Papers by Zihao Cheng
LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing (2024.emnlp-main)
Copied to clipboard
Jiangshu Du, Yibo Wang, Wenting Zhao, Zhongfen Deng, Shuaiqi Liu, Renze Lou, Henry Zou, Pranav Narayanan Venkit, Nan Zhang, Mukund Srinath, Haoran Zhang, Vipul Gupta, Yinghui Li, Tao Li, Fei Wang, Qin Liu, Tianlin Liu, Pengzhi Gao, Congying Xia, Chen Xing, Cheng Jiayang, Zhaowei Wang, Ying Su, Raj Shah, Ruohao Guo, Jing Gu, Haoran Li, Kangda Wei, Zihao Wang, Lu Cheng, Surangika Ranathunga, Meng Fang, Jie Fu, Fei Liu, Ruihong Huang, Eduardo Blanco, Yixin Cao, Rui Zhang, Philip Yu, Wenpeng Yin
| Challenge: | a comparative analysis of paper (meta-)reviews by large language models (LLMs) aims to identify and distinguish LLMs from human activities . |
| Approach: | They present a comparative analysis to identify and distinguish LLM activities from human activities. |
| Outcome: | The proposed analysis aims to improve recognition of instances when someone implicitly uses LLMs for reviewing activities. |
RepoDebug: Repository-Level Multi-Task and Multi-Language Debugging Evaluation of Large Language Models (2025.findings-emnlp)
Copied to clipboard
Jingjing Liu, Zeming Liu, Zihao Cheng, Mengliang He, Xiaoming Shi, Yuhang Guo, Xiangrong Zhu, Yuanfang Guo, Yunhong Wang, Haifeng Wang
| Challenge: | Large Language Models (LLMs) have exhibited significant proficiency in code debugging, especially in automatic program repair. |
| Approach: | They propose a repository-level code debugging dataset with 22 subtypes of errors that supports 8 commonly used programming languages and 3 debug tasks. |
| Outcome: | The proposed dataset supports 8 commonly used programming languages and 3 debugging tasks. |
ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models (2024.emnlp-main)
Copied to clipboard
Yuxiang Zhang, Jing Chen, Junjie Wang, Yaxin Liu, Cheng Yang, Chufan Shi, Xinyu Zhu, Zihao Lin, Hanwen Wan, Yujiu Yang, Tetsuya Sakai, Tian Feng, Hayato Yamana
| Challenge: | Currently, tool-augmented large language models (LLMs) only achieve total scores of 45.3 and 37.0, respectively, on a scale of 100. |
| Approach: | They propose a multi-level diagnostic process to assess the LLM's hallucinations through two perspectives: depth and breadth. |
| Outcome: | The proposed diagnostic process assesses the hallucinations of large language models through two perspectives: depth and breadth. |
ToolSpectrum: Towards Personalized Tool Utilization for Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches focus on functional tool selection following user instructions while overlooking the critical role of context-aware personalization in tool selection. |
| Approach: | They propose a benchmark to evaluate LLMs’ capabilities in personalized tool utilization. |
| Outcome: | The proposed benchmark evaluates LLMs' capabilities in personalized tool utilization. |
MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Existing studies on knowledge editing focus on monolingual scenarios, neglecting the complexities presented by multilingual contexts and multi-hop reasoning. |
| Approach: | They propose a benchmark to evaluate the adaptability of multilingual knowledge editing methods. |
| Outcome: | The proposed benchmark evaluates the adaptability of multilingual knowledge editing methods across five languages. |
RouteRAG: Efficient Retrieval-Augmented Generation from Text and Graph via Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing graph-based or hybrid systems lack the ability to integrate supplementary evidence as reasoning unfolds. |
| Approach: | They propose a framework that integrates non-parametric knowledge into Large Language Models . they use a RL-based framework to optimize the entire generation process via RL . |
| Outcome: | The proposed framework outperforms existing RAG frameworks in five question answering benchmarks. |
Multi-Agent Collaboration via Cross-Team Orchestration (2025.findings-acl)
Copied to clipboard
Zhuoyun Du, Chen Qian, Wei Liu, Zihao Xie, YiFei Wang, Rennai Qiu, Yufan Dang, Weize Chen, Cheng Yang, Ye Tian, Xuantang Xiong, Lei Han
| Challenge: | Large Language Models (LLMs) have significantly impacted various domains, especially through organized LLM-driven autonomous agents. |
| Approach: | They propose a framework that enables orchestrated teams to jointly propose various task-oriented solutions and interact with their insights in a self-independence while cross-team collaboration environment for superior solutions generation. |
| Outcome: | Experiments show that the framework can generate better software quality compared to state-of-the-art frameworks. |
ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models (2025.acl-long)
Copied to clipboard
Hanxing Ding, Shuchang Tao, Liang Pang, Zihao Wei, Jinyang Gao, Bolin Ding, Huawei Shen, Xueqi Cheng
| Challenge: | Existing approaches to tool learning rely on hand-crafted prompts and natural language reasoning, making multi-step planning difficult and lacking precise error diagnosis and reflection mechanisms. |
| Approach: | They propose a framework that reformulates tool learning as a code generation task. |
| Outcome: | The proposed framework achieves superior performance in task completion accuracy and execution reliability compared to existing approaches. |
Reinforcement Learning on Pre-Training Data (2026.acl-long)
Copied to clipboard
Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Kun Li, Haoyuan Wu, null Wujiajia, Zihao Zheng, Chenchen Zhang, Kun Shi, Xue Gong, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang xu, Zheng Fang, Shuai LI, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bochao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Bo Zhou, Di Wang
| Challenge: | Recent progress in large language models is driven by scaling of training compute through pre-training with nexttoken prediction (NTP) or post-training (RL) Pre-training using NTP enables models to acquire extensive knowledge and skills from general data, but it suffers from data inefficiency and catastrophic forgetting in continual learning settings. |
| Approach: | They propose to scale training compute through pre-training with next-token prediction (NTP) or post-training by scaling reinforcement learning (RL) to improve learning from general data. |
| Outcome: | Experiments on multiple benchmarks and models show that the proposed approach improves continual pre-training and provides a strong foundation for post-training on Qwen3-8B-Base. |
LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning (2025.emnlp-main)
Copied to clipboard
Tianshi Zheng, Cheng Jiayang, Chunyang Li, Haochen Shi, Zihao Wang, Jiaxin Bai, Yangqiu Song, Ginny Wong, Simon See
| Challenge: | Modern large language models (LLMs) employ diverse logical inference mechanisms for reasoning. |
| Approach: | They analyze the comparative dynamics of inductive (System 1) versus abductive/deductive (system 2) inference in large language models by using a controlled analogical reasoning environment and a MCQ/free-text task format. |
| Outcome: | The proposed methods can significantly scale LLM reasoning. |
Mem2Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillation (2026.acl-long)
Copied to clipboard
Zihao Cheng, Zeming Liu, Yingyu Shan, Xinyi Wang, Xiangrong Zhu, Yunpu Ma, Hongru Wang, Yuhang Guo, Wei Lin, Yunhong Wang
| Challenge: | Existing frameworks that focus on static tools and static assets are ineffective for self-evolving agents. |
| Approach: | They propose a paradigm of co-evolutionary Capability Expansion and Experience Distillation that leverages accumulated experience to guide dynamic creation of assets. |
| Outcome: | The proposed framework improves performance in single-task and cross-task settings by 18.53% over standard LLMs, 11.80% over agents evolving solely through experience, and 6.46% over those evolving solelly through asset creation. |
MacLaSa: Multi-Aspect Controllable Text Generation via Efficient Sampling from Compact Latent Space (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to multi-aspect controllable text generation require expensive iteration / searching within the discrete text space during the decoding stage, resulting in a degradation of text quality due to the domain discrepancies between different aspects. |
| Approach: | They propose a framework that estimates compact latent space for multiple aspects and performs efficient Sampling with a fast sampler to eliminate domain discrepancies. |
| Outcome: | The proposed framework outperforms baselines on attribute relevance and textual quality while maintaining a high inference speed. |
Experiential Co-Learning of Software-Developing Agents (2024.acl-long)
Copied to clipboard
Chen Qian, Yufan Dang, Jiahao Li, Wei Liu, Zihao Xie, YiFei Wang, Weize Chen, Cheng Yang, Xin Cong, Xiaoyin Che, Zhiyuan Liu, Maosong Sun
| Challenge: | Recent advances in large language models (LLMs) have brought significant changes to various domains, especially through autonomous agents. |
| Approach: | They propose a framework that lets agents learn shortcuts from their past tasks and use them for future task execution. |
| Outcome: | The proposed framework enables agents to tackle unseen software-developing tasks more effectively. |
The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis (2026.acl-long)
Copied to clipboard
Zihao Wei, Liang Pang, Jiahao Liu, Wenjie Shi, Jingcheng Deng, Shicheng Xu, Zenghao Duan, Jingang Wang, Fei Sun, Huawei Shen, Xueqi Cheng
| Challenge: | Explicit reasoning trajectories increase performance but often trigger overthinking . despite its importance, this study examines how each step of reasoning affects the final outcome . |
| Approach: | They propose a Reasoning Completion Point Detector that detects the RCP by monitoring rank dynamics of termination tokens. |
| Outcome: | The proposed method reduces token usage by up to 44% while preserving accuracy. |
Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment (2025.emnlp-main)
Copied to clipboard
Jingcheng Deng, Zhongtao Jiang, Liang Pang, Zihao Wei, Liwei Chen, Kun Xu, Yang Song, Huawei Shen, Xueqi Cheng
| Challenge: | Experimental results demonstrate that our method significantly outperforms traditional contrastive learning approaches when using the same amount of data. |
| Approach: | They propose a new contrastive learning method built on embedding conditional probability distributions that integrates two tasks: information compression and conditional distribution alignment. |
| Outcome: | The proposed method outperforms traditional contrastive learning approaches and achieves comparable performance to state-of-the-art models when using the same amount of data. |