the LLM prompt. |
| Outcome: | The proposed approach significantly improves the LLM’s performance in risk assessment tasks. |
Enhancing Long-Chain Reasoning Distillation through Error-Aware Self-Reflection (2026.findings-acl)
Copied to clipboard
Zhuoyang Wu, Xinze Li, Zhenghao Liu, Yukun Yan, Zhiyuan Liu, Minghe Yu, Cheng Yang, Yu Gu, Ge Yu, Maosong Sun
| Challenge: | Existing studies treat SLMs as student models and use long-form Chains-of-Thought (CoTs) as supervision signals for Supervised Fine-Tuning (SFT). Existing research focuses on distilling reasoning ability from LLMs to enhance the mathematical reasoning performance of small-scale models. |
| Approach: | They propose a framework that refines teacher CoTs through an error-aware reflection process to enable the student model to construct more tailored teacher Cots. |
| Outcome: | Experiments on multiple mathematical reasoning benchmarks show that ORION improves performance by more than 2% over all baselines. |
Structured Episodic Event Memory (2026.acl-long)
Copied to clipboard
| Challenge: | Current approaches to memory in Large Language Models (LLMs) rely on static Retrieval-Augmented Generation (RAG) this lacks the cognitive organization necessary to model the dynamic and associative nature of long-term interaction. |
| Approach: | They propose a hierarchical framework that transforms interaction streams into structured Episodic Event Frames (EEFs) anchored by precise provenance pointers. |
| Outcome: | The proposed framework outperforms baseline approaches on LoCoMo and LongMemEval benchmarks. |
Task Knowledge Injection via Interpolations and Reinstatement for Large Language Model Generalization (2025.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained large language models have been widely adopted to elicit their superior performance on downstream tasks, but instruction tuning may overfit them to specific task formats, compromising their generalization on unseen tasks. |
| Approach: | They propose to inject latent task adaptation and knowledge reinstatement into large language models to mitigate spurious correlations between inputs and targets. |
| Outcome: | The proposed method improves generalization on in-domain and out-of-domain unseen tasks. |
Decoding LLM Personality Measurement: Forced-Choice vs. Likert (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent research has focused on investigating the psychological characteristics of Large Language Models (LLMs), emphasizing the importance of comprehending their behavioral traits. |
| Approach: | They evaluated six Large Language Models: Llama-3.1-8B, GLM-4-9B, Claude-3.5-sonnet, and Deepseek-V3 and used the forced-choice test to assess their personality traits. |
| Outcome: | The forced-choice test is more reliable and more accurate than the likert scale and forced-CHOICE test results for LLMs' Big Five personality scores. |
Learn To Remember: Transformer with Recurrent Memory for Document-Level Machine Translation (2022.findings-naacl)
Copied to clipboard
| Challenge: | Recent studies have shown that the effective use of contextual information between sentences can achieve better performance in document-level machine translation. |
| Approach: | They propose a recurrent memory unit to the Transformer to support the information exchange between the sentence and previous context. |
| Outcome: | The proposed model outperforms the previous work on TED and News by 0.91 s-BLEU and 1.49 d-BLUE on average. |
MetaMem: Evolving Meta-Memory for Knowledge Utilization through Self-Reflective Symbolic Optimization (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing memory systems can support long-horizon human-LLM interactions by persisting historical interactions beyond limited context windows. |
| Approach: | They propose a framework that augments memory systems with a self-evolving meta-memory . meta-meso is iteratively distilling transferable knowledge utilization experiences . results show MetaMem outperforms strong baselines by over 3.6% . |
| Outcome: | The proposed framework outperforms baselines by over 3.6% in the long-horizon human-LLM interaction. |
ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation (2025.findings-emnlp)
Copied to clipboard
Hao Chen, Yukun Yan, Sen Mei, Wanxiang Che, Zhenghao Liu, Qi Shi, Xinze Li, Yuchun Fan, Pengcheng Huang, Qiushi Xiong, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing RAG systems often underutilize the retrieved documents, authors say . they fail to extract and integrate key clues needed to support faithful and interpretable reasoning . |
| Approach: | a new framework extracts key clues from retrieved content and generates multiple reasoning paths . the framework optimizes the model by selecting the most appropriate reasoning path . |
| Outcome: | Experiments show that ClueAnchor outperforms baseline RAG frameworks in completeness and robustness. |
ModSCAN: Measuring Stereotypical Bias in Large Vision-Language Models from Vision and Language Modalities (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large vision-language models have been widely used but stereotypical biases are unexplored. |
| Approach: | They propose a framework to SCAN stereotypical bias within large vision-language models . they examine stereotype biases with respect to gender and race in three scenarios . |
| Outcome: | The proposed framework can reduce stereotypical biases in large vision-language models . the currently popular models show significant stereotype biase . |
AEQ-Bench: Measuring Empathy of Omni-Modal Large Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks focus on cognitive abilities, such as knowledge retrieval, complex reasoning, and instruction following, largely overlooking empathy evaluation. |
| Approach: | They propose to benchmark two core empathetic capabilities of omnimodal large models (OLMs) generating empatries by comprehending affective cues from multi-modal inputs and judging empathy of audio responses without relying on text transcription. |
| Outcome: | The proposed benchmark outperforms existing models with audio output capabilities but is unreliable for evaluating fine-grained paralinguistic expressiveness. |
Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization (2026.acl-long)
Copied to clipboard
Shaohua Duan, Pengcheng Huang, Xinze Li, Zhenghao Liu, Xiaoyuan Yi, Yukun Yan, Shuo Wang, Yu Gu, Ge Yu, Maosong Sun
| Challenge: | Recent studies have explored fine-tuning Large Language Models with synthetic data to enhance their long-context capabilities. |
| Approach: | They propose a framework that leverages a Multi-Armed Bandit rollout strategy to identify the most informative chunks from the given long context for sampling high-quality and diverse responses. |
| Outcome: | The proposed framework achieves 4% improvement on long-context reasoning benchmarks on Llama and Qwen. |
ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization (2025.findings-emnlp)
Copied to clipboard
Zhensheng Jin, Xinze Li, Yifan Ji, Chunyi Peng, Zhenghao Liu, Qi Shi, Yukun Yan, Shuo Wang, Furong Peng, Ge Yu
| Challenge: | Existing methods to train LLMs suffer from overthinking, leading to lengthy reasoning traces . Existing approaches to train large language models suffer from this problem . |
| Approach: | They propose a method to combine multiple reasoning chains for training LLMs . they use stepwise exploration and long-short switched sampling to evaluate reasoning paths . |
| Outcome: | The proposed method reduces reasoning lengths by approximately 30-50% . it also maintains or improves reasoning accuracy compared to baselines . |
KG-ViP: Bridging Knowledge Grounding and Visual Perception in Multi-modal LLMs for Visual Question Answering (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to Visual Question Answering lack synergistic potential of scene graphs and scene graph. |
| Approach: | They propose a retrieval-and-fusion pipeline that fuses scene graphs and commonsense graphs to enable multi-modal reasoning. |
| Outcome: | Experiments on FVQA 2.0+ and MVQA benchmarks show that KG-ViP outperforms existing methods. |
RankCoT: Refining Knowledge for Retrieval-Augmented Generation through Ranking Chain-of-Thoughts (2025.acl-long)
Copied to clipboard
| Challenge: | Retrieval-Augmented Generation (RAG) models enable Large Language Models to access external knowledge. |
| Approach: | They propose a knowledge refinement method that incorporates reranking signals to generate CoT-based summarization based on query and retrieval documents. |
| Outcome: | RankCoT generates CoT-based summarization based on query and all retrieval documents . Rank CoT incorporates a self-reflection mechanism that refines the outputs . |
Open Schrödinger’s Closed Box: Identifying Retrieval Augmented Generation in API-Accessible Large Language Model Services (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) are powerful at question-answering but prone to hallucinations due to limited domain-specific or up-to-date knowledge. |
| Approach: | They propose a framework for IDentifying RAG properties in LLM services that integrates LLMs with retrieval systems and adds an external retriever and knowledge database to mitigate hallucinations. |
| Outcome: | The proposed framework detects RAG-enhanced LLMs with 99.97% accuracy with partial or no optional knowledge and nearly 100% when the LLM and database are known. |
DORA: A Dual-Objective Reinforcement Learning Framework for Effective and Efficient Multimodal Agentic Search (2026.acl-long)
Copied to clipboard
Guangming Qin, Yuhao Deng, Yukun Zhao, Zhenyang Li, Junfeng Wang, Dawei Yin, Ye Yuan, Guoren Wang, Yizhou Yan, Chengliang Chai, Lei Cao
| Challenge: | Existing methods to train large language models overlook quality of intermediate search results . existing methods often invoke search calls during reasoning, making inference inefficient . |
| Approach: | They propose a dual-objective reinforcement learning framework to improve search strategies of MLLMs . DORA outperforms state-of-the-art methods, achieving up to 8.4% higher accuracy . |
| Outcome: | The proposed model outperforms state-of-the-art methods while reducing search calls by 9.7%. |
STORYTELLER: An Enhanced Plot-Planning Framework for Coherent and Cohesive Story Generation (2025.findings-acl)
Copied to clipboard
Jiaming Li, Yukun Chen, Ziqiang Liu, Minghuan Tan, Lei Zhang, Yunshui Li, Run Luo, Longze Chen, Jing Luo, Ahmadreza Argha, Hamid Alinejad-Rokny, Wei Zhou, Min Yang
| Challenge: | Existing methods for storytelling lack coherence and consistency, compromising the overall storytelling experience. |
| Approach: | They propose a novel approach that improves the coherence and consistency of automatically generated stories by managing plot nodes and enabling dynamic interactions between different parts of the story. |
| Outcome: | The proposed approach outperforms existing methods in 84.33% of the trials. |
Long-Chain Reasoning Distillation via Adaptive Prefix Alignment (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities, especially in solving complex mathematical problems. |
| Approach: | They propose a framework that exploits teacher CoTs for distillation through adaptive prefix alignment. |
| Outcome: | The proposed framework outperforms baseline models on multiple mathematical reasoning benchmarks by over 3%. |
COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis (2025.findings-naacl)
Copied to clipboard
Weiqing Yang, Hanbin Wang, Zhenghao Liu, Xinze Li, Yukun Yan, Shuo Wang, Yu Gu, Minghe Yu, Zhiyuan Liu, Ge Yu
| Challenge: | Existing code debugging benchmarks focus on the Code Repair stage of the code generation process. |
| Approach: | They propose a framework to evaluate the debugging abilities of large language models by emulating the human debug process. |
| Outcome: | The proposed framework outperforms human-curated and GPT-4-generated training data, enabling 7B-scale LLMs to achieve comparable debugging performance to GPT-3.5. |
Toward the Limitation of Code-Switching in Cross-Lingual Transfer (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have shown the success of multilingual pretrained models for cross-lingual knowledge transfer. |
| Approach: | They propose to make code-switched sentences replace tokens from multiple languages so they are grammatically consistent . they also consider the similarity between context and the switched tokens to ensure that the newly substituted sentences are grammatically consistent - a limitation that could affect inference . |
| Outcome: | The proposed method outperforms the mBERT and original code-switching method on cross-lingual POS and Named-Entity-Recognition tasks on 30+ languages. |
AgentMark: Utility-Preserving Behavioral Watermarking for Agents (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have improved text generation and reasoning. |
| Approach: | They propose a behavioral watermarking framework that embeds multi-bit identifiers into planning decisions while preserving utility. |
| Outcome: | The proposed framework embeds multi-bit provenance into planning decisions while preserving utility. |