Papers by Jiazheng Li
NarrativePlay: Interactive Narrative Understanding (2024.eacl-demo)
Copied to clipboard
| Challenge: | Existing systems for interactive agents focus on specific capabilities in predetermined scenarios. |
| Approach: | They propose a novel system that allows users to role-play a fictional character and interact with other characters in narratives in an immersive environment. |
| Outcome: | The proposed system generates human-like responses guided by personality traits extracted from narratives. |
Two Heads Are Better Than One: Dual-Model Verbal Reflection at Inference-Time (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing LLMs struggle to reliably detect subtle reasoning errors in ASAS tasks. |
| Approach: | They propose a dual-model framework with a dedicated Critic model trained for effective reflection that generates precise verbal feedback. |
| Outcome: | The proposed framework outperforms existing ASAS benchmarks and provides valuable insights into the performance of the proposed framework. |
Better Process Supervision with Bi-directional Rewarding Signals (2025.findings-acl)
Copied to clipboard
Wenxiang Chen, Wei He, Zhiheng Xi, Honglin Guo, Boyang Hong, Jiazheng Zhang, Nijun Li, Tao Gui, Yun Li, Qi Zhang, Xuanjing Huang
| Challenge: | Existing processes that reward for each step are one-directional and lack a mechanism to model the distance to the final target. |
| Approach: | They propose a process supervision model that evaluates the correctness of previous steps and the probability of future success. |
| Outcome: | The proposed model outperforms existing supervision models like ORM and PRM on reasoning tasks and improves solution re-design. |
Distilling ChatGPT for Explainable Automated Student Answer Assessment (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing automated student answer assessment models lack explainable and faithful feedback. |
| Approach: | They propose a framework that leverages ChatGPT for student answer scoring and rationale generation. |
| Outcome: | The proposed method improves the overall QWK score by 11% compared to ChatGPT. |
AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments (2026.acl-long)
Copied to clipboard
Zhiheng Xi, Dingwen Yang, Jiaqi Liu, Jixuan Huang, Honglin Guo, Baodai Huang, Tinggang Chen, Qi Zhang, Zhonghang Lu, Chenyu Liu, Jiajun Sun, Jiazheng Zhang, Dingwei Zhu, Xin Guo, Junzhe Wang, Zhihao Zhang, Yuming Yang, Junjie Ye, Minghe Gao, Dongrui Liu, Jiaming Ji, Guohao Li, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing benchmarks evaluate agents in simplified, idealized settings, relying on pre-packaged tool interfaces, overlooking critical steps, and assume inputs are clean and fully specified. |
| Approach: | They propose a framework that evaluates language agents in simplified, idealized settings . they show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 . |
| Outcome: | Experiments on 15 proprietary and open-source models show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 . |
Calibrating LLMs with Preference Optimization on Thought Trees for Generating Rationale in Science Question Scoring (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for generating rationales that justify scoring decisions are not accurate and often contain hallucinated information. |
| Approach: | They propose a framework capable of generating more faithful rationales and matching performance with classifier-based scoring systems. |
| Outcome: | The proposed framework achieves 38% improvement in QWK score compared to prior work . it can be used to match performance with classifier-based scoring systems . |
NapSS: Paragraph-level Medical Text Simplification via Narrative Prompting and Sentence-matching Summarization (2023.findings-eacl)
Copied to clipboard
| Challenge: | a recent study shows that accessing medical literature is difficult for laypeople because it is written for specialists and contains medical jargon. |
| Approach: | They propose a two-stage strategy to identify relevant content to be simplified . they first generate reference summaries via sentence matching between the original and simplified abstracts . |
| Outcome: | The proposed approach improves on a seq2seq-based test set on an English medical corpus . it also improves the SARI score by 1.1% . |
DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories (2024.findings-acl)
Copied to clipboard
Jia Li, Ge Li, Yunfei Zhao, Yongmin Li, Huanyu Liu, Hao Zhu, Lecheng Wang, Kaibo Liu, Zheng Fang, Lanshen Wang, Jiazheng Ding, Xuanming Zhang, Yuqi Zhu, Yihong Dong, Zhi Jin, Binhua Li, Fei Huang, Yongbin Li, Bin Gu, Mengfei Yang
| Challenge: | Existing benchmarks are poorly aligned with real-world code repositories and are insufficient to evaluate the coding abilities of Large Language Models (LLMs). |
| Approach: | They propose a repository-level benchmark named DevEval to evaluate LLMs' coding abilities in real-world code repositories. |
| Outcome: | The proposed benchmarks show that the LLMs perform better in real-world code repositories than existing benchmarks. |
The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and Analysis (2024.emnlp-main)
Copied to clipboard
| Challenge: | In-context learning (ICL) is a capability that enables large language models to excel in proficiency through demonstration examples. |
| Approach: | They present a survey on the interpretation and analysis of in-context learning . they focus on theoretical and empirical perspectives on the concept . |
| Outcome: | The proposed model can perform tasks with minimal examples without re-training and has demonstrated proficiency across various tasks with a minimal set of task-oriented examples. |
Large Language Models Fall Short: Understanding Complex Relationships in Detective Narratives (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing datasets for narrative understanding fail to represent complexity and uncertainty of relationships in real-life social scenarios. |
| Approach: | They propose a benchmark for extracting and analysing intricate character relation graphs from detective narratives using large-scale large-language models. |
| Outcome: | The proposed dataset extracts and analyses character relation graphs from detective narratives using advanced Large Language Models like GPT-3.5, GPT-4, and Llama2 . |
RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing role-playing datasets mostly contribute to controlling role style and knowledge boundaries, but overlook role-following in instruction-follower scenarios. |
| Approach: | They propose a fine-grained role-playing and instruction-following composite benchmark, named RoleMRC, which includes multi-turn dialogues between ideal roles and humans, including free chats or discussions upon given passages . |
| Outcome: | The proposed model improves instruction-following without compromising general role-playing and reasoning capabilities. |
Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysis (2021.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to improve performance of deep neural models are limited by the nature of spurious patterns in the data. |
| Approach: | They propose to use augmented data to generate spurious patterns in NLP models . they propose to generate counterfactual data for data augmentation and explanation . |
| Outcome: | The proposed approach improves performance on augmented data and on human-generated data. |
LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks (2025.acl-long)
Copied to clipboard
Yushi Bai, Shangqing Tu, Jiajie Zhang, Hao Peng, Xiaozhi Wang, Xin Lv, Shulin Cao, Jiazheng Xu, Lei Hou, Yuxiao Dong, Jie Tang, Juanzi Li
| Challenge: | Existing benchmarks on longcontext large language models fail to reflect their deep understanding capabilities across diverse tasks. |
| Approach: | They propose a benchmark to assess the ability of long-context large language models to handle long-text problems. |
| Outcome: | The proposed model achieves 50.1% accuracy when directly answering the questions . human experts achieve only 53.7% accuracy under a 15-minute time constraint . |
LearnLens: LLM-Enabled Personalised, Curriculum-Grounded Feedback with Educators in the Loop (2025.emnlp-demos)
Copied to clipboard
| Challenge: | Existing systems that provide personalised, curriculum-aligned feedback are time-intensive and time-consuming. |
| Approach: | They propose a modular, LLM-based system that generates personalised, curriculum-aligned feedback in science education. |
| Outcome: | The proposed system generates personalised, curriculum-aligned feedback in science education. |
EnigmaToM: Improve LLMs’ Theory-of-Mind Reasoning Capabilities with Neural Knowledge Base of Entity States (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing ToM reasoning methods rely excessively on off-the-shelf LLMs, reducing their efficiency and limiting their applicability to high-order ToM. |
| Approach: | They propose a neuro-symbolic framework that integrates a Neural Knowledge Base of Entity States and knowledge injection to enhance ToM reasoning. |
| Outcome: | The proposed framework improves ToM reasoning on ToMi, HiToM, and FANToM benchmarks. |
SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory Graph (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities, but their application to complex, multi-step, and long-horizon tasks remains challenging. |
| Approach: | They propose a framework that provides a finer-grained advantage assignment derived solely from outcome rewards. |
| Outcome: | The proposed framework provides a finer-grained advantage assignment, derived solely from outcome rewards. |
Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies attributed verbosity to biased labels, but new research shows that DPO can be effective in mitigating verboses. |
| Approach: | They propose to use a method to reduce the amount of verbosity in LLMs by using a downsampling approach. |
| Outcome: | The proposed approach overcomes the problem of verbosity by reducing the length reliance of the proposed algorithm. |
AERA Chat: An Interactive Platform for Automated Explainable Student Answer Assessment (2025.emnlp-demos)
Copied to clipboard
| Challenge: | Existing systems that use pretrained language models to score student answers are noisy and unreliable. |
| Approach: | They propose a visualization platform for automated student answer assessment that leverages multiple LLMs to generate rationales. |
| Outcome: | The proposed platform enables educators to mark tasks and researchers to evaluate rationale quality from different models. |
Enhancing Transformers for Generalizable First-Order Logical Entailment (2025.acl-long)
Copied to clipboard
Tianshi Zheng, Jiazheng Wang, Zihao Wang, Jiaxin Bai, Hang Yin, Zheye Deng, Yangqiu Song, Jianxin Li
| Challenge: | Moreover, transformers have demonstrated proficiency in logical reasoning over natural language. |
| Approach: | They propose a logic-aware architecture that improves the performance in generalizable first-order logical entailment by combining distribution shifts and unseen knowledge. |
| Outcome: | The proposed architecture outperforms methods designed specifically for knowledge graph query answering on a dataset with a large dataset. |
Towards Self-Improving Error Diagnosis in Multi-Agent Systems (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing diagnostic approaches rely on expensive expert annotations and ”LLM-as-a-judge” paradigms. |
| Approach: | They propose a framework for semantic failure attribution that identifies responsible agents and the originating error step. |
| Outcome: | The proposed framework outperforms baselines in step-level localization and validation. |
PHEE: A Dataset for Pharmacovigilance Event Extraction from Text (2022.emnlp-main)
Copied to clipboard
Zhaoyue Sun, Jiazheng Li, Gabriele Pergola, Byron Wallace, Bino John, Nigel Greene, Joseph Kim, Yulan He
| Challenge: | Using NLP methods to discover and extract adverse drug events from unstructured textual data is difficult because it requires time-consuming manual curation. |
| Approach: | They propose to use a hierarchical event schema to extract annotated events from medical case reports and biomedical literature to analyze patient data. |
| Outcome: | The proposed dataset is the largest public dataset to date and contains over 5000 events from medical case reports and biomedical literature. |
ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development (2026.findings-acl)
Copied to clipboard
Jie Yang, Honglin Guo, Li Ji, Jiazheng Zhou, Rui Zheng, Zhikai Lei, Shuo Zhang, Zhiheng Xi, Shichun Liu, Yuxin Wang, Bo Wang, Yining Zheng, Tao Gui, Xipeng Qiu
| Challenge: | Large Language Models (LLMs) have redefined the role of AI in software engineering . current benchmarks focus on localized code generation, but neglect dynamic, full-process requirements of real-world engineering. |
| Approach: | They propose a benchmark to evaluate agentic backend coding within a realistic, executable workflow. |
| Outcome: | The ABC-Bench benchmark evaluates agentic backend coding within a realistic, executable workflow. |
Drift: Enhancing LLM Faithfulness in Rationale Generation via Dual-Reward Probabilistic Inference (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to improving LLM faithfulness rely on superficial calibration methods or costly retraining. |
| Approach: | They propose a probabilistic inference paradigm that leverages task-specific and lookahead rewards to ensure that LLM-generated rationales are more faithful to model decisions. |
| Outcome: | The proposed model improves both accuracy and faithfulness of Large Language Models (LLMs) on three reasoning tasks. |
A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code (2026.findings-acl)
Copied to clipboard
Keke Lian, Wang Bin, Lei Zhang, Libo Chen, Junjie Wang, Ziming Zhao, Yujiu Yang, Miaoqian Lin, Haotong Duan, Haoran Zhao, Shuang Liao, Mingda Guo, Quan Jiazheng, Yilu Zhong, Chenhao He, Chen Zichuan, Jie Wu, Haoling Li, Zhaoxuan Li, Jiongchi Yu, Hui LI, Dong Zhang
| Challenge: | Existing security evaluation benchmarks lack relevance to real-world AI programming tasks . current LLMs struggle with secure coding, research shows . |
| Approach: | They propose a repository-level evaluation benchmark to assess security of AI-generated code. |
| Outcome: | The proposed framework mirrors real-world AI programming tasks and offers valuable insights into the state of AI code generation. |