Papers by Zhan Chen
From Answers to Arguments: Toward Trustworthy Clinical Diagnostic Reasoning with Toulmin-Guided Curriculum Goal-Conditioned Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are obstructed by their opaque and often unreliable reasoning. |
| Approach: | They propose a framework for trustworthy clinical argumentation by adapting the Toulmin model to the diagnostic process. |
| Outcome: | The proposed method achieves diagnostic accuracy comparable to resource-intensive RL methods while offering a more stable and efficient training pipeline. |
The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit (2025.acl-long)
Copied to clipboard
Huixue Zhou, Hengrui Gu, Zaifu Zhan, Xi Liu, Kaixiong Zhou, Yongkang Xiao, Mingfu Liang, Srinivas Prasad Govindan, Piyush Chawla, Jiyan Yang, Xiangfei Meng, Huayu Li, Buyun Zhang, Liang Luo, Wen-Yen Chen, Yiping Han, Bo Long, Rui Zhang, Tianlong Chen
| Challenge: | Existing frameworks for Large Language Models (LLMs) for Click-Through Rate prediction require a careful balance between computational efficiency and predictive accuracy. |
| Approach: | They propose a framework that integrates Retrieval-Augmented Generation with a novel multi-head early exit architecture to address both challenges. |
| Outcome: | The proposed framework reduces retrieval time while maintaining high model performance. |
Tailoring Diagnostic Modeling to Individual Learners: Personalized Distractor Generation via MCTS-Guided Reasoning Reconstruction (2026.acl-long)
Copied to clipboard
| Challenge: | Current distractor generation methods produce shared distractors for all students, ignoring individual variations in reasoning, which limits their diagnostic effectiveness. |
| Approach: | They propose a method which tailors distractors to each student’s specific cognitive flaws, inferred from their past question-answering (QA) history. |
| Outcome: | The proposed framework outperforms existing methods in generating plausible distractors and adapts to group-level settings. |
LongTutor: Benchmarking Large Language Models for Long-term Personalized Tutoring (2026.acl-long)
Copied to clipboard
| Challenge: | Existing evaluations focus on isolated, short-term interactions, overlooking the inherently long-term nature of learning. |
| Approach: | They propose a benchmark for long-term personalized tutoring based on an annotated learning log . they propose an automated generator–verifier pipeline to enable benchmark expansion . |
| Outcome: | The proposed benchmarks evaluate LLMs across three progressive tasks: evidence acquisition, knowledge state diagnosis, and adaptive teaching action. |
Emphasising Structured Information: Integrating Abstract Meaning Representation into LLMs for Enhanced Open-Domain Dialogue Evaluation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing evaluation metrics struggle to evaluate adversarial negative examples . existing metrics struggle in handling adversarials, resulting in low correlations with human judgments. |
| Approach: | They propose a framework that integrates AMR and domain-specific language models for automatic open-domain dialogue evaluation. |
| Outcome: | The proposed evaluation framework achieves strong correlations with human judgments across multiple datasets. |
A Dual-View Analysis of Multiple Languages in Colonial Newspapers (2026.findings-acl)
Copied to clipboard
Zhan Su, Xiaoya Chen, Fengran Mo, Ida L. Vos, Prayag Tiwari, Yazhou Zhang, Qian Zheng, Natália da Silva Perez
| Challenge: | Historical newspapers from the colonial period offer valuable evidence of how racializing language evolved over time. |
| Approach: | They propose a contextual question answering and visual question answering task from colonial newspapers . they propose linguistic training for temporal word embedding with a compass to study racialization . |
| Outcome: | The proposed tasks are limited for low-resource tasks, the authors show . the authors compare the results of two QA pairs from colonial newspapers to a compass . |
Augmenting Knowledge-grounded Conversations with Sequential Knowledge Transition (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing knowledge-grounded dialogue models lack fine-grained control over knowledge selection and integration with dialogues. |
| Approach: | They propose to explicitly model the knowledge transition in sequential multi-turn conversations by abstracting knowledge into topic tags. |
| Outcome: | The proposed model outperforms baseline models on knowledge-grounded dialogue benchmarks. |
SLIDE: A Framework Integrating Small and Large Language Models for Open-Domain Dialogues Evaluation (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to evaluate open domain dialogues have a one-to-many problem . existing approaches lack commonsense reasoning biases and perform poorly in domain-specific scenarios. |
| Approach: | They propose a framework that leverages both a small, specialised model and LLMs for the evaluation of open-domain dialogues. |
| Outcome: | The proposed framework achieves state-of-the-art performance in both classification and evaluation tasks and exhibits better correlation with human judgements. |
Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward (2025.findings-emnlp)
Copied to clipboard
Han Weng, Puzhen Wu, Cui Longjie, Yi Zhan, Boyi Liu, Yuanfeng Song, Dun Zeng, Yingxiang Yang, Qianru Zhang, Dong Huang, Xiaoming Yin, Yang Sun, Xing Chen
| Challenge: | Existing methods to enhance performance of large language models (LLMs) on Text-to-SQL tasks rely on execution-based or LLM-based reward models. |
| Approach: | They propose a reward model framework for RL-based Text-to-SQL that employs the GMNScore outcome reward model. |
| Outcome: | The proposed reward model outperforms existing reward models on standard benchmarks including Spider and BIRD. |
Unlocking Black-Box Prompt Tuning Efficiency via Zeroth-Order Optimization (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Prompt optimization is an important technique for adapting Large Language Models (LLMs) to specific tasks. |
| Approach: | They propose a zeroth-order approach which enables efficient prompt tuning solely via inference APIs. |
| Outcome: | The proposed approach outperforms existing black-box prompt tuning methods in terms of performance and convergence speed. |
GRNFormer: A Biologically-Guided Framework for Integrating Gene Regulatory Networks into RNA Foundation Models (2025.findings-acl)
Copied to clipboard
Mufan Qiu, Xinyu Hu, Fengwei Zhan, Sukwon Yun, Jie Peng, Ruichen Zhang, Bhavya Kailkhura, Jiekun Yang, Tianlong Chen
| Challenge: | Foundation models for single-cell RNA sequencing ignore biological prior knowledge encoded in gene regulatory relationships and fail to leverage multi-omics signals. |
| Approach: | They propose a framework that integrates multi-scale gene regulatory networks into RNA foundation model training. |
| Outcome: | The proposed framework improves on state-of-the-art models on three downstream tasks . it integrates multi-scale gene regulatory networks (GRNs) from multi-omics data into training . |
PhyVer: Physics-Grounded Material Claim Verification with Multi-Fidelity Physical Evidence (2026.acl-demo)
Copied to clipboard
| Challenge: | Existing claim verification pipelines operate over text, producing ungrounded judgments. |
| Approach: | They propose a physics-grounded material claim verification system that can be used to verify claims with physical evidence. |
| Outcome: | The proposed system reduces MAE and sign-offs with experts over text-only GPT-5.1. |
Open Set Relation Extraction via Unknown-Aware Training (2023.acl-long)
Copied to clipboard
Jun Zhao, Xin Zhao, WenYu Zhan, Qi Zhang, Tao Gui, Zhongyu Wei, Yun Wen Chen, Xiang Gao, Xuanjing Huang
| Challenge: | Existing supervised relation extraction methods can still misclassify unknown relations into known relations due to the lack of supervision signals. |
| Approach: | They propose a method that regularizes the model by dynamically synthesizing negative instances that can provide the missing supervision signals. |
| Outcome: | The proposed method achieves SOTA unknown relation detection without compromising the classification of known relations. |
Stable Language Guidance for Vision–Language–Action Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing vision-Language-Action models are notoriously brittle to linguistic perturbations. |
| Approach: | They propose a probabilistic framework that disentangles physical affordance from semantic execution. |
| Outcome: | The proposed framework disentangles physical affordance from semantic execution. |
SLM-Mod: Small Language Models Surpass LLMs at Content Moderation (2025.naacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) are expensive to query in real-time and do not allow for a community-specific approach to content moderation. |
| Approach: | They propose to use small language models for community-specific content moderation tasks by fine-tuning and evaluating their performance against larger open- and closed-sourced models. |
| Outcome: | The proposed models outperform zero-shot LLMs in content moderation tasks with 11.5% higher accuracy and 25.7% higher recall across all communities. |
Large Language Models as an Indirect Reasoner: Contrapositive and Contradiction for Automated Reasoning (2025.coling-main)
Copied to clipboard
| Challenge: | Recent studies have focused on improving the ability of Large Language Models to perform complex reasoning. |
| Approach: | They propose a Direct-Indirect Reasoning method that integrates DR and IR as parallel reasoning paths that are merged to derive the final answer. |
| Outcome: | The proposed method outperforms existing methods on four datasets related to logical reasoning and proof. |
DUET: Joint Exploration of User–Item Profiles in Recommendation System (2026.findings-acl)
Copied to clipboard
Yue Chen, Yifei Sun, Lu Wang, Fangkai Yang, Pu Zhao, Minjie Hong, Yifei Dong, Minghua He, Nan Hu, Jianjin Zhang, Zhiwei Dai, Yuefeng Zhan, Weihao Han, Hao Sun, Qingwei Lin, Weiwei Deng, Feng Sun, Qi Zhang, Saravan Rajmohan, Dongmei Zhang
| Challenge: | Existing LLMs are opaque and difficult to interpret, resulting in limited interpretability. |
| Approach: | They propose an interaction-aware profile generator that jointly produces user and item profiles conditioned on both user history and item evidence. |
| Outcome: | The proposed model outperforms baselines on three real-world datasets. |
Enhancing Transformation from Natural Language to Signal Temporal Logic Using LLMs with Diverse External Knowledge (2025.findings-acl)
Copied to clipboard
| Challenge: | Temporal Logic (STL) is a formal specification tool for cyber-physical systems . but it is difficult to transform ambiguous and complex data into STL, a paper argues . |
| Approach: | They propose a NL-STL dataset with 16,000 samples enriched with diverse patterns . they propose KGST framework to transform natural language into STL using a generate-then-refine process . |
| Outcome: | The proposed dataset outperforms baseline models in diversity and accuracy . the proposed dataset contains 16,000 samples enriched with diverse patterns . |
Uncertainty-Aware Contrastive Sentence Embedding With Local Context Representation for Text Classification (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing models for text classification are based on encoder-only transformers and generative pre-trained transformers. |
| Approach: | They propose an uncertainty-aware contrastive sentence embedding approach that addresses language ambiguity and inter-class separability for a text classification task. |
| Outcome: | The proposed approach improves classification accuracy on public datasets compared with state-of-the-art methods. |
PwnGPT: Automatic Exploit Generation Based on Large Language Models (2025.acl-long)
Copied to clipboard
Wanzong Peng, Lin Ye, Xuetao Du, Hongli Zhang, Dongyang Zhan, Yunting Zhang, Yicheng Guo, Chen Zhang
| Challenge: | Automated exploit generation (AEG) is the automatic discovery and exploitation of vulnerabilities against unknown targets. |
| Approach: | They propose an automatic exploit generation framework that automatically solves pwn challenges by using large language models. |
| Outcome: | The proposed framework improves the completion rate of exploits on the openAI o1-preview model and the GPT-4o model. |
Playing 20 Question Game with Policy-Based Reinforcement Learning (D18-1)
Copied to clipboard
| Challenge: | The 20 Questions (Q20) game encourages deductive reasoning and creativity. |
| Approach: | They propose a policy-based Reinforcement Learning method which learns optimal question selection . the method is robust to noisy answers and uses a reward network to estimate the more informative reward . |
| Outcome: | The proposed method outperforms an entropy-based engineering system and has competitive performance in noisy-free simulation environment. |
Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for audio captioning lack fine-grained detail and contextual accuracy due to limited unimodal or superficial information. |
| Approach: | They propose a two-stage automated pipeline that uses pretrained models to extract contextual cues from video . a large language model synthesizes these inputs to generate detailed and context-aware captions . |
| Outcome: | The proposed method is scalable and generates detailed and context-aware captions on large-scale audio datasets. |
Beyond the Context Window: Scaling Agentic RL via End-to-end Optimized Context Compression (2026.acl-long)
Copied to clipboard
| Challenge: | Existing reinforcement learning pipelines suffer from degraded instruction following, excessive rollout costs, and strict context limits. |
| Approach: | They propose a reinforcement learning (RL) fine-tuning of large language model (LLM) agents for long-horizon multi-turn tool use where context length quickly becomes a bottleneck. |
| Outcome: | The proposed framework improves the success rate while maintaining the same or even lower working context length compared to baselines. |
MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers (2026.acl-long)
Copied to clipboard
Linrui Ma, Chun Hei Lo, Xinyu Wang, Peng Lu, Xihao Yuan, Hanting Chen, Kai Han, Xinghao Chen, Chengjun Zhan, Hanlin xu, Yichun Yin, Lifeng Shang, Feng Wen, Boxing Chen, Yufei Cui
| Challenge: | Existing approaches to improve efficiency often enforce rigid structural constraints such as local attention windows. |
| Approach: | They propose a framework that augments sparse-attention mechanisms with dynamically integrated in-context information through an efficient retrieval system. |
| Outcome: | Empirical results show that MATCH significantly improves the performance of sparse-attention models on synthetic and real-world natural-language tasks. |
From Recognition to Reasoning: Benchmarking and Enhancing MLLMs on Real-World Receipt Document Understanding (2026.acl-long)
Copied to clipboard
| Challenge: | Existing models for visual information extraction suffer from limitations in scale and realism . ReceiptBench is a large-scale, human-annotated benchmark for receipts . |
| Approach: | They propose a large-scale, human-annotated benchmark for visual information extraction . the method organizes information extraction into four hierarchical sub-tasks . |
| Outcome: | The proposed method surpasses proprietary models on complex reasoning tasks. |
History-Aware Conversational Dense Retrieval (2024.findings-acl)
Copied to clipboard
| Challenge: | Current approaches for conversational dense retrieval rely on fine-tuning a pre-trained ad-hoc retriever, which can be lengthy and noisy. |
| Approach: | They propose a context-denoised query reformulation and automatic mining of supervision signals based on historical turns. |
| Outcome: | The proposed system improves on two public conversational search datasets. |
Effectiveness of Pre-training for Few-shot Intent Classification (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing paradigms further pre-train language models such as BERT on vast amount of unlabeled corpus, but we find it highly effective and efficient to simply fine-tune BERT with roughly 1,000 labeled utterances from public datasets. |
| Approach: | They propose to fine-tune BERT with a small set of labeled utterances from public datasets to achieve a pre-trained model based on a set of 1,000 labeles. |
| Outcome: | The proposed model can outperform existing models on domains with very different semantics on novel domains. |
Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering (2022.acl-long)
Copied to clipboard
Jiawei Zhou, Xiaoguang Li, Lifeng Shang, Lan Luo, Ke Zhan, Enrui Hu, Xinyu Zhang, Hao Jiang, Zhao Cao, Fan Yu, Xin Jiang, Qun Liu, Lei Chen
| Challenge: | Existing methods to train dense passage retrieval have a large data gap between upstream and downstream relevance. |
| Approach: | They propose a method to pre-train the dense retriever with the text relevance induced by hyperlinks within Web documents. |
| Outcome: | The proposed method outperforms existing methods under different scenarios and in the open-domain question answering domain. |
MoMoE: Mixture of Moderation Experts Framework for AI-Assisted Online Governance (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches for content moderation require a separate model for every community and are opaque in their decision-making. |
| Approach: | They propose a modular framework that adds post-hoc explanations to enable scalable content moderation. |
| Outcome: | The proposed framework yields scalable, transparent moderation without fine-tuning across domains. |
CoLV: A Collaborative Latent Variable Model for Knowledge-Grounded Dialogue Generation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to knowledge-grounded dialogue generation perform relatively independent sub-tasks . Typical approaches tend to decompose this task into two streamlined sub- tasks . |
| Approach: | They propose a collaborative latent variable model to integrate knowledge selection and knowledge-aware response generation simultaneously in separate but collaborative latences. |
| Outcome: | The proposed model outperforms previous methods on knowledge selection and response generation. |