Papers by Le Wang

ARise: Towards Knowledge-Augmented Reasoning via Risk-Adaptive Search (2025.acl-long)

Challenge:	Existing code sandboxes fail to provide accurate verification and efficiency under high-concurrency workloads.
Approach:	They propose a high-fidelity code verification system that provides sandbox feedback for RL training and evaluation.
Outcome:	The proposed system outperforms heuristic-matching baselines on LiveCodeBench and training stability on high-concurrency workloads.

Copied to clipboard

Yize Zhang, Tianshu Wang, Sirui Chen, Kun Wang, Xingyu Zeng, Hongyu Lin, Xianpei Han, Le Sun, Chaochao Lu

Finding Spoken Identifications: Using GPT-4 Annotation for an Efficient and Fast Dataset Creation Pipeline (2024.lrec-main)

Challenge:	Large language models (LLMs) have impressive capabilities but their application in open-ended, knowledge-intensive, complex reasoning scenarios is limited.
Approach:	They propose a framework that integrates risk assessment of intermediate reasoning states with dynamic retrieval-augmented generation within a Monte Carlo tree search paradigm.
Outcome:	The proposed framework outperforms the state-of-the-art KAR methods by up to 23.10% and the latest RAG-equipped large reasoning models by upto 25.37%.

Copied to clipboard

Maliha Jahan, Helin Wang, Thomas Thebaud, Yinglun Sun, Giang Ha Le, Zsuzsanna Fagyal, Odette Scharenborg, Mark Hasegawa-Johnson, Laureano Moro Velazquez, Najim Dehak

All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAG (2026.acl-long)

Challenge:	Existing datasets that are limited to a few dialects, ethnicities, and age groups are not annotated considering these factors.
Approach:	They propose a semi-automated dataset creation pipeline that leverages large language models to perform two complex annotation tasks using human annotations as ground truths.
Outcome:	The proposed pipeline reduces time required for the filtering and tagging tasks while losing no important information.

Copied to clipboard

Dan Wang, Guozhao Mo, Yafei Shi, Cheng Zhang, Bo Zheng, Boxi Cao, Xuanang Chen, Yaojie Lu, Hongyu Lin, Ben He, Xianpei Han, Le Sun

Multilinguality

Challenge:	Existing mRAG systems suffer from a language bias during reranking, systematically favoring English and the query’s native language.
Approach:	They propose a language-agnostic utility-driven reranker alignment technique to mitigate language bias during re-ranking.
Outcome:	The proposed approach mitigates language bias and consistently improves mRAG performance across languages.

UPTON: Preventing Authorship Leakage from Public Text Release via Data Poisoning (2023.findings-emnlp)

Copied to clipboard

Ziyao Wang, Thai Le, Dongwon Lee

Robustness in NLP

Challenge:	Recent authorship attribution models can reveal the true authorship of unseen texts with high accuracies, with some cases up to 95% accuracy.
Approach:	They propose a solution that weakens authorship features in training samples and makes released texts unlearnable by exploiting black-box data poisoning methods.
Outcome:	The proposed model weakens authorship features in training samples and makes released texts unlearnable.

LAVIS: A One-stop Library for Language-Vision Intelligence (2023.acl-demo)

Copied to clipboard

Dongxu Li, Junnan Li, Hung Le, Guangsen Wang, Silvio Savarese, Steven C.H. Hoi

Multimodality

Challenge:	a new open-source library for language-vision research and applications is available for free.
Approach:	They introduce LAVIS, an open-source deep learning library for LAnguage-VISion research and applications.
Outcome:	The proposed library is open-source and highly extensible and configurable.

Magnet: Multi-turn Tool-use Data Synthesis and Distillation via Graph Translation (2025.acl-long)

Copied to clipboard

Fan Yin, Zifeng Wang, I-Hung Hsu, Jun Yan, Ke Jiang, Yanfei Chen, Jindong Gu, Long Le, Kai-Wei Chang, Chen-Yu Lee, Hamid Palangi, Tomas Pfister

Beyond Surface-Level Pattern Trap: LLM Agents for Faster and Smarter Cross-Architecture Code Migration (2026.findings-acl)

Challenge:	Large language models have been shown to be effective in multi-turn interactions . however, their performance may be limited in complex, multi-turned interactions involving users and multiple tools.
Approach:	They propose a framework for synthesizing high-quality training trajectories to enhance the function calling capability of large language model agents in multi-turn conversations with humans.
Outcome:	The proposed model outperforms the teacher model by 68.01 on BFCL-v3 and 73.30 on ToolQuery.

Copied to clipboard

Weijia Li, KE Gao, Pengfei Chen, Jiajie Li, Xinyu Wang, Yiran Le, Yize Wu, Ling Li

From Local to Global: Revisiting Structured Pruning Paradigms for Large Language Models (2026.acl-long)

Challenge:	cross-architecture code migration is a resource-intensive and errorprone task.
Approach:	a framework for cross-architecture code migration is proposed to decouple implementation details through functional mining and code refactoring.
Outcome:	a new framework improves performance and correctness over state-of-the-art frameworks on OpenCV migration tasks.

Copied to clipboard

Ziyan Wang, Enmao Diao, Qi Le, Pu Wang, Minwoo Lee, Shu-ping Yeh, Evgeny Stupachenko, Hao Feng, Li Yang

DiffLM: Controllable Synthetic Data Generation via Diffusion Language Models (2025.findings-acl)

Challenge:	Structured pruning is a practical approach to deploying large language models (LLMs) but it fails to capitalize on modest task-specific calibration signals, causing limited downstream gains.
Approach:	They propose a method that removes attention heads and MLP channels using loss-based important scores . they use perplexity for language modeling and a margin-based objective for decision-style tasks .
Outcome:	The proposed method lowers perplexity and improves accuracy at higher sparsity . it also stabilizes accuracy and mitigates perxity collapse without fine-tuning .

Copied to clipboard

Ying Zhou, Xinyao Wang, Yulei Niu, Yaojie Shen, Lexin Tang, Fan Chen, Ben He, Le Sun, Longyin Wen

FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation (2024.findings-acl)

Challenge:	Recent advances in large language models (LLMs) have significantly enhanced their knowledge and generative capabilities, leading to a surge of interest in leveraging LLMs for high-quality data synthesis.
Approach:	They propose a controllable data synthesis framework based on variational autoencoder which leverages diffusion models to reserve more information of original distribution and format structure in the learned latent distribution.
Outcome:	The proposed framework generates high-quality data with performance exceeding that of real data by 2%–7% on seven real-world datasets.

Copied to clipboard

Tu Vu, Mohit Iyyer, Xuezhi Wang, Noah Constant, Jerry Wei, Jason Wei, Chris Tar, Yun-Hsuan Sung, Denny Zhou, Quoc Le, Thang Luong

Semantic Text Processing

Challenge:	Modern large language models often "hallucinate" plausible but factually incorrect information, which reduces their trustworthiness especially in settings where accurate and up-to-date information is critical.
Approach:	They develop a human evaluation procedure to measure correctness and hallucination and use it to benchmark both closed and open-source LLMs.
Outcome:	The proposed method outperforms both competing search engine-augmented prompting methods and commercial systems on search-augmented QA.

Reverse Thinking Makes LLMs Stronger Reasoners (2025.naacl-long)

Copied to clipboard

Justin Chen, Zifeng Wang, Hamid Palangi, Rujun Han, Sayna Ebrahimi, Long Le, Vincent Perot, Swaroop Mishra, Mohit Bansal, Chen-Yu Lee, Tomas Pfister

Found in the middle: Calibrating Positional Attention Bias Improves Long Context Utilization (2024.findings-acl)

Challenge:	Reverse-Enhanced Thinking (RevThink) is a framework for large language models to perform reverse thinking.
Approach:	They propose a framework for enhancing forward-backward reasoning by collecting data from a teacher model and employing three objectives to train a student model in a multi-task learning fashion.
Outcome:	The proposed framework outperforms a fine-tuning method trained on 10x more forward reasoning on 12 datasets covering commonsense, math, and logical reasoning.

Copied to clipboard

Cheng-Yu Hsieh, Yung-Sung Chuang, Chun-Liang Li, Zifeng Wang, Long Le, Abhishek Kumar, James Glass, Alexander Ratner, Chen-Yu Lee, Ranjay Krishna, Tomas Pfister

Challenge:	Large language models struggle to capture relevant information located in the middle of their input.
Approach:	They propose a calibration mechanism that allows the model to attend to contexts faithfully according to their relevance even when they are in the middle.
Outcome:	The proposed calibration mechanism mitigates this positional bias and improves retrieval-augmented generation performance.

In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents (2025.acl-long)

Copied to clipboard

Zhen Tan, Jun Yan, I-Hung Hsu, Rujun Han, Zifeng Wang, Long Le, Yiwen Song, Yanfei Chen, Hamid Palangi, George Lee, Anand Rajan Iyer, Tianlong Chen, Huan Liu, Chen-Yu Lee, Tomas Pfister

Natural Language Interfaces

Challenge:	Existing approaches to long-term dialogue memory management fail to capture the natural semantic structure of conversations, leading to fragmented and incomplete representations.
Approach:	They propose a mechanism that integrates forward- and backward-looking reflections into a personalized memory bank for effective future retrieval.
Outcome:	The proposed mechanism outperforms state-of-the-art benchmarks on a long-term dialogue memory model.

DuReadervis: A Chinese Dataset for Open-domain Document Visual Question Answering (2022.findings-acl)

Copied to clipboard

Le Qi, Shangwen Lv, Hongyu Li, Jing Liu, Yu Zhang, Qiaoqiao She, Hua Wu, Haifeng Wang, Ting Liu

Improving Robustness of Language Models from a Geometry-aware Perspective (2022.findings-acl)

Challenge:	Open-domain question answering is a task that requires answering questions based on a collection of document images.
Approach:	They propose to use document images to answer questions using layouts and visual features instead of text.
Outcome:	The proposed approach reduces human cost and improves scalability of QA systems by incorporating layouts and visual features.

Copied to clipboard

Bin Zhu, Zhaoquan Gu, Le Wang, Jinyin Chen, Qi Xuan

Robustness in NLP

Challenge:	Recent studies have found that removing the norm-bounded projection and increasing search steps in adversarial training can significantly improve robustness.
Approach:	They propose friendly adversarial data augmentation and geometry-aware adversarial training to achieve stronger robustness using fewer search steps.
Outcome:	The proposed method can obtain stronger robustness using fewer steps than existing methods.

PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving (2025.emnlp-main)

Copied to clipboard

Mihir Parmar, Xin Liu, Palash Goyal, Yanfei Chen, Long Le, Swaroop Mishra, Hossein Mobahi, Jindong Gu, Zifeng Wang, Hootan Nakhost, Chitta Baral, Chen-Yu Lee, Tomas Pfister, Hamid Palangi

TrendSim: Simulating Trending Topics in Social Media Under Poisoning Attacks with LLM-based Multi-agent System (2025.findings-naacl)

Challenge:	Existing methods for natural planning lack constraint-guided iterative verification and adaptive selection . a recent study found that LLMs are not good at such planning.
Approach:	They propose a model-agnostic and easily scalable agent framework with three key components: constraint, verification, and selection agents.
Outcome:	The proposed framework improves inference-time algorithms on NATURAL PLAN and OlympiadBench benchmarks.

Copied to clipboard

Zeyu Zhang, Jianxun Lian, Chen Ma, Yaning Qu, Ye Luo, Lei Wang, Rui Li, Xu Chen, Yankai Lin, Le Wu, Xing Xie, Ji-Rong Wen

Robustness in NLP

Challenge:	Trending topics bring in a new channel for poisoning attacks, resulting in negative impacts on society.
Approach:	They propose an LLM-based multi-agent system to simulate trending topics in social media . they propose a time-aware interaction mechanism, centralized message dissemination, and an interactive system .
Outcome:	The proposed system simulates trending topics under poisoning attacks on social media platforms.

RouteMoA: Dynamic Routing without Pre-Inference Boosts Efficient Mixture-of-Agents (2026.acl-long)

Copied to clipboard

Jize Wang, Han Wu, Zhiyuan You, Yiming Song, Yijun Wang, Zifei Shan, Yining Li, Songyang Zhang, Xinyi Le, Cailian Chen, Xinping Guan, Dacheng Tao

Green & Sustainable NLP

Challenge:	Existing methods for mixing-of-agents (MoA) lack model selection criteria and struggle with large model pools.
Approach:	They propose a mixture-of-agents framework with dynamic routing that uses a lightweight scorer to perform initial screening and refines the model scores through self- and cross-assessment.
Outcome:	The proposed framework outperforms existing methods for large model pools and tasks . it reduces cost by 89.8% and latency by 63.6% in the large-scale model pool.

NPRF: A Neural Pseudo Relevance Feedback Framework for Ad-hoc Information Retrieval (D18-1)

Copied to clipboard

Canjia Li, Yingfei Sun, Ben He, Le Wang, Kai Hui, Andrew Yates, Le Sun, Jungang Xu

PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning (2026.findings-acl)

Challenge:	Existing neural IR models do not have a mechanism for treating expansion terms differently from the original query terms, making it difficult to combine them with existing PRF approaches.
Approach:	They propose an end-to-end neural PRF framework that can be used with existing neural IR models by embedding different neural models as building blocks.
Outcome:	Extensive experiments on two standard test collections confirm the effectiveness of the proposed framework in improving the performance of two state-of-the-art neural IR models.

Copied to clipboard

Ruixiang Feng, Yuntao Wen, Silin Zhou, Ke Shi, Yifan Wang, Ran Le, Zhenwei An, Zongchao Chen, Chen Yang, Guangyue Peng, Yiming Jia, Dongsheng Wang, Tao Zhang, Lisi Chen, Yang Song, Shen Gao, Shuo Shang

Retentive or Forgetful? Diving into the Knowledge Memorizing Mechanism of Language Models (2024.lrec-main)

Challenge:	Existing LRMs often suffer from "overthinking" and excessively long reasoning traces . a dual-level framework for length compression of LRM is proposed .
Approach:	They propose a framework for prefix-protected and difficulty-aware compression under hierarchical supervision.
Outcome:	The proposed framework reduces token usage while improving accuracy on math benchmarks.

Copied to clipboard

Boxi Cao, Qiaoyu Tang, Hongyu Lin, Shanshan Jiang, Bin Dong, Xianpei Han, Jiawei Chen, Tianshu Wang, Le Sun

Beyond Yes and No: Improving Zero-Shot LLM Rankers via Scoring Fine-Grained Relevance Labels (2024.naacl-short)

Challenge:	Pre-trained language models have shown remarkable memory formation, but vanilla networks without pre-training suffer catastrophic forgetting problem.
Approach:	They conduct experiments to investigate the retentive-forgetful contradiction between vanilla and pre-trained language models by controlling the target knowledge types, learning strategies and learning schedules.
Outcome:	The results show that pre-trained language models are forgetful and pre-training leads to retentive models .

Copied to clipboard

Honglei Zhuang, Zhen Qin, Kai Hui, Junru Wu, Le Yan, Xuanhui Wang, Michael Bendersky

Not All Contexts Are Equal: Teaching LLMs Credibility-aware Generation (2024.emnlp-main)

Challenge:	Existing pointwise LLMs provide noisy or biased answers for documents that are partially relevant to the query.
Approach:	They propose to incorporate fine-grained relevance labels into the LLM prompt . they propose to better differentiate between documents with different levels of relevance .
Outcome:	The proposed model can differentiate between documents with different levels of relevance to the query and derive a more accurate ranking.

Copied to clipboard

Ruotong Pan, Boxi Cao, Hongyu Lin, Xianpei Han, Jia Zheng, Sirui Wang, Xunliang Cai, Le Sun

TermDiffuSum: A Term-guided Diffusion Model for Extractive Summarization of Legal Documents (2025.coling-main)

Challenge:	Existing RAG paradigms suffer from the impact of flawed information introduced during the retrieval phrase, thereby diminishing the reliability and correctness of the generated output.
Approach:	They propose a framework that empowers models to discern and process information based on its credibility.
Outcome:	The proposed framework outperforms existing models with retrieval augmentation and exhibits robustness despite increasing noise in the context.

Copied to clipboard

Xiangyun Dong, Wei Li, Yuquan Le, Zhangyue Jiang, Junxi Zhong, Zhong Wang

Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models (2026.acl-long)

Challenge:	Recent studies have explored diffusion models for extractive summarization task, showcasing their remarkable capabilities.
Approach:	They propose a term-guided diffusion model for extractive summarization of legal documents that incorporates legal terminology into the model via a well-designed multifactor fusion noise weighting schedule.
Outcome:	The proposed model outperforms existing models on a self-constructed legal summarization dataset and achieves improvements of 3.10, 2.84, and 2.89 on three public datasets.

Copied to clipboard

Binghai Wang, Yantao Liu, Yuxuan Liu, Tianyi Tang, Shenzhi Wang, Chang Gao, Chujie Zheng, Yichang Zhang, Le Yu, Shixuan Liu, Tao Gui, Qi Zhang, Xuanjing Huang, Bowen Yu, Fei Huang, Junyang Lin

Beyond Full Fine-tuning: Harnessing the Power of LoRA for Multi-Task Instruction Tuning (2024.lrec-main)

Challenge:	Recent studies observe a phenomenon where reward models achieve high accuracy on static datasets but fail to generalize effectively during RLHF.
Approach:	They propose a method that combines rationale consistency with outcome accuracy to improve performance on RM-Bench and JudgeBench.
Outcome:	The proposed method surpasses baselines on RM-Bench and JudgeBench by an average of 5% and improves creative writing tasks by 7%.

Copied to clipboard

Chunlei Xin, Yaojie Lu, Hongyu Lin, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Zhongyi Liu, Xianpei Han, Le Sun

Contextual Interaction for Argument Post Quality Assessment (2023.emnlp-main)

Challenge:	Low-Rank Adaptation (LoRA) is a parameter-efficient fine-tuning algorithm for large-scale language models.
Approach:	They conduct a systematic study of Low-Rank Adaptation (LoRA) on diverse tasks and rich resources with different learning capacities.
Outcome:	The proposed algorithm can achieve remarkable performance in high-resource and multi-task scenarios, even comparable to full fine-tuning.

Copied to clipboard

Yiran Wang, Xuanang Chen, Ben He, Le Sun

Challenge:	Existing methods for assessing the quality of natural language arguments are limited . existing methods focus on evaluating individual argument posts, but they often fail to distinguish between arguments with a narrow quality gap.
Approach:	They propose to use supervised contrastive learning to model arguments' quality . large language models with in-context examples harness the power of LLMs .
Outcome:	The proposed approach outperforms state-of-the-art models on a publicly available dataset . it shows that the LLMs with in-context examples are more effective than baseline models .

NGQA: A Nutritional Graph Question Answering Benchmark for Personalized Health-aware Nutritional Reasoning (2025.acl-long)

Copied to clipboard

Zheyuan Zhang, Yiyang Li, Nhi Ha Lan Le, Zehong Wang, Tianyi Ma, Vincent Galassi, Keerthiram Murugesan, Nuno Moniz, Werner Geyer, Nitesh V Chawla, Chuxu Zhang, Yanfang Ye

Multimodality

Challenge:	Diet plays a critical role in human health, but tailoring dietary reasoning to individual health conditions remains a challenge.
Approach:	a new benchmark evaluates dietary reasoning using a national health survey data set.
Outcome:	The NGQA benchmark evaluates dietary reasoning across three tasks using a set of question complexity settings and baseline models.

Aligning Retrieval with Reader Needs: Reader-Centered Passage Selection for Open-Domain Question Answering (2025.coling-main)

Copied to clipboard

Chunlei Xin, Shuheng Zhou, Xuanang Chen, Yaojie Lu, Huijia Zhu, Weiqiang Wang, Zhongyi Liu, Xianpei Han, Le Sun

When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models (2026.findings-acl)

Challenge:	Existing retrieval methods aim to gather relevant passages but fail to prioritize consistent and useful information for the reader.
Approach:	They propose a novel method which re-ranks passages based on the reader's prediction probability distribution and clusters passage according to the predicted answers.
Outcome:	The proposed method improves the quality of evidence passages under zero-shot scenarios.

Copied to clipboard

Yingzhi Mao, Chunkang Zhang, Junxiang Wang, Xinyan Guan, Boxi Cao, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun

KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches (2024.findings-emnlp)

Challenge:	Existing methods often apply coarse-grained constraints over entire reasoning trajectories . Existing approaches often apply unsafe constraints, causing unsafe outputs .
Approach:	They propose a trajectory-level training framework that mitigates Self-Jailbreak . they propose 'chain-of-guardrail' to mitigate self-jailbreak by targeting step-level interventions .
Outcome:	The proposed framework mitigates Self-Jailbreak by targeting step-level interventions while maintaining reasoning ability.

Copied to clipboard

Jiayi Yuan, Hongyi Liu, Shaochen Zhong, Yu-Neng Chuang, Songchen Li, Guanchu Wang, Duy Le, Hongye Jin, Vipin Chaudhary, Zhaozhuo Xu, Zirui Liu, Xia Hu

Green & Sustainable NLP

Challenge:	Long context capability is a crucial competency for large language models as it mitigates the human struggle to digest long-form texts.
Approach:	They propose to evaluate 10+ state-of-the-art approaches for long context-capable LLMs.
Outcome:	The proposed methods are compared against 10+ state-of-the-art approaches across seven categories of long context tasks.

REARANK: Reasoning Re-ranking Agent via Reinforcement Learning (2025.emnlp-main)

Copied to clipboard

Le Zhang, Bo Wang, Xipeng Qiu, Siva Reddy, Aishwarya Agrawal

Lightweight Adapter Tuning for Multilingual Speech Translation (2021.acl-short)

Challenge:	REARANK is a large language model-based listwise reasoning reranking agent . it explicitly reasons be- fore reranked results, significantly improving performance and interpretability.
Approach:	They propose a large language model-based listwise reasoning reranking agent that explicitly reasons be- fore reranked lists.
Outcome:	The proposed agent outperforms GPT-4 on reasoning-intensive benchmarks and surpasses GPL-4 on BRIGHT benchmarks.

Copied to clipboard

Hang Le, Juan Pino, Changhan Wang, Jiatao Gu, Didier Schwab, Laurent Besacier

Green & Sustainable NLP

Challenge:	Adapter tuning is an efficient alternative to fine-tuning in NLP . a multilingual model could be outperformed by its bilingual counterparts .
Approach:	They propose to use adapter tuning to optimize for multilingual speech translation . they use pre-trained models to freeze pre-train parameters and inject lightweight modules .
Outcome:	The proposed adapters can specialize to specific language pairs with low extra cost . the proposed models outperform bilingual models on high-resource language pairs .

CaLM: Contrasting Large and Small Language Models to Verify Grounded Generation (2024.findings-acl)

Copied to clipboard

I-Hung Hsu, Zifeng Wang, Long Le, Lesly Miculicich, Nanyun Peng, Chen-Yu Lee, Tomas Pfister

MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora (2025.emnlp-main)

Challenge:	Existing methods to generate grounded responses are prone to errors due to the irrelevancy of input documents.
Approach:	They propose a framework that leverages the insight that a robust grounded response should be consistent with information derived solely from its cited sources.
Outcome:	Experiments on three open-domain question-answering datasets show that the proposed framework improves performance by 1.5% to 7% without any model fine-tuning.

Copied to clipboard

Tuan-Luc Huynh, Thuy-Trang Vu, Weiqing Wang, Trung Le, Dragan Gasevic, Yuan-Fang Li, Thanh-Toan Do

The Linguistic Connectivities Within Large Language Models (2025.findings-acl)

Challenge:	Existing approaches to update model-based indexes with new documents are expensive and require expensive retraining.
Approach:	They propose a framework that combines an expandable mixture of Low-Rank Adaptation experts with a layer-wise out-of-distribution-driven expansion strategy.
Outcome:	Experiments on NQ320k and MS MARCO Passage show that the proposed framework outperforms full-model update baselines with minimal parameter overhead and substantially lower training costs.

Copied to clipboard

Dan Wang, Boxi Cao, Ning Bian, Xuanang Chen, Yaojie Lu, Hongyu Lin, Jia Zheng, Le Sun, Shanshan Jiang, Bin Dong, Xianpei Han

Semantic Text Processing

Challenge:	Recent studies have discovered notable disparities in their performance across different languages.
Approach:	They conduct a systematic investigation into the behaviors of large language models across 27 different languages on 3 different scenarios and reveals a Linguistic Map correlates with the richness of available resources and linguistic family relations.
Outcome:	The proposed model demonstrates that there are significant disparities in performance across languages across 27 different languages on 3 different scenarios.

Consolidating Ranking and Relevance Predictions of Large Language Models through Post-Processing (2024.emnlp-main)

Copied to clipboard

Le Yan, Zhen Qin, Honglei Zhuang, Rolf Jagerman, Xuanhui Wang, Michael Bendersky, Harrie Oosterhuis

Conditional Language Policy: A General Framework For Steerable Multi-Objective Finetuning (2024.findings-emnlp)

Challenge:	Existing approaches to generate relevance labels for large language models have not been successful in generating relevance labels.
Approach:	They propose a method to combine LLM relevance labels with ranking abilities . they take both LLM generated relevance labels and pairwise preferences .
Outcome:	The proposed method balances the ranking and labeling abilities of large language models . it takes both LLM generated relevance labels and pairwise preferences .

Copied to clipboard

Kaiwen Wang, Rahul Kidambi, Ryan Sullivan, Alekh Agarwal, Christoph Dann, Andrea Michi, Marco Gelmi, Yunxuan Li, Raghav Gupta, Kumar Dubey, Alexandre Rame, Johan Ferret, Geoffrey Cideron, Le Hou, Hongkun Yu, Amr Ahmed, Aranyak Mehta, Leonard Hussenot, Olivier Bachem, Edouard Leurent

Multi-step Problem Solving Through a Verifier: An Empirical Analysis on Model-induced Process Supervision (2024.findings-emnlp)

Challenge:	Existing approaches for multi-objective Reinforcement Learning (RL) are difficult due to plurality of preferences and applications.
Approach:	They propose a framework for finetuning language models on multiple objectives using conditional language policy.
Outcome:	The proposed framework outperforms and Pareto-dominates existing approaches for multi-objective Reinforcement Learning (RL) it does not require training or maintaining multiple models to achieve different trade-offs between the objectives.

Copied to clipboard

Zihan Wang, Yunxuan Li, Yuexin Wu, Liangchen Luo, Le Hou, Hongkun Yu, Jingbo Shang

XMC-Agent : Dynamic Navigation over Scalable Hierarchical Index for Incremental Extreme Multi-label Classification (2024.findings-acl)

Challenge:	a method for process supervision has shown significant improvements in multi-step problem solving . despite the advances in process supervision, there are still easily observable mistakes in state-of-the-art LLMs.
Approach:	They propose a method for automating data curation by using a trained verifier to evaluate intermediate steps generated by a reasoner.
Outcome:	The proposed method improves the performance of PaLM 2 on math and coding tasks.

Copied to clipboard

Yanjiang Liu, Tianyun Zhong, Yaojie Lu, Hongyu Lin, Ben He, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Zhongyi Liu, Xianpei Han, Le Sun

Debiasing In-Context Learning by Instructing LLMs How to Follow Demonstrations (2024.findings-acl)

Challenge:	Existing methods for XMC struggle with the growing set of labels due to their static label assumptions, and embedding-based methods struggle with complex mapping relationships due to late interaction paradigm.
Approach:	They propose a large language model (LLM) powered agent framework for extreme multi-label classification, XMC-Agent, which can effectively learn, manage and predict the extremely large and dynamically increasing set of labels.
Outcome:	The proposed framework can learn, manage and predict the extremely large and dynamically growing set of labels and achieves state-of-the-art performance on three standard datasets.

Copied to clipboard

Lvxue Li, Jiaqi Chen, Xinyu Lu, Yaojie Lu, Hongyu Lin, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Zhongyi Liu, Xianpei Han, Le Sun

Match, Compare, or Select? An Investigation of Large Language Models for Entity Matching (2025.coling-main)

Challenge:	In-context learning (ICL) has gained considerable attention due to its data efficiency and task adaptability.
Approach:	They propose to de-biase demonstration bias in in-context learning by focusing on semantic ambiguity induced by demonstrations and reducing the semantic hazard.
Outcome:	The proposed methods significantly improve performance on six datasets.

Copied to clipboard

Tianshu Wang, Xiaoyang Chen, Hongyu Lin, Xuanang Chen, Xianpei Han, Le Sun, Hao Wang, Zhenyu Zeng

Semantic Text Processing

Challenge:	Entity matching (EM) is a critical step in entity resolution (ER).
Approach:	They propose a method that incorporates record interactions from different perspectives.
Outcome:	The proposed framework improves on 8 ER datasets and 10 LLMs and achieves higher efficiency and effectiveness.

The UIR Uncertainty Corpus for Chinese: Annotating Chinese Microblog Corpus for Uncertainty Identification from Social Media (L18-1)

Copied to clipboard

Binyang Li, Jun Xiang, Le Chen, Xu Han, Xiaoyan Yu, Ruifeng Xu, Tengjiao Wang, Kam-fai Wong

Challenge:	Uncertainty identification is an important semantic processing task, critical to the quality of information in terms of factuality in many NLP techniques and applications.
Approach:	They propose to annotate Chinese microblogs with an open uncertainty corpus . they propose to use contextual uncertain semantics rather than traditional cue-phrases to identify uncertainty .
Outcome:	The proposed corpus can be used to identify uncertainty in social media texts.

ChatHF: Collecting Rich Human Feedback from Real-time Conversations (2024.emnlp-demo)

Copied to clipboard

Andrew Li, Zhenduo Wang, Ethan Mendes, Duong Le, Wei Xu, Alan Ritter

Dialogue Systems & Conversational Agents

Challenge:	We present an interactive framework for chatbot evaluation that integrates configurable annotation within a chat interface.
Approach:	They propose an interactive framework for chatbot evaluation that integrates configurable annotation within a chat interface.
Outcome:	The proposed framework supports fine-grained error detection and human evaluation at the same time.

Question Directed Graph Attention Network for Numerical Reasoning over Text (2020.emnlp-main)

Copied to clipboard

Kunlong Chen, Weidi Xu, Xingyi Cheng, Zou Xiaochuan, Yuyu Zhang, Le Song, Taifeng Wang, Yuan Qi, Wei Chu

ScholaWrite: A Dataset of End-to-End Scholarly Writing (2026.acl-long)

Challenge:	Numerical reasoning requires both natural language understanding and arithmetic computation.
Approach:	They propose a graph representation for the context of the passage and question needed for numerical reasoning.
Outcome:	The proposed model achieves remarkable results in benchmark datasets such as DROP.

Copied to clipboard

Khanh Chi Le, Linghe Wang, Minhwa Lee, Ross Volkov, Luan Tuyen Chau, Dongyeop Kang

Challenge:	SCHOLAWRITE traces the multi-month journey from initial drafts to final manuscripts . authors demonstrate the value of capturing scientists’ cognitive writing process .
Approach:	They present a dataset of end-to-end scholarly writing tracing the multi-month journey from initial drafts to final manuscripts.
Outcome:	The first dataset of end-to-end scholarly writing traces the multi-month journey from initial drafts to final manuscripts over four months.

AutoAlign: Get Your LLM Aligned with Minimal Annotations (2025.acl-demo)

Copied to clipboard

Xinyu Lu, Dong Xu, Chunkang Zhang, Xinyan Guan, Junxiang Wang, Qingyu Zhang, Pengbo Wang, Yingzhi Mao, Hao Xiang, Xueru Wen, Zichao Li, Yaojie Lu, Hongyu Lin, Le Sun, Xianpei Han

Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization (2026.acl-long)

Challenge:	Automated Alignment (ALM) is a set of algorithms designed to align Large Language Models (LLMs) with human intentions and values while minimizing manual intervention.
Approach:	They propose an open-source toolkit that integrates mainstream automated algorithms through a consistent interface and an accessible workflow supporting one-click execution for prompt synthesis and automatic alignment signal construction.
Outcome:	The proposed framework enables easy reproduction of existing results through extensive benchmarks and facilitates the development of novel approaches via modular components.

Copied to clipboard

Yifeng Ding, Hung Le, Songyang Han, Kangrui Ruan, Zhenghui Jin, Varun Kumar, Zijian Wang, Anoop Deoras

Rose-SQL: Role-State Evolution Guided Structured Reasoning for Multi-Turn Text-to-SQL (2026.acl-long)

Challenge:	Current reinforcement learning methods suffer from coarse-grained, trajectory-level rewards that provide insufficient learning signals for complex multi-turn interactions, leading to training stagnation.
Approach:	They propose a novel RL algorithm for training large language models for multi-turn tool-integrated reasoning (TIR) that incorporates three innovations: turn-level reward assignment that provides fine-grained feedback for individual turns, return-based advantage estimation where normalized discounted returns are calculated as advantages, and self-supervised reward shaping that exploits self-supervision signals from generated code to densify sparse binary outcome-based rewards.
Outcome:	The proposed algorithm outperforms GRPO by 3.0% across diverse math reasoning benchmarks and improves grepo by 3.9% on commonsense reasoning and program synthesis tasks.

Copied to clipboard

Le Zhou, Feng Yao, Fengcai Qiao, Bo Xu, Fangyuan Wang, Boyan Xu

Programming Languages in NLP

Challenge:	Existing approaches to multi-turn Text-to-SQL tasks rely on unstable APIs or expensive fine-tuning.
Approach:	They propose a training-free framework that leverages small-scale LRMs through in-context learning to enable accurate context-dependent parsing.
Outcome:	The proposed framework outperforms in-context learning baselines at the 4B scale and surpasses state-of-the-art models at the 8B and 14B scales.

Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting (2024.findings-naacl)

Copied to clipboard

Zhen Qin, Rolf Jagerman, Kai Hui, Honglei Zhuang, Junru Wu, Le Yan, Jiaming Shen, Tianqi Liu, Jialu Liu, Donald Metzler, Xuanhui Wang, Michael Bendersky

Large Language Models Can Self-Improve (2023.emnlp-main)

Challenge:	Existing methods to rank documents using large language models do not understand these challenging ranking formulations.
Approach:	They propose to use Pairwise Ranking Prompting to improve ranking performance . they propose to outperform fine-tuned baseline rankers on benchmark datasets .
Outcome:	The proposed technique outperforms supervised baselines on benchmark datasets and outperformed other LLM-based solutions by over 10% on average.

Copied to clipboard

Jiaxin Huang, Shixiang Gu, Le Hou, Yuexin Wu, Xuezhi Wang, Hongkun Yu, Jiawei Han

Low-Resource NLP

Challenge:	Large Language Models (LLMs) have excellent performance in various tasks, but fine-tuning requires extensive supervision.
Approach:	They propose to use a pre-trained Large Language Model to generate rationale-augmented answers for unlabeled questions and fine-tune the LLM using those self-generated solutions as target outputs.
Outcome:	The proposed approach improves the general reasoning ability of a 540B-parameter LLM without any ground truth label.

Exploring Layer Activation Dynamic of CoT via Knowledge Probe (2026.acl-long)

Copied to clipboard

Chuanxin Zhang, Jiajun Liu, Yao He, Wenjun Ke, Peng Wang, Yankun Le, Sirui Liu, Zhaoyu Yang

CodeT5+: Open Code Large Language Models for Code Understanding and Generation (2023.emnlp-main)

Challenge:	Chain-of-thought reasoning has emerged as a crucial paradigm for multi-step reasoning tasks.
Approach:	They propose a multi-stage probing framework that enforces structured reasoning with three explicit stages: keyword extraction, theorem generation, and computation execution.
Outcome:	The proposed framework enforces structured reasoning with three explicit stages: keyword extraction, theorem generation, and computation execution.

Copied to clipboard

Yue Wang, Hung Le, Akhilesh Gotmare, Nghi Bui, Junnan Li, Steven Hoi

Chain-of-Rewrite: Aligning Question and Documents for Open-Domain Question Answering (2024.findings-emnlp)

Challenge:	Existing code LLMs adopt a specific architecture or rely on a unified encoder-decoder network for downstream tasks, lacking flexibility to operate in the optimal architecture for a particular task.
Approach:	They propose to initialize code LLMs with frozen off-the-shelf LLM and explore instruction-tuning to align with natural language instructions.
Outcome:	The proposed model outperforms open-source LLMs on 20 code-related benchmarks.

Copied to clipboard

Chunlei Xin, Yaojie Lu, Hongyu Lin, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Zhongyi Liu, Xianpei Han, Le Sun

Natural Language Interfaces

Challenge:	Existing approaches to answer open-domain question have encountered term mismatch and limited interaction between IR systems and large language models.
Approach:	They propose a method which leverages the guidance and feedback gained from the analysis to provide faithful and consistent extensions for effective question answering.
Outcome:	Experiments on four open-domain question answering datasets show the proposed method performs well under zero-shot settings.

AutoL2S: Auto Long-Short Reasoning for Efficient Large Language Models (2026.findings-acl)

Copied to clipboard

Feng Luo, Yu-Neng Chuang, Guanchu Wang, Hoang Anh Duy Le, Shaochen Zhong, Hongyi Liu, Jiayi Yuan, Yang Sui, Vladimir Braverman, Vipin Chaudhary, Xia Hu

POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion (2025.emnlp-main)

Challenge:	Existing approaches to distilling large language models (LLMs) are inefficient and generate excessively long chain-of-thought reasoning even for inputs that admit concise solutions.
Approach:	They propose a distillation framework that empowers non-reasoning LLMs to think only when necessary.
Outcome:	The proposed framework reduces reasoning length up to 71% with minimal accuracy loss while preserving accuracy.

Copied to clipboard

Yuan Liu, Zhongyin Zhao, Le Tian, Haicheng Wang, Xubing Ye, Yangxiu You, Zilin Yu, Chuhan Wu, Zhou Xiao, Yang Yu, Jie Zhou

BTW: A Non-Parametric Variance Stabilization Framework for Multimodal Model Integration (2025.findings-emnlp)

Challenge:	Existing approaches to training document conversion models with manual annotation are costly and time-consuming, and training student models by distilling outputs from teacher models can significantly limit their performance in real-world applications.
Approach:	They propose a fully automated framework for constructing high-quality document extraction datasets and models capable of handling diverse document formats and layouts.
Outcome:	The proposed model outperforms existing models and improves on annotated documents.

Copied to clipboard

Jun Hou, Le Wang, Xuan Wang

Text Classification

Challenge:	Existing methods for multimodal learning are difficult to scale beyond two modalities and lack resolution for instance-level control.
Approach:	They propose a bi-level weighting framework that combines instance-level Kullback-Leibler divergence and modality-level mutual information to dynamically adjust modality importance during training.
Outcome:	The proposed method significantly improves regression performance and multiclass classification accuracy.

Lock on Target! Precision Unlearning via Directional Control (2025.findings-emnlp)

Copied to clipboard

Yuntao Wen, Ruixiang Feng, Feng Guo, Yifan Wang, Ran Le, Yang Song, Shen Gao, Shuo Shang

Challenge:	Existing methods for unlearning harmful, sensitive, or outdated knowledge suffer from two critical limitations: (1) collateral forgetting, where erasing target data inadvertently removes related but desirable knowledge, and (2) generality forgetting degrades the model’s general capabilities.
Approach:	They propose a method that identifies and leverages a targeted "unlearning direction" in the model's parameter space and selectively updates along this direction.
Outcome:	Experiments show that the proposed method achieves state-of-the-art unlearning precision while preserving both related knowledge and general capabilities.

FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation (2025.acl-long)

Copied to clipboard

Qinggang Zhang, Zhishang Xiang, Yilin Xiao, Le Wang, Junhui Li, Xinrun Wang, Jinsong Su

AID: Adaptive Integration of Detectors for Safe AI with Language Models (2025.naacl-long)

Challenge:	Existing faithful RAG approaches enforce strict context adherence, but they forcibly suppress the model’s parametric knowledge, which undermines the model's internal knowledge structure and increases the risk of misinterpreting the context.
Approach:	They propose a framework that resolves knowledge conflicts by explicitly modeling discrepancies between the model’s parametric knowledge and retrieved context.
Outcome:	The proposed framework outperforms state-of-the-art methods in knowledge conflict cases and identifies conflicting knowledge at the fact level and designs a self-thinking process.

Copied to clipboard

Xinran Wang, Enmao Diao, Qi Le, Jie Ding, Ali Anwar

Beyond Sentence-level Labels: Integrating Conversational Context and Personal Experience for Natural Emotional Expression (2026.findings-acl)

Challenge:	Large language models (LLMs) are increasingly used to generate human-like text, but safety concerns have emerged with the deployment of LLMs.
Approach:	They propose an approach that orchestrates the strengths of multiple pretrained detectors to ensure comprehensive effectiveness in diverse scenarios.
Outcome:	The proposed approach can improve the area under the curve (AUC) by 0.07 to 0.21, with a median of 0.12, compared to the best individual detectors developed for specific safety aspects.

Copied to clipboard

Haiyang Sun, Chenyang Le, Wei Wang, Leying Zhang, Chuang Li, Bing Han, Chenda Li, Mengxiao Bi, Yanmin Qian

Dialogue Systems & Conversational Agents

Challenge:	Existing systems rely on sentence-level labels, which fails to capture the subtle nuances of human affect.
Approach:	They propose to use a large-scale, context-aware speech corpus derived from multi-speaker audiobooks to generate a speech that is human-like.
Outcome:	The proposed model outperforms existing methods in terms of emotional expression accuracy and naturalness.

GlossaGen: Making Academic Translation Smarter with Glossing (2026.findings-acl)

Copied to clipboard

Zixiao Wang, Duzhen Zhang, Juntian Zhang, Yuhan Liu, Guoming Li, Haolun Wu, Le Song, Xiuying Chen

Adaptive Hinge Balance Loss for Document-Level Relation Extraction (2023.findings-emnlp)

Challenge:	Existing machine translation systems obscure or mistranslate key terminology, while paraphrasing aimed at lay readers often oversimplifies it, hindering their ability to master domain-specific technical vocabulary.
Approach:	They propose a task which produces translations dynamically adapted to a reader’s academic proficiency, or level, and a framework to address this challenge.
Outcome:	The proposed framework achieves higher scores than baselines on a synthesized benchmark and human evaluations.

Copied to clipboard

Jize Wang, Xinyi Le, Xiaodi Peng, Cailian Chen

Beyond Profile: From Surface-Level Facts to Deep Persona Simulation in LLMs (2025.findings-acl)

Challenge:	Document-Level Relation Extraction is a multi-label classification task . however, most entity pairs do not express any relations .
Approach:	They propose to use a distance between the classification threshold and predicted score to reduce the imbalance problem by balancing the easy negatives.
Outcome:	The proposed method is superior to other methods, the authors show . it reduces the threshold to an appropriate value, and increases quadratically with the number of entities.

Copied to clipboard

Zixiao Wang, Duzhen Zhang, Ishita Agarwal, Shen Gao, Le Song, Xiuying Chen

Natural Language Interfaces

Challenge:	Existing approaches to persona simulation large language models (LLMs) focus on learning basic biographical information, or using limited role-play dialogue datasets to capture a character’s responses.
Approach:	They propose to train characters using a linguistic structure and a style-tuning mechanism that allows a general linguistic style expert to collaborate with other task-specific experts to better understand their thoughts.
Outcome:	The proposed model outperforms baselines on linguistic accuracy and opinion comprehension on three tasks for Lu Xun's essay collection.

Sparse Latents Steer Retrieval-Augmented Generation (2025.acl-long)

Copied to clipboard

Chunlei Xin, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Xuanang Chen, Xinyan Guan, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun

Can LLMs Clarify? Investigation and Enhancement of Large Language Models on Argument Claim Optimization (2025.coling-main)

Challenge:	In this study, we uncover interpretable latents that govern RAG behavior in large language models . Sparse Autoencoders are used to control large language model (LLM) behavior .
Approach:	They leverage Sparse Autoencoders within the LLaMA Scope to uncover latents that govern RAG behaviors.
Outcome:	The proposed model can be used to control large language models without architectural modifications.

Copied to clipboard

Yiran Wang, Ben He, Xuanang Chen, Le Sun

CodecLM: Aligning Language Models with Tailored Synthetic Data (2024.findings-naacl)

Challenge:	While Large Language Models (LLMs) have demonstrated proficiency in text rewriting tasks such as style transfer and query rewrite, their application to claim optimization remains unexplored.
Approach:	They propose to use a sliding window mechanism to evaluate the performance of large language models in claim clarification tasks under different settings.
Outcome:	The proposed model improves the performance of three LLMs on the claim clarification task under zero-shot, few-shot and supervised fine-tuning settings.

Copied to clipboard

Zifeng Wang, Chun-Liang Li, Vincent Perot, Long Le, Jin Miao, Zizhao Zhang, Chen-Yu Lee, Tomas Pfister