Papers by Zhiwei Wang

ParroT: Translating during Chat using Large Language Models tuned with Human Translation and Feedback (2023.findings-emnlp)

Challenge:	Existing methods for reinforcement learning with verifiable rewards suffer from limited exploration diversity and inefficient reasoning.
Approach:	They propose a method that rewards concise and correct reasoning while penalizing unnecessarily long reasoning chains.
Outcome:	Extensive experiments on Qwen and Llama models validate the effectiveness and efficiency of ROSE.

Copied to clipboard

Wenxiang Jiao, Jen-tse Huang, Wenxuan Wang, Zhiwei He, Tian Liang, Xing Wang, Shuming Shi, Zhaopeng Tu

RFS-Guard: Detecting Reasoning Hallucinations via Cross-Phase Routing Focus in Large Reasoning Models (2026.acl-long)

Challenge:	Large language models (LLMs) like ChatGPT are only accessible through restricted APIs, which creates barriers to new research and advancements in the field.
Approach:	They propose a framework to enhance and regulate the translation abilities during chat . they reformulate translation data into the instruction-following style and introduce a "Hint" field .
Outcome:	The proposed framework enhances and regulates the translation abilities during chat . it reformulates translation data into the instruction-following style and introduces a "Hint" field .

Copied to clipboard

Zihang Liu, Fang Zhouhua, Hui Liu, Zhiwei Liu, Yong Li, Haishuai Wang

Draft Model Knows When to Stop: Self-Verification Speculative Decoding for Long-Form Generation (2025.emnlp-main)

Challenge:	Large reasoning models (LRMs) generate intermediate reasoning traces before the final answer, yet they remain vulnerable to reasoning hallucinations such as subtle arithmetic errors.
Approach:	They propose a Routing Focus Score (RFS) that measures how strongly cross-step attention routing aligns with semantic proximity derived from hidden-state cosine similarity.
Outcome:	The proposed framework detects and localizes hallucinations without external tools or repeated sampling.

Copied to clipboard

Ziyin Zhang, Jiahao Xu, Tian Liang, Xingyu Chen, Zhiwei He, Rui Wang, Zhaopeng Tu

ActionStudio: A Lightweight Framework for Data and Training of Large Action Models (2025.emnlp-main)

Challenge:	Conventional speculative decoding methods use a predefined length policy for proposing drafts, but the reality deviates from this assumption.
Approach:	They propose a self-verification length policy that adaptively determines the lengths of draft sequences by referring to the draft entropy.
Outcome:	The proposed method achieves 17% speedup on MT-Bench and 22% speedup in long-form reasoning.

Copied to clipboard

Jianguo Zhang, Thai Quoc Hoang, Ming Zhu, Zuxin Liu, Shiyu Wang, Tulika Manoj Awalgaonkar, Akshara Prabhakar, Haolin Chen, Weiran Yao, Zhiwei Liu, Juntao Tan, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong

Challenge:	Existing infrastructure for efficient agentic data processing and model training remains underdeveloped.
Approach:	They propose a lightweight and extensible data and training framework for large action models . they propose to unify diverse agent trajectories using Unified Format 2.0 .
Outcome:	The proposed framework shows 9 higher throughput than existing frameworks and performs well across public and realistic agent benchmarks.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs (2025.acl-long)

Copied to clipboard

Yuchen Fu, Zifeng Cheng, Zhiwei Jiang, Zhonghui Wang, Yafeng Yin, Zhengliang Li, Qing Gu

Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent Systems (2025.findings-emnlp)

Challenge:	Recent studies have focused on prompt engineering to extract sentence embeddings from large language models (LLMs) but these models are mostly decoder-only and the earlier tokens in the sentence cannot attend to the latter, resulting in biased encoding of sentence information and cascading effects on the final decoded token.
Approach:	They propose a plug-and-play and training-free technique that prepends each layer’s decoded sentence embedding to the beginning of the sentence in the next layer’ s input.
Outcome:	The proposed technique can significantly improve the performance of existing prompt-based sentence embedding methods across different LLMs while incurring negligible additional inference cost.

Copied to clipboard

Minghang Zhu, Zhengliang Shi, Zhiwei Xu, Shiguang Wu, Lingjie Wang, Pengjie Ren, Zhaochun Ren, Zhumin Chen

Challenge:	Existing methods for fine-tuning agents are often inadequate . a multi-agent system can solve complex tasks by dividing responsibilities among specialized agents .
Approach:	a new framework is proposed to improve agents collaboration through iterative alignment.
Outcome:	The proposed framework outperforms state-of-the-art benchmarks on held-in and held-out tasks.

Encouraging Good Processes Without the Need for Good Answers: Reinforcement Learning for LLM Agent Planning (2025.emnlp-industry)

Copied to clipboard

Zhiwei Li, Yong Hu, Wenqing Wang

Challenge:	Currently, the dominant end-to-end reinforcement learning paradigm for agents in Large Language Models (LLMs) employs multi-objective optimization that jointly trains both planning and answer summarization capabilities.
Approach:	They propose a framework that decouples the training process to enable a focused, single-objective optimization of the planning module.
Outcome:	The proposed framework achieves an 8%–12% improvement in planning performance compared to end-to-end baselines.

PersonaBench: Evaluating AI Models on Understanding Personal Information through Accessing (Synthetic) Private User Data (2025.findings-acl)

Copied to clipboard

Juntao Tan, Liangwei Yang, Zuxin Liu, Zhiwei Liu, Rithesh R N, Tulika Manoj Awalgaonkar, Jianguo Zhang, Weiran Yao, Ming Zhu, Shirley Kokane, Silvio Savarese, Huan Wang, Caiming Xiong, Shelby Heinecke

PairCFR: Enhancing Model Training on Paired Counterfactually Augmented Data through Contrastive Learning (2024.acl-long)

Challenge:	Existing research lacks direct access to such data, making benchmarking difficult due to privacy concerns.
Approach:	They propose a synthetic data pipeline that generates realistic user profiles and private documents and a benchmark to evaluate models' ability to understand personal information.
Outcome:	The proposed pipeline generates realistic user profiles and private documents, enabling PersonaBench, a benchmark for evaluating models’ ability to understand personal information.

Copied to clipboard

Xiaoqi Qiu, Yongjie Wang, Xu Guo, Zhiwei Zeng, Yu Yue, Yuhong Feng, Chunyan Miao

EXPLAIN: Enhancing Retrieval-Augmented Generation with Entity Summary (2025.acl-industry)

Challenge:	Recent research shows that training with CAD may lead models to overly focus on modified features while ignoring other important contextual information.
Approach:	They propose to use contrastive learning to promote global feature alignment and learning counterfactual clues to improve model performance.
Outcome:	The proposed method outperforms the state-of-the-art on out-of distribution (OOD) datasets.

Copied to clipboard

Yaozhen Liang, Xiao Liu, Jiajun Yu, Zhouhua Fang, Qunsheng Zou, Linghan Zheng, Yong Li, Zhiwei Liu, Haishuai Wang

Explainability & Interpretability in NLP

Challenge:	Existing document question answering methods reduce inference costs and input tokens.
Approach:	They propose a retrieval-augmented generation method that automatically extracts useful entities and generates summaries from documents.
Outcome:	The proposed method surpasses baseline retrieval-augmented generation (RAG) and long-context question answering (LC) methods achieve higher accuracy by processing entire documents, but at the cost of increased computational Corresponding authors.

Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors (2026.acl-long)

Copied to clipboard

Zhiwei Zhang, Fei Zhao, Rui Wang, Zezhong Wang, Bin Liang, Jiakang Wang, Yao Hu, Shaosheng Cao, Kam-Fai Wong

Robustness in NLP

Challenge:	Large language models (LLMs) can call tools effectively, but they remain brittle in multi-turn execution.
Approach:	They propose a framework that converts execution errors into on-policy corrective supervision within the RL training loop.
Outcome:	The proposed framework improves the error recovery rate of Qwen3-8B by 5.7% absolute and overall accuracy by 4.0% on BFCL v4 Multi-Turn.

Aggregating Multiple Heuristic Signals as Supervision for Unsupervised Automated Essay Scoring (2023.acl-long)

Copied to clipboard

Cong Wang, Zhiwei Jiang, Yafeng Yin, Zifeng Cheng, Shiping Ge, Qing Gu

Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model (2024.naacl-long)

Challenge:	Automated Essay Scoring (AES) aims to evaluate the quality score of input essays without human intervention.
Approach:	They propose an unsupervised approach to evaluate the quality of input essays . they use multiple heuristic quality signals as pseudo-groundtruths to train a neural AES model .
Outcome:	The proposed approach achieves state-of-the-art performance on eight prompts of ASPA dataset compared with previous unsupervised methods .

Copied to clipboard

Zhiwei He, Xing Wang, Wenxiang Jiao, Zhuosheng Zhang, Rui Wang, Shuming Shi, Zhaopeng Tu

Machine Translation

Challenge:	Existing methods to improve translation quality using human feedback have not been validated.
Approach:	They propose to use quality estimation to predict human preferences for feedback training . they propose to detect incorrect translations and assign a penalty term to the reward scores .
Outcome:	The proposed method outperforms systems using larger parallel corpora by a small amount of monolingual data.

CLEAN–EVAL: Clean Evaluation on Contaminated Large Language Models (2024.findings-naacl)

Copied to clipboard

Wenhong Zhu, Hongkun Hao, Zhiwei He, Yun-Ze Song, Jiao Yueyang, Yumeng Zhang, Hanxu Hu, Yiran Wei, Rui Wang, Hongyuan Lu

Multi-Granularity Semantic Revision for Large Language Model Distillation (2026.acl-long)

Challenge:	Existing methods to evaluate large language models are prone to data contamination.
Approach:	They propose a method which parses contaminated data and back-translates it into a candidate set.
Outcome:	The proposed method reduces data contamination and evaluates the LLMs more cleanly.

Copied to clipboard

Xiaoyu Liu, Yun Zhang, Wei Li, Simiao Li, Xudong Huang, Hanting Chen, Yehui Tang, Jie Hu, Zhiwei Xiong, Yunhe Wang

TeCS: A Dataset and Benchmark for Tense Consistency of Machine Translation (2023.acl-short)

Challenge:	Existing methods for generating large language models rely on student-generated outputs, which introduce generation errors and misguide the distillation process.
Approach:	They propose a multi-granularity semantic revision method for LLM distillation that corrects errors using teacher-generated tokens and re-generates the sequence to minimize errors.
Outcome:	The proposed method reduces errors and misguides distillation on student models and improves consistency between teacher and student outputs.

Copied to clipboard

Yiming Ai, Zhiwei He, Kai Yu, Rui Wang

Machine Translation

Challenge:	tense inconsistency is a common problem in machine translation systems.
Approach:	They propose a parallel tense test set, containing French-English 552 utterances, and introduce a benchmark, tence prediction accuracy.
Outcome:	The proposed model can measure the tense consistency performance of machine translation systems for the first time.

Focusing Condition: Inference-Time Self-Contrastive Steering Elicits Better Conditional Text Embeddings in LLMs (2026.acl-long)

Copied to clipboard

Zifeng Cheng, Lingyun Qian, Zhiwei Jiang, Cong Wang, Yafeng Yin, Fei Shen, Ao Zhou, Qing Gu

GAMIC: Graph-Aligned Molecular In-context Learning for Molecule Analysis via LLMs (2025.findings-emnlp)

Challenge:	Existing methods for extracting conditional text embeddings from large language models (LLMs) relying on prompts often fails to produce high-quality conditional embeddables, resulting in degradation of quality.
Approach:	They propose a plug-and-play method that constructs unconditional general text embeddings and uses them to refine conditional text embeds.
Outcome:	The proposed method improves performance of prompt-based methods on clustering, Semantic Textual Similarity, and triplet alignment datasets.

Copied to clipboard

Ali Al Lawati, Jason S Lucas, Zhiwei Zhang, Prasenjit Mitra, Suhang Wang

DGPO: Beyond Pairwise Preferences with Directional Consistent Groupwise Optimization (2026.findings-acl)

Challenge:	Current methods for retrieving large language models rely on molecule feature similarity, such as Morgan fingerprints, which do not adequately capture the global molecular and atom-binding relationships.
Approach:	They propose a self-supervised learning technique that embeds demonstration examples into the input prompt.
Outcome:	The proposed technique outperforms simple Morgan-based retrieval methods across tasks by up to 45%.

Copied to clipboard

Mengyi Deng, Zhiwei Li, Xin Li, Tingyu Zhu, Yulan Yuan, Zhijiang Guo, Wei Wang

BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps (2020.acl-main)

Challenge:	Existing methods for directional consistency alignment of large language models are limited . a recent study suggests reverse supervision as a complement to forward reasoning .
Approach:	They propose a framework that aggregates supervision signals at the group level and explicitly models direction-aware alignment through multi-candidate comparisons.
Outcome:	The proposed framework achieves 3.2% accuracy improvement across five benchmarks and multiple datasets.

Copied to clipboard

Wang Zhu, Hexiang Hu, Jiacheng Chen, Zhiwei Deng, Vihan Jain, Eugene Ie, Fei Sha

Same Claim, Different Judgment: Benchmarking Scenario-Induced Bias in Multilingual Financial Misinformation Detection (2026.findings-acl)

Challenge:	Existing state-of-the-art VLN agents do not generalize well for long navigation tasks.
Approach:	They propose a VLN agent that is learned to navigate by decomposing long instructions into shorter ones and completing them sequentially.
Outcome:	The proposed agent can follow long instructions better than existing ones, but it does not generalize well.

Copied to clipboard

Zhiwei Liu, Yupeng Cao, Yuechen Jiang, Mohsinul Kabir, Polydoros Giannouris, Chen Xu, Ziyang Xu, Tianlei Zhu, Md. Tariquzzaman, Triantafillos Papadopoulos, Yan Wang, Lingfei Qian, Xueqing Peng, Zhuohan Xie, Ye Yuan, Saeed Almheiri, Abdulrazzaq Alnajjar, Ming-Bin Chen, Harry Stuart, Paul Thompson, Prayag Tiwari, Alejandro Lopez-Lira, Xue Liu, Jimin Huang, Sophia Ananiadou

Image Corruption-Inspired Membership Inference Attacks against Large Vision-Language Models (2026.eacl-long)

Challenge:	Existing research on LLM biases has focused on direct questioning or general-purpose settings . pronounced behavioral biase despite their growing deployment in financial analysis, forecasting, and decision support.
Approach:	They propose a benchmark to evaluate behavioral biases of large language models in MFMD . they use a multilingual financial misinformation dataset to integrate these with misinformation claims .
Outcome:	The proposed benchmark evaluates behavioral biases of large language models across economic scenarios.

Copied to clipboard

Zongyu Wu, Minhua Lin, Zhiwei Zhang, Fali Wang, Xianren Zhang, Xiang Zhang, Suhang Wang

Measuring Bargaining Abilities of LLMs: A Benchmark and A Buyer-Enhancement Method (2024.findings-acl)

Challenge:	Large vision-language models (LVLMs) are trained on large-scale datasets, which can pose privacy risks if training images contain sensitive information.
Approach:	They propose to detect whether a target image is used to train LVLMs by using image-text pairs and single-modality content to detect image-related data.
Outcome:	The proposed methods detect whether a target image is used to train the LVLM on large-scale datasets.

Copied to clipboard

Tian Xia, Zhiwei He, Tong Ren, Yibo Miao, Zhuosheng Zhang, Yang Yang, Rui Wang

Challenge:	Using a novel approach, we can evaluate an agent’s bargaining abilities as an asymmetric incomplete information game.
Approach:	They propose an approach that integrates a deterministic Offer Generator and an LLM Narrator to create natural language sentences for generated offers.
Outcome:	The proposed approach improves the buyer’s deal rates from 26.67% to 88.88% and brings a ten times multiplication of profits on all baselines, even a model that has not been aligned.

DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI (2024.findings-eacl)

Copied to clipboard

Jianguo Zhang, Kun Qian, Zhiwei Liu, Shelby Heinecke, Rui Meng, Ye Liu, Zhou Yu, Huan Wang, Silvio Savarese, Caiming Xiong

Dialogue Systems & Conversational Agents

Challenge:	DialogStudio is the largest and most diverse collection of dialogue datasets . existing datasets lack diversity and comprehensiveness, authors say .
Approach:	They introduce DialogStudio: the largest and most diverse collection of dialogue datasets . DialogStuio aggregates more than 80 diverse dialogue dataset .
Outcome:	a new dataset is created to improve the quality and diversity of dialogue datasets . DialogStudio is the largest and most diverse collection of dialogue data .

History-Aware Hierarchical Transformer for Multi-session Open-domain Dialogue System (2022.findings-emnlp)

Copied to clipboard

Tong Zhang, Yong Liu, Boyang Li, Zhiwei Zeng, Pengwei Wang, Yuan You, Chunyan Miao, Lizhen Cui

Dialogue Systems & Conversational Agents

Challenge:	Existing open-domain dialogue systems conduct one-session conversations, but multi-session MSCs are under-investigated.
Approach:	They propose a History-Aware Hierarchical Transformer for multi-session open-domain dialogue . they propose to encode history conversations into a history memory and leverage historical information to generate well-informed responses.
Outcome:	The proposed model outperforms baseline models on a large-scale MSC dataset.

Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanism (2025.findings-emnlp)

Copied to clipboard

Zhiwei Wang, Yunji Wang, Zhongwang Zhang, Zhangchen Zhou, Hui Jin, Tianyang Hu, Jiacheng Sun, Zhenguo Li, Yaoyu Zhang, Zhi-Qin John Xu

Learn over Past, Evolve for Future: Forecasting Temporal Trends for Fake News Detection (2023.acl-industry)

Challenge:	Large language models struggle with complex reasoning tasks, such as mathematical problem-solving.
Approach:	They constructed a symbolic multi-step reasoning task to investigate the information propagation mechanisms in Transformer models when solving the task through direct answering and Chain-of-Thought (CoT) reasoning.
Outcome:	The proposed algorithm improves on 7 multi-step reasoning datasets, while introducing only 132 trainable parameters.

Copied to clipboard

Beizhe Hu, Qiang Sheng, Juan Cao, Yongchun Zhu, Danding Wang, Zhengjia Wang, Zhiwei Jin

Bridging the Data Gap between Training and Inference for Unsupervised Neural Machine Translation (2022.acl-long)

Challenge:	Existing work on fake news detection does not consider the temporal shift issue caused by the rapidly-evolving nature of news data.
Approach:	They propose a framework to forecast temporal patterns of news data and guide detector to fast adapt to future distributions.
Outcome:	The proposed framework forecasts temporal distribution patterns and guides detector to fast adapt to future distribution.

Copied to clipboard

Zhiwei He, Xing Wang, Rui Wang, Shuming Shi, Zhaopeng Tu

Machine Translation

Challenge:	Experimental results show that backtranslation improves UNMT performance by reducing the data gap between training and inference.
Approach:	They propose an online method to remedy the source discrepancy between training and inference . they use pseudo parallel data with translated source and translated target to mimic inference scenario .
Outcome:	The proposed method outperforms baselines on several widely-used language pairs by remedying the style and content gaps.

DUET: Joint Exploration of User–Item Profiles in Recommendation System (2026.findings-acl)

Copied to clipboard

Yue Chen, Yifei Sun, Lu Wang, Fangkai Yang, Pu Zhao, Minjie Hong, Yifei Dong, Minghua He, Nan Hu, Jianjin Zhang, Zhiwei Dai, Yuefeng Zhan, Weihao Han, Hao Sun, Qingwei Lin, Weiwei Deng, Feng Sun, Qi Zhang, Saravan Rajmohan, Dongmei Zhang

Challenge:	Existing LLMs are opaque and difficult to interpret, resulting in limited interpretability.
Approach:	They propose an interaction-aware profile generator that jointly produces user and item profiles conditioned on both user history and item evidence.
Outcome:	The proposed model outperforms baselines on three real-world datasets.

MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)

Copied to clipboard

Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie

Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering (2025.acl-long)

Challenge:	Existing evaluations of LLMs in finance are text-only, monolingual, and largely saturated by current models.
Approach:	They propose a multilingual and multimodal benchmark for evaluating LLMs in real financial contexts.
Outcome:	The first expert-annotated multilingual and multimodal benchmark is released . it evaluates 21 leading LLMs and shows they perform better in multilingual settings .

Copied to clipboard

Zifeng Cheng, Zhonghui Wang, Yuchen Fu, Zhiwei Jiang, Yafeng Yin, Cong Wang, Qing Gu

LocAgent: Graph-Guided LLM Agents for Code Localization (2025.acl-long)

Challenge:	Existing studies focus on prompt engineering to encode the full semantics of a sentence into the embedding of the last token.
Approach:	They propose a technique that introduces an extra auxiliary prompt to elicit better sentence embedding . they propose to use the hidden state of the token as the sentence embedded in LLMs .
Outcome:	The proposed technique can improve performance of existing prompt-based methods on STS tasks and downstream classification tasks.

Copied to clipboard

Zhaoling Chen, Robert Tang, Gangda Deng, Fang Wu, Jialong Wu, Zhiwei Jiang, Viktor Prasanna, Arman Cohan, Xingyao Wang

LATTE: Learning to Think with Vision Specialists (2025.emnlp-main)

Challenge:	Existing approaches struggle to efficiently navigate complex codebases when identifying relevant code snippets.
Approach:	They propose a graph-guided agent framework that addresses code localization through a distributed graph-based agent.
Outcome:	The proposed framework improves accuracy on real-world benchmarks and can be used to locate code snippets at a cost of 86%.

Copied to clipboard

Zixian Ma, Jianguo Zhang, Zhiwei Liu, Jieyu Zhang, Juntao Tan, Manli Shu, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Caiming Xiong, Ranjay Krishna, Silvio Savarese

GCRC: A New Challenging MRC Dataset from Gaokao Chinese for Explainable Evaluation (2021.findings-acl)

Challenge:	Open-source vision-language models excel on simple question-answering tasks, but struggle with complex questions that require both perception and reasoning.
Approach:	They propose a family of vision-language models that have LeArned to Think wiTh vision spEcialists by offloading perception to state-of-the-art vision models.
Outcome:	The proposed model achieves 4-5% gains over baselines across 6 benchmarks covering both perception and reasoning abilities.

Copied to clipboard

Hongye Tan, Xiaoyue Wang, Yu Ji, Ru Li, Xiaoli Li, Zhiwei Hu, Yunxiao Zhao, Xiaoqi Han

MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models (2025.emnlp-demos)

Challenge:	Existing machine reading comprehension datasets lack an explainable evaluation of systems' reasoning capabilities.
Approach:	They propose a dataset with multi-choice questions that evaluates MRC systems' reasoning process . they use sentence-level relevant supporting facts, error reason of distractors to evaluate MRC .
Outcome:	The proposed dataset is more challenging and useful for identifying limitations of existing MRC systems in an explainable way.

Copied to clipboard

Zhiwei Liu, Jielin Qiu, Shiyu Wang, Jianguo Zhang, Zuxin Liu, Roshan Ram, Haolin Chen, Weiran Yao, Shelby Heinecke, Silvio Savarese, Huan Wang, Caiming Xiong

Challenge:	Existing evaluation frameworks suffer from limitations such as static task benchmarks, limited scope, and inadequate integration with practical applications.
Approach:	They propose an open-source, Model Context Protocol-based evaluation framework specifically tailored for comprehensive and systematic assessment of LLM-powered agents.
Outcome:	The proposed framework uncovers nuanced performance patterns and identify domain-specific strengths and weaknesses, providing valuable insights beyond traditional binary success metrics.

Devil’s Advocate: Anticipatory Reflection for LLM Agents (2024.findings-emnlp)

Copied to clipboard

Haoyu Wang, Tao Li, Zhiwei Deng, Dan Roth, Yang Li

Low-Resource NLP

Challenge:	Introspection-driven approach equips LLM agents with introspection, enhancing consistency and adaptability in solving complex tasks.
Approach:	They propose a zero-shot approach that equips LLM agents with introspection, enhancing consistency and adaptability in solving complex tasks.
Outcome:	The proposed approach improves performance and efficiency by reducing the number of trials and plan revisions by 45%.

LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models (2025.acl-long)

Copied to clipboard

Zhiyuan Hu, Yuliang Liu, Jinman Zhao, Suyuchen Wang, WangYan WangYan, Wei Shen, Qing Gu, Anh Tuan Luu, See-Kiong Ng, Zhiwei Jiang, Bryan Hooi

PCBERT: Parent and Child BERT for Chinese Few-shot NER (2022.coling-1)

Challenge:	Large language models face significant challenges in handling long-context tasks because of their limited effective context window size during pretraining, which restricts their ability to generalize over extended sequences.
Approach:	They propose a training strategy for extending the context window of LLMs including impactful token analysis, position index transformation, and training optimization strategies.
Outcome:	Experiments on three types of LLMs show that LongRecipe can utilize long sequences while requiring only 30% of the target context window size.

Copied to clipboard

Peichao Lai, Feiyang Ye, Lin Zhang, Zhiwei Chen, Yanggeng Fu, Yingjie Wu, Yilei Wang

R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (2024.findings-emnlp)

Challenge:	Existing approaches to improve model performance on few-shot or zero-shot datasets are not effective for Chinese few- shot NER.
Approach:	They propose a prompt-based Parent and Child BERT for Chinese few-shot NER to train an annotating model on high-resource datasets and then discover more implicit labels on low-resourced datasets.
Outcome:	The proposed model can be used on Weibo and other Chinese NER datasets and it is shown to be effective in few-shot learning.

Copied to clipboard

Tongxin Yuan, Zhiwei He, Lingzhong Dong, Yiming Wang, Ruijie Zhao, Tian Xia, Lizhen Xu, Binglin Zhou, Fangqi Li, Zhuosheng Zhang, Rui Wang, Gongshen Liu

Challenge:	Large language models (LLMs) have shown compelling abilities in reasoning, decision-making, and instruction following.
Approach:	They propose a benchmark to evaluate the proficiency of large language models (LLMs) in judging and identifying safety risks given agent interaction records.
Outcome:	The proposed model outperforms the best-performing model, GPT-4o, while no other models significantly exceed the random.

Unsupervised Sign Language Translation and Generation (2024.findings-acl)

Copied to clipboard

Zhengsheng Guo, Zhiwei He, Wenxiang Jiao, Xing Wang, Rui Wang, Kehai Chen, Zhaopeng Tu, Yong Xu, Min Zhang

Multilinguality

Challenge:	Experimental results on the BBC-Oxford Sign Language dataset reveal that USLNet achieves competitive results compared to supervised baseline models.
Approach:	They propose an unsupervised sign language translation and generation network that learns from abundant single-modality data without parallel sign language data.
Outcome:	The proposed model achieves competitive results compared to baseline models on the BBC-Oxford Sign Language dataset and Open-Domain American Sign Language data.

InternLM-Law: An Open-Sourced Chinese Legal Large Language Model (2025.coling-main)

Copied to clipboard

Zhiwei Fei, Songyang Zhang, Xiaoyu Shen, Dawei Zhu, Xiao Wang, Jidong Ge, Vincent Ng

Can Watermarks Survive Translation? On the Cross-lingual Consistency of Text Watermark for Large Language Models (2024.acl-long)

Challenge:	InternLM-Law is a large language model (LLM) tailored for addressing diverse legal tasks related to Chinese laws.
Approach:	They introduce a large language model (LLM) tailored for addressing diverse legal tasks related to Chinese laws.
Outcome:	The proposed model performs better than existing models in a variety of legal tasks related to Chinese laws.

Copied to clipboard

Zhiwei He, Binglin Zhou, Hongkun Hao, Aiwei Liu, Xing Wang, Zhaopeng Tu, Zhuosheng Zhang, Rui Wang

Multilinguality

Challenge:	Existing text watermarking technologies lack consistency when texts are translated into different languages.
Approach:	They propose a cross-lingual watermark removal attack to bypass watermarking by first obtaining a response from an LLM in a pivot language and then translating it into the target language.
Outcome:	The proposed method can remove watermarks without performance loss by obtaining a response from an LLM in a pivot language and then translating it into the target language.

ComRAG: Retrieval-Augmented Generation with Dynamic Vector Stores for Real-time Community Question Answering in Industry (2025.acl-industry)

Copied to clipboard

Qinwen Chen, Wenbiao Tao, Zhiwei Zhu, Mingfan Xi, Liangzhong Guo, Yuan Wang, Wei Wang, Yunshi Lan

Natural Language Interfaces

Challenge:	Existing methods for Community Question Answering (CQA) focus on static knowledge, limiting their applicability to real-world scenarios.
Approach:	They propose a retrieval-augmented generation framework for real-time industrial CQA that integrates static knowledge with dynamic historical QA pairs via a centroid-based memory mechanism.
Outcome:	The proposed framework outperforms baselines on three industrial CQA datasets and achieves 25.9% improvement in vector similarity, reducing latency by 8.7%–23.3%, and lowering chunk growth from 20.23% to 2.06% over iterations.

A Zero-Shot Language Agent for Computer Control with Structured Reflection (2023.findings-emnlp)

Copied to clipboard

Tao Li, Gang Li, Zhiwei Deng, Bryan Wang, Yang Li

Towards Scalable Lightweight GUI Agents via Multi-role Orchestration (2026.findings-acl)

Challenge:	Recent works require a model to learn from trace examples of a task via supervised learning or few/many-shot prompting.
Approach:	They propose a model that iteratively learns from its mistakes via self-reflection and structured thought management.
Outcome:	The proposed model outperforms previous models on easy tasks with more efficient reasoning and self-reflection.

Copied to clipboard

Ziwei Wang, Junjie Zheng, Leyang Yang, Sheng Zhou, Xiaoxuan Tang, Fang Zhouhua, Zhiwei Liu, Dajun Chen, Yong Li, Jiajun Bu

Challenge:	Advanced GUI agents suffer from prohibitive deployment costs on resource-constrained devices.
Approach:	They propose a lightweight GUI agent with GUI-specific knowledge and task scalability . LAMO-3B supports monolithic execution and MAS-style orchestration .
Outcome:	The proposed GUI agent LAMO-3B supports monolithic execution and MAS-style orchestration.

Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate (2024.emnlp-main)

Copied to clipboard

Tian Liang, Zhiwei He, Wenxiang Jiao, Xing Wang, Yan Wang, Rui Wang, Yujiu Yang, Shuming Shi, Zhaopeng Tu

AEA: Adaptive Expert Allocation Improves Sentence Embeddings from Mixture-of-Experts LLM (2026.acl-long)

Challenge:	Modern large language models (LLMs) have shown remarkable performance on general language tasks but struggle on complex reasoning tasks.
Approach:	They propose a multi-agent debate framework that encourages divergent thinking in LLMs . they propose to break debate and use a judge to obtain a final solution .
Outcome:	The proposed framework encourages divergent thinking in large language models . it is able to generate novel thoughts even if initial stance is incorrect .

Copied to clipboard

Shufan Yang, Zifeng Cheng, Zhiwei Jiang, Qingfeng Qi, Yafeng Yin, Cong Wang, Ao Zhou, Qing Gu

xLAM: A Family of Large Action Models to Empower AI Agent Systems (2025.naacl-long)

Challenge:	Existing methods to improve embeddings from Mixture-of-Experts models allocate a fixed number of experts uniformly across all layers and tokens, ignoring inter-layer and inter-token heterogeneity.
Approach:	They propose an Adaptive Expert Allocation framework that performs layer-wise and token-wise expert allocation to enhance embedding quality.
Outcome:	The proposed method improves embedding quality across multiple MoE models.

Copied to clipboard

Jianguo Zhang, Tian Lan, Ming Zhu, Zuxin Liu, Thai Quoc Hoang, Shirley Kokane, Weiran Yao, Juntao Tan, Akshara Prabhakar, Haolin Chen, Zhiwei Liu, Yihao Feng, Tulika Manoj Awalgaonkar, Rithesh R N, Zeyuan Chen, Ran Xu, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong

A Survey on Natural Language Counterfactual Generation (2024.findings-emnlp)

Challenge:	Autonomous agents powered by large language models (LLMs) have attracted significant research interest, but there are few standards for developing specialized models for agent tasks.
Approach:	They propose a series of large action models with dense and mixture-of-expert architectures that unifies, augments, and synthesizes diverse datasets to enhance agent generalizability and performance.
Outcome:	The proposed models outperform GPT-4, Claude-3, and many other models in terms of tool use and outperformed GPT-based models on multiple agent ability benchmarks.

Copied to clipboard

Yongjie Wang, Xiaoqi Qiu, Yu Yue, Xu Guo, Zhiwei Zeng, Yuhong Feng, Zhiqi Shen

Challenge:	Recent advances in NLP are driven by a variety of Large Language Models (LLMs), such as GPT-3 (175B) and PaLM (540B).
Approach:	They propose a taxonomy that categorizes the methods into four groups and summarizes the metrics for evaluating the generation quality.
Outcome:	The proposed taxonomy categorizes the generation methods into four groups and summarizes the metrics for evaluating the quality.

CONSTRUCTURE: Benchmarking CONcept STRUCTUre REasoning for Multimodal Large Language Models (2024.findings-emnlp)

Copied to clipboard

Zhiwei Zha, Xiangru Zhu, Yuanyi Xu, Chenghua Huang, Jingping Liu, Zhixu Li, Xuwu Wang, Yanghua Xiao, Bei Yang, Xiaoxiao Xu

Graph-Assisted Large Language Models: A Perspective on Mitigating Intrinsic Limitations (2026.findings-acl)

Challenge:	Existing multimodal large language models lack the ability to perceive the visual world with a deep concept structure cognition.
Approach:	They propose a concept-level benchmark to assess MLLMs’ hierarchical concept understanding and reasoning abilities.
Outcome:	The proposed model outperforms state-of-the-art models in concept structure reasoning evaluation.

Copied to clipboard

Haitong Luo, Fali Wang, Weiyao Zhang, Xianren Zhang, Zhiwei Zhang, Tianxiang Zhao, Minhua Lin, Jiahao Zhang, Hui Liu, Xianfeng Tang, Qi He, Suhang Wang, Xuying Meng, Yujun Zhang

Structured Data in NLP

Challenge:	Large language models exhibit intrinsic limitations such as knowledge cutoff, single-threaded reasoning that hinders finer-grained branch and aggregation, and rigid collaboration mechanisms that struggle to coordinate specialized capabilities.
Approach:	They propose a taxonomy spanning Graph-Assisted Knowledge Augmentation, Graph Assisted Reasoning and Planning, and Graphed LLM Collaboration.
Outcome:	The proposed models show that graphs can augment and correct LLMs and support dynamic coordination among experts and agents in collaborative settings.

Multi-Prompting Decoder Helps Better Language Understanding (2025.findings-acl)

Copied to clipboard

Zifeng Cheng, Zhaoling Chen, Zhiwei Jiang, Yafeng Yin, Cong Wang, Shiping Ge, Qing Gu