Papers by Xi Shi
MIBench: Evaluating Multimodal Large Language Models over Multiple Images (2024.emnlp-main)
Copied to clipboard
Haowei Liu, Xi Zhang, Haiyang Xu, Yaya Shi, Chaoya Jiang, Ming Yan, Ji Zhang, Fei Huang, Chunfeng Yuan, Bing Li, Weiming Hu
| Challenge: | Existing benchmarks and MLLMs focus on single-image input scenarios, leaving performance of ML models when handling multiple images underexplored. |
| Approach: | They propose a benchmark to evaluate fine-grained abilities of multimodal large language models in multi-image scenarios. |
| Outcome: | The proposed benchmark categorizes the multi-image abilities into three scenarios: MII, MKS and MIC. |
Hidden in Plain Sight: Evaluation of the Deception Detection Capabilities of LLMs in Multimodal Settings (2025.acl-long)
Copied to clipboard
| Challenge: | Detecting deception in an increasingly digital world is a critical and challenging task. |
| Approach: | They evaluate the performance of both open-source and proprietary LLMs on three datasets . they find that fine-tuned LLM achieve state-of-the-art performance on textual deception detection . |
| Outcome: | The proposed models achieve state-of-the-art on textual deception detection, whereas LMMs struggle to fully leverage multimodal cues. |
Counteracting the Matthew Effect in Self-Improvement of LVLMs through Head-Tail Re-balancing (2026.acl-long)
Copied to clipboard
Xin Guo, Zhiheng Xi, Yiwen Ding, Yitao Zhai, Xiaowei Shi, Xunliang Cai, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Large vision language models have impressive reasoning capabilities across complex multimodal tasks. |
| Approach: | They propose to use distribution-reshaping and trajectory-rebalancing to improve visual reasoning capabilities. |
| Outcome: | Experiments on Qwen2-VL-7B-Instruct and InternVL2.5-4B models show that their methods outperform baselines by 3.86 points. |
Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling (2025.naacl-long)
Copied to clipboard
Yiwen Ding, Zhiheng Xi, Wei He, Lizhuoyuan Lizhuoyuan, Yitao Zhai, Shi Xiaowei, Xunliang Cai, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Large language models (LLMs) generate solutions themselves and iteratively train on filtered, high-quality rationales, but performance reaches a ceiling after a few iterations. |
| Approach: | They propose a strategy to improve the efficiency of sampling heavy-tailed data by using Socratic-style guidance signals to help LLMs reasoning with complex queries. |
| Outcome: | The proposed approach is effective on difficult queries and on held-out tasks, while requiring human supervision. |
iAgent: LLM Agent as a Shield between User and Recommender Systems (2025.findings-acl)
Copied to clipboard
Wujiang Xu, Yunxiao Shi, Zujie Liang, Xuying Ning, Kai Mei, Kun Wang, Xi Zhu, Min Xu, Yongfeng Zhang
| Challenge: | Traditional recommender systems focus on the user-platform paradigm, where users are directly exposed under the control of the platform's recommendation algorithms. |
| Approach: | They propose a user-agent-platform paradigm where agent serves as the protective shield between user and recommender system that enables indirect exposure. |
| Outcome: | The proposed model improves 16.6% over baselines on four datasets and mitigates echo chamber effects and reduces model bias in disadvantaged users. |
LegalCore: A Dataset for Event Coreference Resolution in Legal Documents (2025.findings-acl)
Copied to clipboard
Kangda Wei, Xi Shi, Jonathan Tong, null Sai Ramana Reddy, Anandhavelu Natarajan, Rajiv Jain, Aparna Garimella, Ruihong Huang
| Challenge: | Existing research on event coreference resolution is limited to news articles . existing datasets for news articles are limited to events and coreferences . |
| Approach: | They present a dataset for the legal domain LegalCore which has been annotated with event and event coreference information. |
| Outcome: | The legal contract documents annotated in this dataset are several times longer than news articles, with an average length of around 25k tokens per document. |
AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation (2026.findings-acl)
Copied to clipboard
Wentao Shi, Yu Wang, Yuyang Zhao, Yuxin Chen, Fuli Feng, Xueyuan Hao, Xi Su, Qi GU, Hui Su, Xunliang Cai, Xiangnan He
| Challenge: | Existing approaches to verify agent behaviors in complex environments rely on rule-based verifiers or LLM-as-a-Judge models. |
| Approach: | They propose a benchmark to evaluate Agent-as-a-Judge across three domains . the benchmark covers search, data systems, and graphical user interfaces - with 155 tasks and 516 trajectories . |
| Outcome: | The proposed benchmark outperforms existing benchmarks in search, data systems, and GUI domains while revealing open challenges in agent-based verification. |
Instruction-tuned Language Models are Better Knowledge Learners (2024.acl-long)
Copied to clipboard
Zhengbao Jiang, Zhiqing Sun, Weijia Shi, Pedro Rodriguez, Chunting Zhou, Graham Neubig, Xi Lin, Wen-tau Yih, Srini Iyer
| Challenge: | Large language models store factual knowledge in parameters, but it can become outdated as the work evolves . pre-instruction-tuning improves ability of LLMs to absorb knowledge from new documents . |
| Approach: | They propose a method that instruction-tunes on questions prior to training on documents . they propose to use QA pairs to update factual knowledge of large language models . |
| Outcome: | The proposed method outperforms instruction-tuning on documents by 17.8%. |
TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use (2025.findings-emnlp)
Copied to clipboard
Junjie Ye, Yilong Wu, Sixian Li, Yuming Yang, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang, Peng Wang, Zhongchao Shi, Jianping Fan, Zhengyin Du
| Challenge: | a new approach to training large language models (LLMs) overlooks task-specific characteristics in tool use, leading to performance bottlenecks. |
| Approach: | They propose a task-feature-based framework that mitigates the effects of suboptimal training data . they use a dataset to train large-scale LLMs and a reward mechanism tailored to error categories . |
| Outcome: | The proposed framework matches or surpasses open- and closed-source LLMs in tool-use performance using only 1,217 training data points. |
Dialect-SQL: An Adaptive Framework for Bridging the Dialect Gap in Text-to-SQL (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing Text-to-SQL research focuses on specific database systems, limiting adaptability to different dialects. |
| Approach: | They propose a framework that employs Object Relational Mapping (ORM) code as an intermediate language to bridge this gap. |
| Outcome: | The proposed framework outperforms existing methods that generate SQL queries directly. |
Self-supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies have focused on replacing the reward model in Reinforcement Learning with Human Feedback (RLHF) methods for Large Language Models (LLMs). |
| Approach: | They propose a self-supervised preference optimization framework that replaces the reward model with a preference loss and alignment loss to improve LLMs' ability to understand human preferences. |
| Outcome: | The proposed framework can be integrated with existing preference optimization methods and significantly boost their performance. |
HoLLMwood: Unleashing the Creativity of Large Language Models in Screenwriting via Role Playing (2024.findings-emnlp)
Copied to clipboard
Jing Chen, Xinyu Zhu, Cheng Yang, Chufan Shi, Yadong Xi, Yuxiang Zhang, Junjie Wang, Jiashu Pu, Tian Feng, Yujiu Yang, Rongsheng Zhang
| Challenge: | Generative AI has demonstrated unprecedented creativity in the field of computer vision, yet such phenomena have not been observed in the realm of literary creation. |
| Approach: | They propose a framework for unleashing the creativity of large language models (LLMs) they assign LLMs to different roles involved in real-world scenario, they write . |
| Outcome: | The proposed framework outperforms baselines in terms of coherence, relevance, interestingness and overall quality on automatically generated screenplays. |