Papers by Zhicheng Yang
CLOMO: Counterfactual Logical Modification with Large Language Models (2024.acl-long)
Copied to clipboard
Yinya Huang, Ruixin Hong, Hongming Zhang, Wei Shao, Zhicheng Yang, Dong Yu, Changshui Zhang, Xiaodan Liang, Linqi Song
| Challenge: | Existing studies on evaluating model reasoning are limited in both form and content. |
| Approach: | They propose a task to cultivate counterfactual thought processes within large language models and an evaluation metric to evaluate their natural language output instead of modeling the task as a multiple-choice problem. |
| Outcome: | The proposed evaluation metric aligns well with human preference. |
Defending against Indirect Prompt Injection by Instruction Detection (2025.findings-emnlp)
Copied to clipboard
Tongyu Wen, Chenglong Wang, Xiyuan Yang, Haoyu Tang, Yueqi Xie, Lingjuan Lyu, Zhicheng Dou, Fangzhao Wu
| Challenge: | Indirect Prompt Injection attacks can be exploited by LLMs that are embedded with external data. |
| Approach: | They propose a detection-based approach that leverages the behavioral states of LLMs to identify potential IPI attacks. |
| Outcome: | The proposed approach reduces the success rate of attacks to 0.03% on the BIPIA benchmark. |
Understanding GUI Agent Localization Biases through Logit Sharpness (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Multimodal large language models often exhibit hallucinations that compromise reliability . despite promising performance, these models often display systematic localization errors . |
| Approach: | They propose a framework that categorizes model predictions into four distinct types . they propose metric that evaluates alignment between semantic continuity and logits distribution . |
| Outcome: | The proposed framework categorizes model predictions into four different types . it reveals nuanced failure modes beyond traditional accuracy metrics . |
Unbiased Math Word Problems Benchmark for Mitigating Solving Bias (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing solvers with data bias and learning bias only learn shallow heuristics rather than deep semantics for understanding problems. |
| Approach: | They propose a MWP dataset named UnbiasedMWP which is constructed by varying the grounded expressions in collected data and annotating them manually. |
| Outcome: | The proposed dataset has significantly fewer biases than its original data and other datasets, posing a promising benchmark for fairly evaluating the solvers’ reasoning skills rather than matching nearest neighbors. |
When Inverse Data Outperforms: Exploring the Pitfalls of Mixed Data in Multi-Stage Fine-Tuning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for o1-level performance focus on unidirectional supervised fine-tuning (SFT), overlooking the intricate interplay between diverse reasoning patterns. |
| Approach: | They construct a reverse reasoning dataset and examine how it is supervised . they find that naively mixing forward and reverse data during SFT weakens the directional distinction . |
| Outcome: | The proposed model improves accuracy by 1.6%–6.8% over a standard model. |
Aligning Paralinguistic Understanding and Generation in Speech LLMs via Multi-Task Reinforcement Learning (2026.eacl-industry)
Copied to clipboard
Minseok Kim, Jingxiang Chen, Seong-Gyun Leem, Yin Huang, Rashi Rungta, Zhicheng Ouyang, Haibin Wu, Surya Teja Appini, Ankur Bansal, Yang Bai, Yue Liu, Florian Metze, Ahmed A Aly, Anuj Kumar, Ariya Rastrow, Zhaojiang Lin
| Challenge: | Using paralinguistic cues is challenging for speech large language models, authors say . limited training data, annotation difficulty, and models exploiting lexical shortcuts are challenges . a recent study shows that modeling paralinguistic reasoning with multitask RL improves paralinguistics understanding . |
| Approach: | They propose multi-task reinforcement learning with chain-of-thought prompting that elicits explicit affective reasoning. |
| Outcome: | The proposed model improves paralinguistics understanding over baselines and strong proprietary models by 8-12% on Expresso, IEMOCAP, and RAVDESS. |
Value Compass Benchmarks: A Comprehensive, Generative and Self-Evolving Platform for LLMs’ Value Evaluation (2025.acl-demo)
Copied to clipboard
Jing Yao, Xiaoyuan Yi, Shitong Duan, Jindong Wang, Yuzhuo Bai, Muhua Huang, Yang Ou, Scarlett Li, Peng Zhang, Tun Lu, Zhicheng Dou, Maosong Sun, James Evans, Xing Xie
| Challenge: | Current evaluation methods for large language models face two key challenges: 1. evaluation validity and 2. Result interpretation reduce the pluralistic and incommensurable values to one-dimensional scores. |
| Approach: | They propose a platform for comprehensive value diagnosis of large language models (LLMs) that provides a generative evaluation paradigm that automatically creates real-world test items co-evolving with ever-advancing LLMs. |
| Outcome: | The proposed platform provides a framework for comprehensive value diagnosis of large language models (LLMs) with fine-grained scores and case studies across 27 value dimensions for 33 leading LLMs, customized comparisons, and visualized analysis of LLM’s alignment with cultural values. |
Prompt-Guided Retrieval Augmentation for Non-Knowledge-Intensive Tasks (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent studies focus on retrieval to solve knowledge-intensive tasks, but the potential of retrieval for non-knowledge-intensive (NKI) tasks remains under-explored. |
| Approach: | They propose a task-agnostic retrieval framework for NKI tasks that uses a static index and a prompt-guided reranker to re-rank the nearest evidence according to task-specific relevance. |
| Outcome: | The proposed framework outperforms state-of-the-art retrieval-augmented methods on NKI tasks and will be released for further research. |
AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing LLMs are delicate and elusive in prompt words and styles. |
| Approach: | They propose an LLM-acquainted prompting technique that includes proficient "native-speaking" they propose to use in-context learning to prompt LLMs to perform high-performance reasoning . |
| Outcome: | The proposed technique achieves step-wise prompts in zero-shot scenarios while maintaining the prompt quality. |
StableToolBench-MirrorAPI: Modeling Tool Environments as Mirrors of 7,000+ Real-World APIs (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing tool environments face challenges in balancing stability, scale, and realism, especially for benchmarking purposes. |
| Approach: | They propose a framework that trains specialized LLMs to accurately simulate real API responses by supervised fine-tuning and chain-of-thought reasoning. |
| Outcome: | The proposed framework achieves superior accuracy and stability compared to state-of-the-art methods on the newly constructed MirrorAPI-Bench and its integration into StableToolBench. |
CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases (2025.naacl-long)
Copied to clipboard
Xiangyan Liu, Bo Lan, Zhiyuan Hu, Yang Liu, Zhicheng Zhang, Fei Wang, Michael Qizhe Shieh, Wenmeng Zhou
| Challenge: | Large Language Models excel in stand-alone code tasks but struggle with handling entire code repositories. |
| Approach: | They propose a system that integrates LLM agents with graph database interfaces extracted from code repositories. |
| Outcome: | The proposed system integrates LLM agents with graph database interfaces extracted from code repositories. |
Web Sitemap Knowledge Can Enhance Autonomous Browsing (2026.findings-acl)
Copied to clipboard
Yuyao Zhang, Hongyu Lu, Jiajie Jin, Hongjin Qian, Shiyu Li, Zhao Yang, Yutao Zhu, Ji-Rong Wen, Zhicheng Dou
| Challenge: | Existing web agents suffer from limited robustness, efficiency and task success due to lack of structural understanding of websites and lack of browsing priors in pre-trained models. |
| Approach: | They propose an agent-oriented sitemap protocol that integrates structured website knowledge into web agents. |
| Outcome: | The proposed agent-oriented sitemap improves robustness, efficiency and effectiveness without extra training. |
Decoding in Latent Spaces for Efficient Inference in LLM-based Recommendation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Light Latent-space Decoding (L2D) is an efficient and efficient latent- space decoding method. |
| Approach: | They propose to bypass language-space decoding by matching candidate items with LLM's internal thought representations in the latent space. |
| Outcome: | The proposed method is 10x faster than language-space decoding while maintaining or enhancing performance. |
ATG: Benchmarking Automated Theorem Generation for Generative Language Models (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing generative language models (LMs) can generate new or reusable theorems, but their ability to generate new theorels is under-explored. |
| Approach: | They propose to use Metamath library to generate new theorems that can be saved as reusable knowledge for future theoretical proving. |
| Outcome: | The proposed benchmark evaluates whether an agent can generate valuable (and possibly brand new) theorems that are applicable for downstream theoretic proving as reusable knowledge. |
StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models (2024.findings-acl)
Copied to clipboard
Zhicheng Guo, Sijie Cheng, Hao Wang, Shihao Liang, Yujia Qin, Peng Li, Zhiyuan Liu, Maosong Sun, Yang Liu
| Challenge: | Large Language Models (LLMs) have witnessed remarkable advancements in recent years, prompting the exploration of tool learning. |
| Approach: | They propose a virtual API server and stable evaluation system to assess the stability of large-scale real-time APIs. |
| Outcome: | The proposed benchmarks demonstrate the stability of the proposed system and its caching system. |
HealMe: Harnessing Cognitive Reframing in Large Language Models for Psychotherapy (2024.acl-long)
Copied to clipboard
Mengxi Xiao, Qianqian Xie, Ziyan Kuang, Zhicheng Liu, Kailai Yang, Min Peng, Weiguang Han, Jimin Huang
| Challenge: | Large Language Models (LLMs) can be used in psychotherapy to overcome challenges such as shame, distrust, and resource scarcity. |
| Approach: | They propose a cognitive reframing therapy method that uses empathetic dialogue to address deep-rooted negative thoughts and fosters rational, balanced perspectives. |
| Outcome: | The proposed model outperforms other models in terms of empathy, guidance, and logical coherence, demonstrating its effectiveness and potential positive impact on psychotherapy. |
Little Giants: Synthesizing High-Quality Embedding Data at Scale (2025.naacl-long)
Copied to clipboard
| Challenge: | Synthetic data generation is an increasingly popular way of training models without the need for large, manually labeled datasets. |
| Approach: | They propose a framework that aligns open-source small models to efficiently generate large-scale embedding data. |
| Outcome: | The proposed framework outperforms state-of-the-art embedding models by using only 1/10 of the GPT API calls. |
Lightweight LLM Agent Memory with Small Language Models (2026.acl-long)
Copied to clipboard
Jiaquan Zhang, Chaoning Zhang, Shuxu Chen, Zhenzhen Huang, Pengcheng Zheng, Zhicheng Wang, Ping Guo, Fan Mo, Sung-Ho Bae, Jie Zou, Jiwei Wei, Yang Yang
| Challenge: | Existing external memory systems for LLMs have low online overhead but are unstable in accumulating latency over long interactions. |
| Approach: | They propose a lightweight memory system for better agent memory driven by Small Language Models . lightmem modularizes memory retrieval, writing, and long-term consolidation . they show consistent gains across model scales and high efficiency . |
| Outcome: | The proposed system improves agent memory but has low latency and low online overhead . it separates online processing from offline consolidation to enable efficient memory invocation . the proposed system achieves an average F1 improvement of 2.5 over A-MEM on LoCoMo . |
GLARE: Agentic Reasoning for Legal Judgment Prediction (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models struggle with fine-grained distinctions between similar charges. |
| Approach: | They propose an agentic legal reasoning framework that actively retrieves external knowledge during decision-making. |
| Outcome: | The proposed model outperforms baseline models on complex cases involving confusing or rare charges on real-world datasets. |
mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data (2025.findings-acl)
Copied to clipboard
| Challenge: | Multimodal embedding models encode multimedia inputs into latent vector representations. |
| Approach: | They propose to synthesize multimodal multilingual data using a multimodal large language model . they identify three criteria for high-quality synthetic multimodal data . |
| Outcome: | The proposed model outperforms existing models on the MMEB Benchmark and the XTD benchmark. |
LogicSolver: Towards Interpretable Math Word Problem Solving with Logical Prompt-enhanced Learning (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in MWP solving are uninterpretable due to shallow heuristics . a new approach to solve automatic word problem solvers requires a solver to predict expression tree and corresponding linguistic logic formulas simultaneously. |
| Approach: | They propose to annotate interpretable logical formulas based on algebraic knowledge as the grounded linguistic logic of each solution equation. |
| Outcome: | The proposed approach improves interpretability of a MWP solver by using logical prompts and interpretation generation. |
SRAP-Agent: Simulating and Optimizing Scarce Resource Allocation Policy with LLM-based Agent (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing research on the allocation of public scarce resources has limitations due to data scarcity and data scariness. |
| Approach: | They propose a framework that integrates Large Language Models into economic simulations . they conduct extensive policy simulation experiments to verify the framework's effectiveness . |
| Outcome: | The proposed framework bridges the gap between theoretical models and real-world dynamics by integrating large language models into economic simulations. |
MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to embed multimodal models face limitations such as suboptimal causal attention in VLMs and limited diversity in training objectives and data. |
| Approach: | They propose a framework for transforming pre-trained VLMs into bidirectional multimodal embedding models. |
| Outcome: | The proposed model improves performance across MMEB and ViDoRe-v2 benchmarks and exhibits strong scalability with both model size and training data on MMEF. |
VC4VG: Optimizing Video Captions for Text-to-Video Generation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in text-to-video generation highlight the critical role of high-quality video-text pairs in training models capable of producing coherent and instruction-aligned videos. |
| Approach: | They propose a caption optimization framework tailored to the needs of T2V models. |
| Outcome: | The proposed framework improves video caption quality and video generation performance. |
EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing lightweight approaches to retrieval-augmented generation fail to capture latent semantic connections between disjoint entities. |
| Approach: | They propose a lightweight RAG framework that constructs a hypergraph capturing both structure and semantic relationships using a hybrid structural-semantic retrieval mechanism. |
| Outcome: | EHRAG outperforms state-of-the-art methods on four datasets while maintaining zero token consumption. |