Papers by Tan Zhu

LECO: Improving Early Exiting via Learned Exits and Comparison-based Exiting Mechanism (2023.acl-srw)

Challenge:	Large language models have created significant safety concerns . factuality ability is crucial in determining whether they can be deployed and applied safely and compliantly within specific regions.
Approach:	They propose a benchmark to evaluate the factuality of large language models in China . they evaluate the models' ability to provide accurate and reliable information .
Outcome:	The proposed benchmark evaluates the factuality abilities of existing LLMs and compares them to LLM abilities.

Copied to clipboard

Jingfan Zhang, Ming Tan, Pengyu Dai, Wei Zhu

UAQFact: Evaluating Factual Knowledge Utilization of LLMs on Unanswerable Questions (2025.findings-acl)

Challenge:	Recent work on dynamic early exiting has neglected the intermediate exits’ architectural designs.
Approach:	They propose a framework for learning exits and COmparison-based early exiting to improve PTMs’ early exit performance.
Outcome:	The proposed framework achieves the SOTA performance on multi-exit BERT training and dynamic early exiting on pre-trained models.

Copied to clipboard

Chuanyuan Tan, Wenbiao Shao, Hao Xiong, Tong Zhu, Zhenhua Liu, Kai Shi, Wenliang Chen

Knowledge Representation

Challenge:	Existing datasets to assess LLMs' performance on unanswerable questions lack factual knowledge support.
Approach:	They propose a bilingual unanswerable question dataset with auxiliary factual knowledge created from a Knowledge Graph and two new tasks to measure LLMs' ability to utilize internal and external factual information.
Outcome:	The proposed datasets show that LLMs do not consistently perform well even when they have factual knowledge stored.

Sharing, Teaching and Aligning: Knowledgeable Transfer Learning for Cross-Lingual Machine Reading Comprehension (2023.findings-emnlp)

Copied to clipboard

Tingfeng Cao, Chengyu Wang, Chuanqi Tan, Jun Huang, Jinhui Zhu

Multilinguality

Challenge:	X-STA is a new approach for cross-lingual machine reading comprehension . the variation of answer span positions in different languages makes it difficult to transfer knowledge across languages.
Approach:	They propose a method that leverages an attentive teacher to subtly transfer the answer spans of the source language to the answer output space of the target.
Outcome:	The proposed method outperforms state-of-the-art approaches on three multi-lingual datasets.

USB: A COMPREHENSIVE AND UNIFIED SAFETY EVALUATION BENCHMARK FOR MULTIMODAL LARGE LANGUAGE MODELS (2026.acl-long)

Copied to clipboard

Baolin Zheng, Guanlin Chen, Qingyang Teng, Hongqiong Zhong, Yingshui Tan, Zhendong Liu, Weixun Wang, Jiaheng Liu, Jian Yang, Huiyun Jing, Jincheng Wei, Wenbo Su, Xiaoyong Zhu, Bo Zheng, Kaifu Zhang

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

Challenge:	Existing safety benchmarks fail to provide reliable assessments due to limited risk coverage, insufficient scale and the oversight of complex modality combinations.
Approach:	They propose a framework that covers 61 risk categories across four modality interactions to address this gap.
Outcome:	The proposed framework covers 61 risk categories across four distinct modality interactions.

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.

SDA: Simple Discrete Augmentation for Contrastive Sentence Representation Learning (2024.lrec-main)

Copied to clipboard

Dongsheng Zhu, Zhenyu Mao, Jinghui Lu, Rui Zhao, Fei Tan

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

Challenge:	Existing methods for data augmentation have not been well explored.
Approach:	They propose to use punctuation insertion, modal verbs, and double negation to produce diverse forms of sentences.
Outcome:	The proposed methods perform better on diverse datasets with semantic similarity and standard negation.

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

Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation (P19-3)

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

Zhiting Hu, Haoran Shi, Bowen Tan, Wentao Wang, Zichao Yang, Tiancheng Zhao, Junxian He, Lianhui Qin, Di Wang, Xuezhe Ma, Zhengzhong Liu, Xiaodan Liang, Wanrong Zhu, Devendra Sachan, Eric Xing

Text Generation

Challenge:	Texar is an open-source text generation toolkit that supports a broad set of text generation tasks.
Approach:	They introduce Texar, an open-source text generation toolkit that supports text generation tasks.
Outcome:	Texar supports machine translation, summarization, dialog, content manipulation, and more.

NAG-NER: a Unified Non-Autoregressive Generation Framework for Various NER Tasks (2023.acl-industry)

Copied to clipboard

Xinpeng Zhang, Ming Tan, Jingfan Zhang, Wei Zhu

Information Extraction & Text Mining

Challenge:	Existing models for general NER tasks require entities to be generated in a predefined order, causing error propagation and inefficient decoding.
Approach:	They propose a non-autoregressive generation framework for general NER tasks that generates entities as a set instead of a sequence, avoiding error propagation and inefficient decoding.
Outcome:	The proposed model outperforms state-of-the-art models on three benchmark NER datasets and two of our proprietary NER tasks.

HiddenDetect: Detecting Jailbreak Attacks against Multimodal Large Language Models via Monitoring Hidden States (2025.acl-long)

Copied to clipboard

Yilei Jiang, Xinyan Gao, Tianshuo Peng, Yingshui Tan, Xiaoyong Zhu, Bo Zheng, Xiangyu Yue

See the World, Discover Knowledge: A Chinese Factuality Evaluation for Large Vision Language Models (2025.findings-acl)

Challenge:	Existing studies focus on posthoc alignment techniques, but the underlying safety mechanisms within LVLMs remain unexplored.
Approach:	They propose a tuning-free framework that leverages internal activations to enhance safety.
Outcome:	The proposed framework outperforms state-of-the-art methods in detecting jailbreak attacks against large vision-language models.

Copied to clipboard

Jihao Gu, Yingyao Wang, Pi Bu, Chen Wang, Ziming Wang, Tengtao Song, Donglai Wei, Jiale Yuan, Yingxiu Zhao, Yancheng He, Shilong Li, Jiaheng Liu, Meng Cao, Jun Song, Yingshui Tan, Xiang Li, Wenbo Su, Xiaoyong Zhu, Bo Zheng

Multimodality

Challenge:	Existing models for large vision language models do not fully reflect their knowledge capacity and reliability, resulting in erroneous outputs that do not align with the image content or provide answers lacking knowledge evidence.
Approach:	They propose a Chinese-based benchmark for visual factuality across 8 major topics and 56 subtopics and a multi-hop question construction.
Outcome:	The proposed model decouples visual factuality into two parts: seeing the world and discovering knowledge.

GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models (2025.acl-long)

Copied to clipboard

Kai Yao, Zhaorui Tan, Penglei Gao, Lichun Li, Kaixin Wu, Yinggui Wang, Yuan Zhao, Yixin Ji, Jianke Zhu, Wei Wang

CPsyExam: A Chinese Benchmark for Evaluating Psychology using Examinations (2025.coling-main)

Challenge:	Existing methods for offsite-tuning of large language models require high computational costs and lack theoretical analysis.
Approach:	They propose an offsite-tuning approach that selectively applies compression techniques such as rank compression and channel pruning to preserve the gradients of fine-tuned adapters while ensuring privacy.
Outcome:	The proposed method surpasses existing OT methods in privacy protection and model performance.

Copied to clipboard

Jiahao Zhao, Jingwei Zhu, Minghuan Tan, Min Yang, Renhao Li, Yang Di, Chenhao Zhang, Guancheng Ye, Chengming Li, Xiping Hu, Derek F. Wong

Challenge:	CPsyExam prioritizes psychological knowledge and case analysis separately, recognizing the significance of applying psychological knowledge to real-world scenarios.
Approach:	They propose a psychological benchmark, CPsyExam, constructed from questions from Chinese examination systems.
Outcome:	The proposed benchmark prioritizes psychological knowledge and case analysis separately, recognizing the significance of applying psychological knowledge to real-world scenarios.

FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition (2021.findings-emnlp)

Copied to clipboard

Yichong Leng, Xu Tan, Rui Wang, Linchen Zhu, Jin Xu, Wenjie Liu, Linquan Liu, Xiang-Yang Li, Tao Qin, Edward Lin, Tie-Yan Liu

Multimodality

Challenge:	Error correction is widely used in automatic speech recognition (ASR) to post-process the generated sentence.
Approach:	They propose a fast correction model that takes multiple ASR candidates as input for better correction accuracy.
Outcome:	The proposed model can reduce the word error rate (WER) with multiple candidates by 3.2% and 2.6%.

TranSFormer: Slow-Fast Transformer for Machine Translation (2023.findings-acl)

Copied to clipboard

Bei Li, Yi Jing, Xu Tan, Zhen Xing, Tong Xiao, Jingbo Zhu

CuMA: Aligning LLMs with Sparse Cultural Values via Demographic-Aware Mixture of Adapters (2026.acl-long)

Challenge:	Prior work has focused on treating subwords as basic units in developing such systems.
Approach:	They propose a slow-fast two-stream learning model that uses a “slow” branch to deal with subword sequences and a "fast" branch to cope with longer character sequences.
Outcome:	The proposed model shows consistent BLEU improvements (larger than 1 BLUE point) on several machine translation benchmarks.

Copied to clipboard

Ao Sun, Xiaoyu Wang, Zhe Tan, Yu Li, Zhu Jiachen, Yuheng Jia, Shu Su

Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical Reasoning (2024.findings-acl)

Challenge:	Large Language Models (LLMs) have a global audience, so alignment must extend to cultural resonance.
Approach:	They propose a framework that frames alignment as a conditional capacity separation problem.
Outcome:	The proposed framework outperforms both dense baselines and semantic-only MoEs on three large language models.

Copied to clipboard

Qiming Bao, Alex Peng, Zhenyun Deng, Wanjun Zhong, Gael Gendron, Timothy Pistotti, Neset Tan, Nathan Young, Yang Chen, Yonghua Zhu, Paul Denny, Michael Witbrock, Jiamou Liu

Learning from Diverse Reasoning Paths with Routing and Collaboration (2025.emnlp-main)

Challenge:	Empirical evidence shows that our proposed method improves performance across seven downstream tasks.
Approach:	They propose a logic-driven data augmentation approach that converts text into AMR graphs and converts them back into text to create augmented data.
Outcome:	The proposed method leads on the ReClor leaderboard and improves on seven downstream tasks.

Copied to clipboard

Zhenyu Lei, Zhen Tan, Song Wang, Yaochen Zhu, Zihan Chen, Yushun Dong, Jundong Li

Explanation in the Era of Large Language Models (2024.naacl-tutorials)

Challenge:	Recent studies suggest that the reasoning abilities of large language models (LLMs) grows with model size and pre-training data.
Approach:	They propose to combine quality filtering, conditional routing, and cooperative peer teaching to transfer knowledge from powerful teacher models to compact and transparent students.
Outcome:	Experiments show that QR-Distill is superior to traditional methods.

Copied to clipboard

Zining Zhu, Hanjie Chen, Xi Ye, Qing Lyu, Chenhao Tan, Ana Marasovic, Sarah Wiegreffe

Explainability & Interpretability in NLP

Challenge:	Explanation has long been a part of communication, where humans use language to elucidate each other and transmit information about mechanisms of events.
Approach:	They review the opportunities and challenges of explanations in the era of large language models and examine how they can be used to generate explanations.
Outcome:	The proposed methods are based on the models of large language models (LLMs) and their opaque nature.

CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling (2024.findings-acl)

Copied to clipboard

Chenhao Zhang, Renhao Li, Minghuan Tan, Min Yang, Jingwei Zhu, Di Yang, Jiahao Zhao, Guancheng Ye, Chengming Li, Xiping Hu

Dialogue Systems & Conversational Agents

Challenge:	Existing datasets lack consulting knowledge, resulting in LLMs lacking professional consulting competence.
Approach:	They propose a report-based multi-turn dialogue reconstruction framework for Chinese psychological counseling that uses large language models to assist counseling.
Outcome:	The proposed framework is open-source and can be used in future research.

FaStFact: Faster, Stronger Long-Form Factuality Evaluations in LLMs (2025.findings-emnlp)

Copied to clipboard

Yingjia Wan, Haochen Tan, Xiao Zhu, Xinyu Zhou, Zhiwei Li, Qingsong Lv, Changxuan Sun, Jiaqi Zeng, Yi Xu, Jianqiao Lu, Yinhong Liu, Zhijiang Guo

Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMs (2024.acl-long)

Challenge:	Prior evaluation pipelines fail to evaluate factuality of long-form LLMs due to inefficiency and costly human assessment.
Approach:	They propose a fast and strong evaluation pipeline that can evaluate factuality of long-form LLMs . they propose 'faStFact' to reduce cost of web searching and inference calling .
Outcome:	The proposed evaluation pipeline achieves highest alignment with human evaluation and efficiency among existing baselines.

Copied to clipboard

Jiejun Tan, Zhicheng Dou, Yutao Zhu, Peidong Guo, Kun Fang, Ji-Rong Wen

Information Retrieval

Challenge:	Existing methods to determine the knowledge an LLM already possesses and the knowledge that requires the help of a search engine are expensive and require excessive computational costs.
Approach:	They propose a slim proxy model that detects missing knowledge in LLMs with a proxy model and use it to perform retrieval for the missing knowledge.
Outcome:	The proposed approach detects missing knowledge in LLMs with a slim proxy model and takes its answers as heuristic answers.

Self-Generated Critiques Boost Reward Modeling for Language Models (2025.naacl-long)

Copied to clipboard

Yue Yu, Zhengxing Chen, Aston Zhang, Liang Tan, Chenguang Zhu, Richard Yuanzhe Pang, Yundi Qian, Xuewei Wang, Suchin Gururangan, Chao Zhang, Melanie Kambadur, Dhruv Mahajan, Rui Hou

Learning from LLM Agents: In-Context Generative Models for Text Casing in E-Commerce Ads (2025.emnlp-industry)

Challenge:	Existing reward models produce scalar scores and struggle to incorporate critiques in a natural language format.
Approach:	They propose a framework that predicts critiques and rewards using self-generated critiques without extra supervision.
Outcome:	The proposed framework improves reward modeling accuracy by 3.7%-7.3% compared to standard reward models and LLM judges.

Copied to clipboard

Yingxue Zhou, Tan Zhu, Tao Zeng, Zigeng Wang, Wei Shen

Reasoning

Challenge:	Existing NER-based transformer models are expensive and lack contextual dependencies, making them less reliable when handling unseen or ad-specific terms, e.g., brand names.
Approach:	They propose a two-stage approach to casing correction in e-commerce ad content that leverages Chain-of-Actions to enforce content policies while accurately handling ads-specific terms.
Outcome:	The proposed model outperforms existing NER-based models and achieves near-LLM performance at a fraction of the cost.

DEFT: Distribution-guided Efficient Fine-Tuning for Human Alignment (2024.findings-emnlp)

Copied to clipboard

Liang Zhu, Feiteng Fang, Yuelin Bai, Longze Chen, Zhexiang Zhang, Minghuan Tan, Min Yang

Learning to Refuse: Towards Mitigating Privacy Risks in LLMs (2025.coling-main)

Challenge:	Experimental results show that the methods enhanced by DEFT outperform the original methods in both alignment capability and generalization ability, with significantly reduced training time.
Approach:	They propose a distribution-based alignment framework that integrates data filtering and distributional guidance to improve alignment efficiency and generalization ability.
Outcome:	The proposed framework outperforms existing methods in alignment capability and generalization ability with significantly reduced training time.

Copied to clipboard

Zhenhua Liu, Tong Zhu, Chuanyuan Tan, Wenliang Chen

Learned Adapters Are Better Than Manually Designed Adapters (2023.findings-acl)

Challenge:	Large language models (LLMs) exhibit remarkable capabilities in understanding and generating natural languages, but can inadvertently memorize private information, posing significant privacy risks.
Approach:	They propose to use a dataset to evaluate machine unlearning methods for protecting personal data in a realistic scenario.
Outcome:	The proposed model outperforms baseline methods by 5.65 points and protects target individuals’ personal data while maintaining general capabilities.

Copied to clipboard

Yuming Zhang, Peng Wang, Ming Tan, Wei Zhu

SearchGym: Bootstrapping Real-World Search Agents via Cost-Effective and High-Fidelity Environment Simulation (2026.acl-long)

Challenge:	Existing approaches to improve adapter-based tuning are sub-optimal . a learning framework is proposed to learn the optimal adapter architectures .
Approach:	They propose a framework to automatically learn optimal adapter architectures for better task adaptation of pre-trained models.
Outcome:	The proposed framework outperforms the previous parameter-efficient tuning baselines while tuning comparable or fewer parameters.

Copied to clipboard

Xichen Zhang, Ziyi He, Yinghao Zhu, Sitong Wu, Shaozuo Yu, Meng Chu, Wenhu Zhang, Haoru Tan, Jiaya Jia

Information Retrieval

Challenge:	Search agents are a pivotal paradigm for solving open-ended, knowledge-intensive reasoning tasks.
Approach:	They propose a search agent simulation environment that bootstraps robust search agents using Reinforcement Learning.
Outcome:	The proposed model outperforms the web-enhanced ASearcher model by 10.6%.

SPT: Learning to Selectively Insert Prompts for Better Prompt Tuning (2023.emnlp-main)

Copied to clipboard

Wei Zhu, Ming Tan

An Efficient Conversational Smart Compose System (2023.acl-demo)

Challenge:	Prompt tuning is a method of pre-trained models that optimizes the prompt to adapt to downstream tasks.
Approach:	They propose a framework that learns to select the proper prompt layers by inserting a probabilistic gate at each intermediate layer.
Outcome:	The proposed framework can perform better than the state-of-the-art prompt tuning frameworks on ten benchmark datasets.

Copied to clipboard

Yun Zhu, Xiayu Chen, Lei Shu, Bowen Tan, Xinying Song, Lijuan Liu, Maria Wang, Jindong Chen, Ning Ruan

Dialogue Systems & Conversational Agents

Challenge:	a cloud-based smart compose system is designed to improve human-to-human conversation efficiency.
Approach:	They propose a cloud-based smart compose system to improve conversation efficiency . they propose heuristics to achieve the best trade-off between quality and latency .
Outcome:	The proposed system reduces latency without losing composing quality further.

Recognizing Conflict Opinions in Aspect-level Sentiment Classification with Dual Attention Networks (D19-1)

Copied to clipboard

Xingwei Tan, Yi Cai, Changxi Zhu

Sentiment Analysis

Challenge:	Existing models ignore conflict opinions because they are sparse in the datasets.
Approach:	They propose a multi-label classification model with dual attention mechanism to address these problems by excluding conflict opinions from existing models.
Outcome:	The proposed model addresses the problem of exclusion of conflict opinions from the datasets.

Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring (2026.acl-long)

Copied to clipboard

Dongxu Zhang, Yiding Sun, Cheng Tan, Wenbiao Yan, Ning Yang, Jihua Zhu, Haijun Zhang

Multimodality

Challenge:	Existing efforts to mitigate this via token compression fail due to its autoregressive nature . linguistically redundant tokens are erroneously pruned, leading to hallucinations .
Approach:	They propose a method that reformulates token pruning as a Visual-Anchored Information Bottleneck (VA-IB) optimization problem.
Outcome:	Experiments on Qwen2-VL and Llama-3.2 families show that the proposed model achieves a speedup with negligible accuracy loss.

Knowledge Representation Learning with Contrastive Completion Coding (2021.findings-emnlp)

Copied to clipboard

Bo Ouyang, Wenbing Huang, Runfa Chen, Zhixing Tan, Yang Liu, Maosong Sun, Jihong Zhu

Empowering Diffusion Models on the Embedding Space for Text Generation (2024.naacl-long)

Challenge:	Existing knowledge representation learning methods suffer from immaturity on tackling potentially-imperfect knowledge graphs and highly-imbalanced positive-negative instances during training.
Approach:	They propose a framework for knowledge representation learning that incorporates two functional components to achieve robust embedding for each entity/relation.
Outcome:	The proposed framework achieves better convergence against state-of-the-art methods on several benchmarks.

Copied to clipboard

Zhujin Gao, Junliang Guo, Xu Tan, Yongxin Zhu, Fang Zhang, Jiang Bian, Linli Xu

Representation Learning

Challenge:	Recent work adapts diffusion models to textual data by diffusing on the embedding space.
Approach:	They propose an embedding diffusion model based on Transformer to solve the problem of embeddable space and denoising model.
Outcome:	The proposed model is more efficient than previous methods on seminal text generation tasks and is superior to existing models.

PARA: Parameter-Efficient Fine-tuning with Prompt-Aware Representation Adjustment (2024.emnlp-industry)

Copied to clipboard

Zequan Liu, Yi Zhao, Ming Tan, Wei Zhu, Aaron Tian

MeasHalu: Mitigation of Scientific Measurement Hallucinations for Large Language Models with Enhanced Reasoning (2026.findings-acl)

Challenge:	Existing methods for parameter-efficient fine-tuning excel in the context of single-backbone multi-tenant applications.
Approach:	They propose to integrate a lightweight vector generator within each Transformer layer to improve prompt-aware representation adjustment.
Outcome:	The proposed method surpasses current benchmarks in terms of performance despite having a similar number of adjustable parameters.

Copied to clipboard

Ruijun Huang, Zhiqiao Kang, Yuxuan Zhu, Junxiong Li, Jiahao Zhao, Minghuan Tan, Feng Jiang, Min Yang

RedCoast: A Lightweight Tool to Automate Distributed Training of LLMs on Any GPU/TPUs (2024.naacl-demo)

Challenge:	Large Language Models (LLMs) exhibit severe hallucinations, which undermine reliability of automated scientific document understanding systems.
Approach:	They propose a framework for mitigating scientific measurement hallucinations through enhanced reasoning and targeted optimization.
Outcome:	The proposed framework significantly reduces hallucination rates and improves overall accuracy on the MeasEval benchmark.

Copied to clipboard

Bowen Tan, Yun Zhu, Lijuan Liu, Hongyi Wang, Yonghao Zhuang, Jindong Chen, Eric Xing, Zhiting Hu

Memory Matters More: Event-Centric Memory as a Logic Map for Agent Searching and Reasoning (2026.findings-acl)

Challenge:	Recent advances in machine learning (ML) are attributed to large language models (LLMs), but their escalating memory requirements require developers to partition a large model to distribute it across multiple GPUs or TPUs.
Approach:	They propose a lightweight and user-friendly tool to automate distributed training and inference for LLMs and to simplify ML pipeline development.
Outcome:	The proposed tool automates distributed training and inference for LLMs, and simplifies ML pipeline development.

Copied to clipboard

Yuyang Hu, Jiongnan Liu, Jiejun Tan, Yutao Zhu, Zhicheng Dou

Reasoning

Challenge:	Existing methods for storing and retrieving memory are limited by shallow semantic retrieval.
Approach:	They propose a memory mechanism that organizes and retrieves past experiences to support decision-making.
Outcome:	Experiments on LoCoMo and NarrativeQA show that CompassMem improves retrieval and reasoning performance across multiple backbone models.

HydraRAG: Structured Cross-Source Enhanced Large Language Model Reasoning (2025.emnlp-main)

Copied to clipboard

Xingyu Tan, Xiaoyang Wang, Qing Liu, Xiwei Xu, Xin Yuan, Liming Zhu, Wenjie Zhang

Surprise Calibration for Better In-Context Learning (2025.emnlp-main)

Challenge:	Current RAG system retrieves evidence from knowledge graphs and text documents but has limitations in multi-hop reasoning, multi-entity questions, and source verification.
Approach:	They propose a training-free framework that unifies graph topology, document semantics, and source reliability to support deep, faithful reasoning in large language models.
Outcome:	The proposed framework outperforms the current hybrid model-based model-driven system by 20.3% and 30.1% on seven benchmark datasets.

Copied to clipboard

Zhihang Tan, Jingrui Hou, Ping Wang, Qibiao Hu, Peng Zhu

Taming the Real-world Complexities in CPT E/M Coding with Large Language Models (2025.emnlp-industry)

Challenge:	Existing methods for in-context learning apply fixed class priors across all inputs . existing methods rely on retraining and retrain models .
Approach:	They propose a Bayesian-based method to capture the temporal dynamics of class priors . they identify "surprise" as an informative signal for class prior shift .
Outcome:	The proposed method outperforms existing methods on a range of benchmark tasks.

Copied to clipboard

Islam Nassar, Yang Lin, Yuan Jin, Rongxin Zhu, Chang Wei Tan, Zenan Zhai, Nitika Mathur, Thanh Tien Vu, Xu Zhong, Long Duong, Yuan-Fang Li

What Does LLM Refinement Actually Improve? A Systematic Study on Document-Level Literary Translation (2026.acl-long)

Challenge:	Evaluation and Management (E/M) coding is performed by physicians and trained human coders who review clinical encounter notes and electronic health record data to assign appropriate codes.
Approach:	They propose a framework that automates evaluation and management coding tasks using the Current Procedural Terminology (CPT) taxonomy.
Outcome:	The proposed framework achieves an increase in coding accuracy of more than 36% over a commercial CPT E/M coding system and almost 5% over our strongest single-prompt baseline.

Copied to clipboard

Shaomu Tan, Dawei Zhu, Ke Tran, Michael Denkowski, Sony Trenous, Leonardo F. R. Ribeiro, Bill Byrne, Felix Hieber

Machine Translation

Challenge:	Large language models (LLMs) have made document-level machine translation increasingly practical, enabled by long-context modeling and strong generation quality.
Approach:	They propose to use document-level MT followed by segment-level refinement to find the strongest and most stable improvements across six LLMs and seven language pairs.
Outcome:	The proposed method outperforms error-specific prompting and evaluate-then-refine schemes in document-level translation.

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

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

M2RC-EVAL: Massively Multilingual Repository-level Code Completion Evaluation (2025.acl-long)

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

Jiaheng Liu, Ken Deng, Congnan Liu, Jian Yang, Shukai Liu, He Zhu, Peng Zhao, Linzheng Chai, Yanan Wu, JinKe JinKe, Ge Zhang, Zekun Moore Wang, Guoan Zhang, Yingshui Tan, Bangyu Xiang, Zhaoxiang Zhang, Wenbo Su, Bo Zheng

Programming Languages in NLP

Challenge:	Existing repository-level code completion benchmarks focus on a limited number of languages . existing benchmarks report overall average scores of different languages ignoring fine-grained abilities .
Approach:	They propose to use repository-level code completion benchmarks to evaluate general code intelligence abilities across languages for existing code Large Language Models.
Outcome:	The proposed benchmarks improve the code completion abilities of existing LLMs by using two types of annotations on the parsed syntax tree.

What Makes Pre-trained Language Models Better Zero-shot Learners? (2023.acl-long)

Copied to clipboard

Jinghui Lu, Dongsheng Zhu, Weidong Han, Rui Zhao, Brian Mac Namee, Fei Tan

Probing Language Models for Pre-training Data Detection (2024.acl-long)

Challenge:	Current methods for prompt learning in zero-shot scenarios rely on a development set with sufficient human-annotated data to select the best-performing prompt template.
Approach:	They propose a method for screening reasonable prompt templates in zero-shot text classification using language discrepancy.
Outcome:	The proposed method improves prediction performance in a realistic zero-shot setting, eliminating the need for labelled examples.

Copied to clipboard

Zhenhua Liu, Tong Zhu, Chuanyuan Tan, Bing Liu, Haonan Lu, Wenliang Chen