Papers by Ke Wu

Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning (2026.findings-acl)

Challenge:	Existing self-supervised methods in natural language processing rely on augmentation rules to generate contrastive samples.
Approach:	They propose a hierarchy-aware information lossless contrastive learning scheme that uses syntactic information reserved in the input sample and fused during the learning process.
Outcome:	The proposed learning scheme is superior to existing methods in hierarchical text classification . the proposed learning system is based on a structure encoder and a text encoder .

Copied to clipboard

Haiyang Yu, Yuchuan Wu, Fan Shi, Jinghui Lu, Ke Niu, Xiaodong Ge, Minghan Zhuo, Jingqun Tang, Bin Li

Detecting Latin in Historical Books with Large Language Models: A Multimodal Benchmark (2026.eacl-long)

Challenge:	Existing document benchmarks focus on English printed texts or simplified Chinese . current vision-language models struggle with visual complexity and poor adaptability .
Approach:	They propose a benchmark to evaluate Chinese ancient documents' visual/linguistic complexity . ancient documents are valuable cultural heritage, but they face challenges in digitization and understanding .
Outcome:	the first benchmark for Chinese ancient documents evaluates VLMs from OCR to knowledge reasoning . ancient documents carry thousands of years of Chinese history and culture . traditional methods only scan images, while current models struggle with visual complexity .

Copied to clipboard

Yu Wu, Ke Shu, Jonas Fischer, Lidia Pivovarova, David Rosson, Eetu Mäkelä, Mikko Tolonen

Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization (2024.acl-long)

Challenge:	This paper presents a novel task of extracting low-resourced and noisy Latin fragments from mixed-language historical documents with varied layouts.
Approach:	They propose to extract low-resourced and noisy Latin fragments from mixed-language historical documents with varied layouts using a multimodal dataset.
Outcome:	The proposed model lacks a functional comprehension of Latin, but reliable detection is achievable with zero-shot models.

Copied to clipboard

Wenqi Zhang, Ke Tang, Hai Wu, Mengna Wang, Yongliang Shen, Guiyang Hou, Zeqi Tan, Peng Li, Yueting Zhuang, Weiming Lu

Breaking the Evaluation Paradox: Evaluating High-Entropy Search with Computationally Irreducible Constraints (2026.findings-acl)

Challenge:	Large Language Models (LLMs) are designed as specific task solvers with sophisticated prompt engineering, but are inherently incapacitating to address complex dynamic scenarios.
Approach:	They propose an LLM-based agent with policy-level reflection and optimization that can learn from interactive experiences and progressively elevate its behavioral policy.
Outcome:	The proposed agent outperforms vanilla LLM and specialized models in blackjack and Texas hold’em.

Copied to clipboard

Juntao Wu, Wei Wen, Xianting Huang, Shuai Pang, Ruizhi Qiao, Xing Sun, Ke Wang

Information Retrieval

Challenge:	a new framework for evaluation of exhaustive search capabilities is needed . high-entropy enumeration tasks make such ground truth impossible for humans to create . VERITAS is a framework built on the principle of computationally irreducible constraints .
Approach:	They propose a framework that uses non-optimizable constraints to create verifiable searches . VERITAS can generate infinite number of test cases with perfect ground truth and precise difficulty control .
Outcome:	a new evaluation framework for large language models is based on non-optimizable constraints . the framework can generate infinite number of test cases with perfect ground truth and precise difficulty control .

Rethinking Text-based Protein Understanding: Retrieval or LLM? (2025.emnlp-main)

Copied to clipboard

Juntong Wu, Zijing Liu, He Cao, Li Hao, Bin Feng, Zishan Shu, Ke Yu, Li Yuan, Yu Li

Information Retrieval

Challenge:	Recent studies have focused on integrating protein-related knowledge into large language models through continued pretraining and multi-modal alignment.
Approach:	They propose a retrieval-enhanced method which significantly outperforms fine-tuned LLMs for protein-to-text generation and shows accuracy and efficiency in training-free scenarios.
Outcome:	The proposed method significantly outperforms fine-tuned LLMs for protein-to-text generation and shows accuracy and efficiency in training-free scenarios.

GR1: Reinforcement-Enhanced LLM for Geoscience Reasoning (2026.findings-acl)

Copied to clipboard

Yule Xie, Jiaxin Ding, Cheng Deng, Shiqing Gao, Junran Zhang, Sibo Zhang, Zeyuan Wang, Ke Wu, Xin Ding, Luoyi Fu, Meng Jin, Xinbing Wang

Reasoning

Challenge:	Recent advances in large language models have demonstrated RL's substantial capacity to enhance multi-step reasoning beyond what supervised instruction tuning achieves.
Approach:	They propose a framework that converts multimodal questions into descriptive text . they propose RL-enhanced geoscience reasoning that can be fine-tuned to a text-only level .
Outcome:	The proposed framework improves accuracy and accuracy on multimodal questions while preserving answerability and difficulty.

Beyond Templates: Dynamic Adaptation of Reasoning Demonstrations via Feasibility-Aware Exploration (2026.findings-acl)

Copied to clipboard

Yong Wu, Weihang Pan, Ke Li, Chen Binhui, Ping Li, Binbin Lin

Sinkhorn Distance Minimization for Knowledge Distillation (2024.lrec-main)

Challenge:	Existing reasoning datasets that are designed for powerful LLMs often lead to degraded performance when directly applied to weaker models.
Approach:	They propose a data adaptation framework that bridges the capability gap between expert reasoning trajectories and diverse SLMs by employing a selective imitation strategy guided by step-wise adaptability estimation via solution simulation.
Outcome:	The proposed framework improves generalization and data efficiency over static fine-tuning and can be applied to large models with limited model capacity.

Copied to clipboard

Xiao Cui, Yulei Qin, Yuting Gao, Enwei Zhang, Zihan Xu, Tong Wu, Ke Li, Xing Sun, Wengang Zhou, Houqiang Li

EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning (2025.acl-long)

Challenge:	Existing knowledge distillation methods investigate divergence measures but fail to deliver effective supervision when few distribution overlap exists between teacher and student.
Approach:	They propose a knowledge distillation method that exploits the Sinkhorn distance to ensure a nuanced assessment of the disparity between teacher and student distributions.
Outcome:	The proposed method outperforms state-of-the-art methods on all kinds of LLMs with encoder-only, encoder decoder, and decoded architectures.

Copied to clipboard

Xiaoqian Liu, Ke Wang, Yongbin Li, Yuchuan Wu, Wentao Ma, Aobo Kong, Fei Huang, Jianbin Jiao, Junge Zhang

Reasoning

Challenge:	Existing methods for strategic reasoning face challenges in adaptability, scalability, and transferring strategies to new contexts.
Approach:	They propose an explicit policy optimization model that provides strategies in open-ended action space and can be plugged into arbitrary LLM agents to motivate goal-directed behavior.
Outcome:	The proposed model provides strategies in open-ended action space and can be plugged into arbitrary LLM agents to motivate goal-directed behavior.

A Sentence is Worth 128 Pseudo Tokens: A Semantic-Aware Contrastive Learning Framework for Sentence Embeddings (2022.findings-acl)

Copied to clipboard

Haochen Tan, Wei Shao, Han Wu, Ke Yang, Linqi Song

Hierarchical Information Matters: Text Classification via Tree Based Graph Neural Network (2022.coling-1)

Challenge:	Existing approaches to contrastive learning are heavily affected by superficial features like sentence length and syntax.
Approach:	They propose a semantic-aware contrastive learning framework for sentence embeddings that explores the pseudo-token space representation of a sentence while eliminating the impact of superficial features such as sentence length and syntax.
Outcome:	The proposed framework outperforms the state-of-the-art on six standard semantic textual similarity tasks while maintaining an additional queue to store the representation of sentence embeddings.

Copied to clipboard

Chong Zhang, He Zhu, Xingyu Peng, Junran Wu, Ke Xu

Information Extraction & Text Mining

Challenge:	Text classification is a primary task in natural language processing (NLP).
Approach:	They propose a graph neural network (HINT) that makes full use of hierarchical information contained in the text for the task of text classification.
Outcome:	The proposed method outperforms the state-of-the-art methods on popular benchmarks while having a simple structure and few parameters.

SDPO: Segment-Level Direct Preference Optimization for Social Agents (2025.acl-long)

Copied to clipboard

Aobo Kong, Wentao Ma, Shiwan Zhao, Yongbin Li, Yuchuan Wu, Ke Wang, Xiaoqian Liu, Qicheng Li, Yong Qin, Fei Huang

Challenge:	Direct Preference Optimization (DPO) has proven effective in aligning LLM behavior with human preferences across various tasks, but is limited in multi-turn social interactions.
Approach:	They propose a method which dynamically selects key segments within interactions to optimize multi-turn agent behavior.
Outcome:	The proposed methods outperform existing methods and proprietary LLMs on the SOTOPIA benchmark and show that they can improve social intelligence.

SEC-FinTables: Evaluating Large Language Models for Detecting Logical Inconsistencies on Tabular Data (2026.findings-acl)

Copied to clipboard

Shuyan Ke, Qiong Wu, Hui Li, Liujuan Cao

QiMeng-Attention: SOTA Attention Operator is generated by SOTA Attention Algorithm (2025.findings-acl)

Challenge:	Large language models are increasingly deployed in high-stakes domains where logical inconsistencies are unrecognized.
Approach:	They propose a benchmarking system that decomposes inconsistency detection into granular subtasks and a protocol that decompiles it into subtask.
Outcome:	The proposed model decomposes inconsistencies into subtasks and identifies them in 103,395 real-world and error-injected table instances.

Copied to clipboard

Qirui Zhou, Shaohui Peng, Weiqiang Xiong, Haixin Chen, Yuanbo Wen, Haochen Li, Ling Li, Qi Guo, Yongwei Zhao, Ke Gao, Ruizhi Chen, Yanjun Wu, Zhao Chen, Yunji Chen

Programming Languages in NLP

Challenge:	Existing LLMs cannot comprehend the complex data flow and computation process of the attention operator and utilize low-level primitive to exploit GPU performance.
Approach:	They propose an LLM-friendly Thinking Language (LLM-TL) that can decouple the generation of high-level optimization logic and low-level implementation on GPU and enhance LLMs’ understanding of attention operator.
Outcome:	The proposed method outshines existing LLMs on A100, RTX8000, and T4 GPUs, achieving a speed-up of up to 35.16.

Watch Every Step! LLM Agent Learning via Iterative Step-level Process Refinement (2024.emnlp-main)

Copied to clipboard

Weimin Xiong, Yifan Song, Xiutian Zhao, Wenhao Wu, Xun Wang, Ke Wang, Cheng Li, Wei Peng, Sujian Li

SATBench: Benchmarking LLMs’ Logical Reasoning via Automated Puzzle Generation from SAT Formulas (2025.emnlp-main)

Challenge:	Recent approaches to enhance agent performance focus on outcome rewards, which may lead to errors or suboptimal actions due to the absence of process supervision signals.
Approach:	They propose a step-level framework that provides detailed step-by-step guidance to enhance agent training by using Monte Carlo methods.
Outcome:	The proposed framework outperforms strong baselines on three tasks and shows that it is effective in augmenting efficiency and its applicability to diverse models.

Copied to clipboard

Anjiang Wei, Yuheng Wu, Yingjia Wan, Tarun Suresh, Huanmi Tan, Zhanke Zhou, Sanmi Koyejo, Ke Wang, Alex Aiken

Reasoning

Challenge:	SATBench is a benchmark for evaluating the logical reasoning capabilities of large language models (LLMs) through logical puzzles derived from Boolean satisfiability (SAT) problems.
Approach:	They propose a benchmark to evaluate logical reasoning capabilities of large language models (LLMs) using logical puzzles derived from Boolean satisfiability problems.
Outcome:	The proposed model achieves 65.0% accuracy on hard UNSAT problems, close to the baseline of 50%.

Enhancing the General Agent Capabilities of Low-Paramter LLMs through Tuning and Multi-Branch Reasoning (2024.findings-naacl)

Copied to clipboard

Qinhao Zhou, Zihan Zhang, Xiang Xiang, Ke Wang, Yuchuan Wu, Yongbin Li

MOA: Multi-Objective Alignment for Role-Playing Agents (2026.acl-long)

Challenge:	Open-source pre-trained Large Language Models exhibit strong language understanding and generation capabilities, making them highly successful in a variety of tasks.
Approach:	They propose a method to construct agent-specific data using GPT-4 and supervised fine-tuning . they find that supervised tunning can significantly reduce hallucination outputs and formatting errors in agent tasks .
Outcome:	The proposed method improves on five agent tasks of AgentBench.

Copied to clipboard

Chonghua Liao, Ke Wang, Yuchuan Wu, Ruoran Li, Fei Huang, Yongbin Li

Challenge:	Prior work on role-playing agents relies on supervised fine-tuning or reinforcement learning with scalarized rewards, but these approaches do not address the coordination of multiple reward dimensions during optimization.
Approach:	They propose a reinforcement-learning framework that enables multi-dimensional, fine-grained rubric optimization for general RPAs.
Outcome:	Experiments on PersonaGym and RoleMRC show that MOA improves multi-dimensional role-playing performance over supervised and standard RL baselines.

AIDER: a Robust and Topic-Independent Framework for Detecting AI-Generated Text (2025.coling-main)

Copied to clipboard

Jiayi Gui, Baitong Cui, Xiaolian Guo, Ke Yu, Xiaofei Wu

Robustness in NLP

Challenge:	Current fine-tuned detectors lack robustness against adversarial attacks and struggle with out-of-distribution topics, limiting their practical applicability.
Approach:	They propose a topic-independent framework for detecting AI-generated text . it leverages the ALBERT model for topic content disentanglement, enhancing transferability to unseen topics.
Outcome:	The proposed framework outperforms state-of-the-art methods in detecting human-written and AI-generated content under adversarial and topic-varied conditions.

RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models (2024.findings-acl)

Copied to clipboard

Noah Wang, Z.y. Peng, Haoran Que, Jiaheng Liu, Wangchunshu Zhou, Yuhan Wu, Hongcheng Guo, Ruitong Gan, Zehao Ni, Jian Yang, Man Zhang, Zhaoxiang Zhang, Wanli Ouyang, Ke Xu, Wenhao Huang, Jie Fu, Junran Peng

DuSQL: A Large-Scale and Pragmatic Chinese Text-to-SQL Dataset (2020.emnlp-main)

Challenge:	Large Language Models (LLMs) have paved the way for complex tasks such as role-playing.
Approach:	They propose a framework to benchmark, elicit, and enhance role-playing abilities in Large Language Models.
Outcome:	The proposed framework improves role-playing abilities with 168,093 samples.

Copied to clipboard

Lijie Wang, Ao Zhang, Kun Wu, Ke Sun, Zhenghua Li, Hua Wu, Min Zhang, Haifeng Wang

Programming Languages in NLP

Challenge:	Existing text-to-SQL parsing methods mainly focus on English, but there is no labeled data available for the language . a larges-scale and pragmatic Chinese dataset is used for cross-domain text- to-Sql task .
Approach:	They propose a larges-scale Chinese dataset for a cross-domain text-to-SQL task . they analyze questions from several representative applications and use an effective data construction framework .
Outcome:	The proposed dataset contains 200 databases, 813 tables, and 23,797 question/SQL pairs.

Long-Form Speech Translation through Segmentation with Finite-State Decoding Constraints on Large Language Models (2023.findings-emnlp)

Copied to clipboard

Arya McCarthy, Hao Zhang, Shankar Kumar, Felix Stahlberg, Ke Wu

Text Generation

Challenge:	a challenge in speech translation is that plenty of spoken content is long-form, but short units are necessary for obtaining high-quality translations.
Approach:	They propose a large language model to split long ASR transcripts into segments that can be independently translated to maximize translation quality.
Outcome:	The proposed model improves the average BLEU by 2.9 points for English–German, English–Spanish, and English–Arabic TED talk translation in 9 sets.

AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs (2024.naacl-long)

Copied to clipboard

Yassir Fathullah, Chunyang Wu, Egor Lakomkin, Ke Li, Junteng Jia, Yuan Shangguan, Jay Mahadeokar, Ozlem Kalinli, Christian Fuegen, Mike Seltzer

FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents (2024.findings-emnlp)

Challenge:	a new model for speech processing and reasoning uses curated data instead of text.
Approach:	They extend the instruction-tuned Llama-2 model with end-to-end speech processing and reasoning abilities without using any carefully curated paired data.
Outcome:	The proposed model outperforms or outperfects existing models on synthesized and recorded speech QA tests.

Copied to clipboard

Ruixuan Xiao, Wentao Ma, Ke Wang, Yuchuan Wu, Junbo Zhao, Haobo Wang, Fei Huang, Yongbin Li

Challenge:	LLM-based agents are susceptible to undesired planning hallucinations when lacking specific knowledge for expertise-intensive tasks.
Approach:	They propose a benchmark to evaluate the efficacy of workflow-guided agent planning by formalizing different formats of workflow knowledge.
Outcome:	The proposed benchmark aims to improve the planning reliability of LLM-based agents by incorporating external workflow-related knowledge.

Relaxing the Constraints: A Dual-Importance Projection Mechanism for Lifelong Model Editing (2026.findings-acl)

Copied to clipboard

Zhenghai Chen, Senbin Xu, Jiaxi Tan, Xinhua Wu, Yan Zhang, Xiawu Zheng, Shengchuan Zhang, Ke Li, Sicheng Zhao, Liujuan Cao, Rongrong Ji

LMOD: A Large Multimodal Ophthalmology Dataset and Benchmark for Large Vision-Language Models (2025.findings-naacl)

Challenge:	Existing knowledge editing methods rely on strict orthogonal projection to preserve previously edited knowledge, but this constraint limits gradient expressiveness, resulting in degradation of model generalization and overall performance as the number of edits increases.
Approach:	They propose a method that leverages Singular Value Decomposition to identify critical gradient subspaces and introduces a dual mechanism comprising "accumulated importance" and "projection importance"
Outcome:	Extensive experiments on five mainstream LLMs show that the proposed method achieves an average comprehensive performance improvement of 10.36% and effectively maintains the model’s general capabilities on downstream tasks.

Copied to clipboard

Zhenyue Qin, Yu Yin, Dylan Campbell, Xuansheng Wu, Ke Zou, Ninghao Liu, Yih Chung Tham, Xiuzhen Zhang, Qingyu Chen

HiTIN: Hierarchy-aware Tree Isomorphism Network for Hierarchical Text Classification (2023.acl-long)

Challenge:	Existing benchmarks for large vision-language models (LVLMs) are limited to ophthalmology-specific applications.
Approach:	They introduce a large-scale multimodal ophthalmology benchmark consisting of 21,993 instances across five ocular imaging modalities and 13 state-of-the-art LVLM representatives from closed-source, open-source and medical domains.
Outcome:	The proposed model shows significant performance drop in ophthalmology compared to other domains.

Copied to clipboard

He Zhu, Chong Zhang, Junjie Huang, Junran Wu, Ke Xu

Multi-modal Semantic Understanding with Contrastive Cross-modal Feature Alignment (2024.lrec-main)

Challenge:	Existing dual-encoder methods in HTC achieve weak performance gains with huge memory overheads and their structure encoders heavily rely on domain knowledge.
Approach:	They propose a hierarchy-aware tree isomorphism network to enhance the text representations with only syntactic information of the label hierarchy.
Outcome:	The proposed model could boost the performance of hierarchical text classification without prior statistics or label semantics without prior data.

Copied to clipboard

Ming Zhang, Ke Chang, Yunfang Wu