Papers by Yuhan Li
Gentopia.AI: A Collaborative Platform for Tool-Augmented LLMs (2023.emnlp-demo)
Copied to clipboard
Binfeng Xu, Xukun Liu, Hua Shen, Zeyu Han, Yuhan Li, Murong Yue, Zhiyuan Peng, Yuchen Liu, Ziyu Yao, Dongkuan Xu
| Challenge: | Existing frameworks for Augmented Language Models lack flexibility, democratization, and holistic evaluation. |
| Approach: | They propose a lightweight and extensible framework for Augmented Language Models called Gentopia. |
| Outcome: | The proposed framework integrates language models, task formats, prompting modules, and plugins into a unified paradigm. |
DialoGPS: Dialogue Path Sampling in Continuous Semantic Space for Data Augmentation in Multi-Turn Conversations (2023.acl-long)
Copied to clipboard
| Challenge: | a context leads to various responses, and a response answers multiple contexts. |
| Approach: | They propose a method that augments open-domain dialogue generation from a many-to-many perspective. |
| Outcome: | The proposed method can augment open-domain dialogue generation tasks with automatic and human evaluation. |
Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey (2025.findings-emnlp)
Copied to clipboard
| Challenge: | specialized LLMs are often limited in domain-specific applications that require specialized knowledge. |
| Approach: | They provide a comprehensive overview of four key methods to enhance large language models by integrating domain-specific knowledge. |
| Outcome: | The proposed methods are categorized into four key approaches: dynamic knowledge injection, static knowledge embedding, modular adapters, and prompt optimization. |
STORM-BORN: A Challenging Mathematical Derivations Dataset Curated via a Human-in-the-Loop Multi-Agent Framework (2025.findings-acl)
Copied to clipboard
Wenhao Liu, Zhenyi Lu, Xinyu Hu, Jerry Zhang, Dailin Li, Jiacheng Cen, Huilin Cao, Haiteng Wang, Yuhan Li, Xie Kun, Dandan Li, Pei Zhang, Chengbo Zhang, Yuxiang Ren, Xiaohong Huang, Yan Ma
| Challenge: | Existing datasets suffer from outdated and insufficient challenging content, neglecting human-like reasoning, and limited reliability due to single-LLM generation. |
| Approach: | They propose a human-in-the-loop, multi-agent data generation framework that integrates reasoning-dense filters, multiagent collaboration, and human mathematicians’ evaluations to ensure the reliability and quality of the dataset. |
| Outcome: | The proposed framework improves accuracy and quality of the 2,000-synthesized datasets by integrating reasoning-dense filters, multi-agent collaboration, and human mathematicians’ evaluations. |
Unsupervised Chinese Word Segmentation with BERT Oriented Probing and Transformation (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for unsupervised Chinese word segmentation exploit shallow semantic information, which can miss important context. |
| Approach: | They propose to take advantage of deep contextual semantic information with a self-training manner to transform it into explicit word segmentation ability. |
| Outcome: | The proposed approach achieves state-of-the-art F1 score on two CWS benchmark datasets. |
FlexiQA: Leveraging LLM’s Evaluation Capabilities for Flexible Knowledge Selection in Open-domain Question Answering (2024.findings-eacl)
Copied to clipboard
| Challenge: | Current methods for open-domain question answering lacks the hallucination and relevance of acquired knowledge to the given question. |
| Approach: | They propose a new pipeline that utilizes the diverse evaluation capabilities of large language models to select knowledge effectively and flexibly. |
| Outcome: | The proposed pipeline combines the strengths of both paradigms and overcomes their shortcomings. |
Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool Use (2024.acl-long)
Copied to clipboard
| Challenge: | In this paper, we demonstrate that an inherent waveform pattern in the attention allocation of large language models significantly affects their performance in tasks demanding a high degree of context awareness. |
| Approach: | They propose a method that compensates an attention trough with an attention peak by a process to enhance the model's awareness to various contextual positions. |
| Outcome: | The proposed method improves the performance of a 7B model on the largest tool-use benchmark, comparable to that of GPT-4. |
TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Base (2022.emnlp-main)
Copied to clipboard
| Challenge: | KBQA is a challenging area for pre-trained language models due to its extensive space and complexity. |
| Approach: | They propose a model that uses multi-grained retrieval to focus on most relevant KB contexts . constrained decoding is used to control output space and reduce generation errors . |
| Outcome: | The proposed model outperforms existing models on GrailQA and WebQuestionsSP. |
DeMAC: Enhancing Multi-Agent Coordination with Dynamic DAG and Manager-Player Feedback (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Multi-agent systems (MAS) powered by large language models struggle to adapt to evolving task dependencies and to handle uncertainties. |
| Approach: | They propose a Dynamic Environment-Aware Manager-Player Agents Coordination framework that enhances multi-agent coordination through long-term strategic planning. |
| Outcome: | The proposed framework outperforms traditional reinforcement learning and human-agent collaboration in the Overcooked simulation. |
Revisiting LoRA through the Lens of Parameter Redundancy: Spectral Encoding Helps (2025.findings-acl)
Copied to clipboard
| Challenge: | Low-Rank Adaptation (LoRA) has emerged as a prominent technique for fine-tuning large foundation models. |
| Approach: | They propose a low-rank Adaptation technique that harnesses the expressiveness of spectral bases to re-parameterize LoRA from a sparse spectral subspace. |
| Outcome: | The proposed technique achieves greater efficiency with fewer parameters than baselines on various downstream tasks, including commonsense reasoning, math reasoning, and code generation. |
Temporal Contrastive Decoding: A Training-Free Method for Large Audio-Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Large audio-language models (LALMs) can exhibit a temporal smoothing bias . unified decoders can produce less specific audio-grounded outputs . |
| Approach: | They propose a temporally blurred slow-path view that is re-encoded by a token-level logit update. |
| Outcome: | Experiments on MMAU and AIR-Bench show consistent improvements on strong unified LALMs. |
Traces in the Brain: Neural Evidence for Syntactic Movement in English and Chinese (2026.findings-acl)
Copied to clipboard
Yuhan Huang, Zhengwu Ma, Yuqi Jin, Beth Chan, Zheng Shen, Jackie Yan-Ki Lai, John T. Hale, Jixing Li
| Challenge: | Syntactic movement is a core concept in generative linguistics to account for word-order variation and long-distance dependencies. |
| Approach: | They annotated every sentence in the audiobook The Little Prince using X-bar style tree annotations. |
| Outcome: | The proposed model shows that deep structure significantly predicts neural responses in English but not in Chinese. |
H-MAS: Hierarchical Multi-Agent Scheduling for Multi-Tenant LLM Serving (2026.findings-acl)
Copied to clipboard
Yuhan Liu, Cong Xu, Qi Jia, Yihua Wang, Feiyu Chen, Liang Jin, Lu Liu, Yaqian Zhao, Yuting Ding, Xiang Li
| Challenge: | Multi-tenant Model-as-a-Service (MaaS) workloads exhibit non-stationarity across multiple time scales . existing request schedulers often rely on a fixed policy that remains unchanged at runtime . |
| Approach: | They propose a hierarchical multi-agent scheduler that operates in a layered closed loop . they propose to maintain 1.2–3.0 higher Goodput than SGLang and vLLM . |
| Outcome: | Experiments show that H-MAS achieves 1.2–3.0 higher Goodput than SGLang and vLLM . it maintains more stable QoS under diverse request lengths and heterogeneous SLO targets . |
OFFSIDE: Benchmarking Unlearning Misinformation in Multimodal Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks for MU are limited by a lack of image diversity and coarse-grained unlearning targets. |
| Approach: | They propose a benchmark to evaluate misinformation unlearning in MLLMs . OFFSIDE supports advanced unlearning targets such as fine-grained unlearning and visual rumor removal. |
| Outcome: | OFFSIDE supports advanced unlearning targets, such as fine-grained unlearning and visual rumor removal. |
MemRec: Collaborative Memory-Augmented Agentic Recommender System (2026.acl-long)
Copied to clipboard
Weixin Chen, Yuhan Zhao, Jingyuan Huang, Zihe Ye, Mingxuan Ju, Tong Zhao, Neil Shah, Li Chen, Yongfeng Zhang
| Challenge: | Existing recommender systems rely on semantic user and item memories to make predictions, but these memories are kept in isolation. |
| Approach: | They propose a framework that architecturally decouples memory management from reasoning to decouple memory management and reasoning from the user and item memories. |
| Outcome: | The proposed framework decouples memory management from reasoning and achieves state-of-the-art performance on four benchmarks. |
From Style to Story: A Curriculum Learning Approach for Imitative Novel Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Novels create rich, immersive worlds with intricate plots and distinct styles, captivating readers through complex storytelling. |
| Approach: | They propose a novel generation system that imitates novel elements by predicting plot developments and writing concrete details using vivid, expressive language. |
| Outcome: | The novel imitative novel generation system is trained through a curriculum learning paradigm, progressing from low-level stylistic mastery to high-level narrative coherence. |
Looking Beyond the One: Operationalizing and Eliciting Visual Ambiguity in VLLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Visual question answering systems typically collapse ambiguity, committing to a single interpretation during decoding and evaluation. |
| Approach: | They operationalize ambiguity as the existence of multiple answer-supporting regions in an image . they show that ambiguities are already encoded in their internal representations . |
| Outcome: | The proposed approach makes ambiguity observable without exhaustive annotations . ambiguities are already encoded in models, but not reliably expressed in outputs despite hidden states . |
DiaASQ: A Benchmark of Conversational Aspect-based Sentiment Quadruple Analysis (2023.findings-acl)
Copied to clipboard
Bobo Li, Hao Fei, Fei Li, Yuhan Wu, Jinsong Zhang, Shengqiong Wu, Jingye Li, Yijiang Liu, Lizi Liao, Tat-Seng Chua, Donghong Ji
| Challenge: | a new task of conversational aspect-based sentiment analysis (DiaASQ) is designed to detect the quadruple of target-aspect-opinion-sentiment in a dialogue. |
| Approach: | They propose a task of conversational aspect-based sentiment quadruple analysis to detect the quadrangle of target-aspect-opinion-sentiment in a dialogue. |
| Outcome: | The proposed task is based on a high-quality dataset in Chinese and English . it improves the end-to-end quadruple prediction and integrates rich feature representations . |
Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Preference Optimization (2025.findings-acl)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) are known to hallucinate, which limits their practical applications. |
| Approach: | They propose a method that uses three types of preference pairs to target hallucinations from their diverse forms and causes. |
| Outcome: | The proposed method surpasses most state-of-the-art methods and shows potential for further improvements. |
AIRepr: An Analyst-Inspector Framework for Evaluating Reproducibility of LLMs in Data Science (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models are increasingly used to automate data analysis, but data science tasks often admit multiple statistically valid solutions. |
| Approach: | They propose a framework to evaluate LLM-generated code and assess its reproducibility . they introduce two reproducibility-enhancing prompting strategies and benchmark them against standard prompting . |
| Outcome: | The proposed framework improves reproducibility of large language models . it provides a foundation for transparent, reliable, and efficient human–AI collaboration in data science. |
GlossaGen: Making Academic Translation Smarter with Glossing (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing machine translation systems obscure or mistranslate key terminology, while paraphrasing aimed at lay readers often oversimplifies it, hindering their ability to master domain-specific technical vocabulary. |
| Approach: | They propose a task which produces translations dynamically adapted to a reader’s academic proficiency, or level, and a framework to address this challenge. |
| Outcome: | The proposed framework achieves higher scores than baselines on a synthesized benchmark and human evaluations. |
Large Language Models Meet Harry Potter: A Dataset for Aligning Dialogue Agents with Characters (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models that can create open-domain dialogue agents lack character representation and annotations. |
| Approach: | They propose a dataset to study character alignment and character representation . it includes all dialogue sessions from the Harry Potter series and includes annotations . |
| Outcome: | The proposed dataset can be used as a universal benchmark for character-driven LLMs. |