Papers by Qin Zhou

RealTalk-CN: A Realistic Chinese Speech Task-Oriented Dialogue Benchmark with Cross-Modal Analysis (2026.acl-long)

Challenge:	a new metric is developed to pinpoint the moment of invocation when hallucinations arise in small LMs.
Approach:	They propose a metric that measures hallucinations during the generation process of small LMs.
Outcome:	The proposed metric outperforms baselines in hallucination detection across multiple QA datasets.

Copied to clipboard

Enzhi Wang, Jiaming Zhou, Yuhang Jia, Aobo Kong, Qicheng Li, Yong Qin

Recyclable Tuning for Continual Pre-training (2023.findings-acl)

Challenge:	Recent advances in speech large language models have enabled end-to-end spoken interactions, but their robustness in real-world applications remains unclear.
Approach:	They propose a multi-turn, multi-domain speech–text TOD dataset for Chinese users . it contains 5.4k dialogues with annotations for dialogue states, disfluency types, speaker characteristics .
Outcome:	The proposed model can be used to evaluate speech large language models in real-world scenarios . the proposed model is based on 5.4k real human-to-human dialogues with annotations .

Copied to clipboard

Yujia Qin, Cheng Qian, Xu Han, Yankai Lin, Huadong Wang, Ruobing Xie, Zhiyuan Liu, Maosong Sun, Jie Zhou

Enhancing Reinforcement Learning for Radiology Report Generation with Evidence-aware Rewards and Self-correcting Preference Learning (2026.acl-long)

Challenge:	Continual pre-training is the paradigm where pre-trained language models acquire fresh knowledge and gradually get upgraded.
Approach:	They propose to use adapted weights to recycle old PLMs for continual pre-training . they propose to combine initialization and distillation methods to achieve better performance .
Outcome:	The proposed method improves the convergence and performance of the upgraded PLM.

Copied to clipboard

Qin Zhou, Guoyan Liang, Qianyi Yang, Jingyuan Chen, Sai Wu, Chang Yao, Zhe Wang

Text Generation

Challenge:	Recent reinforcement learning approaches have advanced radiology report generation (RRG) however, there are two limitations: report-level rewards offer limited evidence-grounded guidance for clinical faithfulness .
Approach:	They propose a method that uses group-wise evidence-aware alignment rewards and self-correcting preference learning to build a reliable, disease-agnostic preference dataset without human supervision.
Outcome:	ESC-RL promotes clinically faithful, disease-aligned reward and supports continual self-improvement during training.

A Regularization-based Transfer Learning Method for Information Extraction via Instructed Graph Decoder (2024.lrec-main)

Copied to clipboard

Kedi Chen, Jie Zhou, Qin Chen, Shunyu Liu, Liang He

Boosting Large Language Models with Continual Learning for Aspect-based Sentiment Analysis (2024.findings-emnlp)

Challenge:	Existing methods for information extraction (IE) focus on training task-specific models, while common knowledge among different IE tasks is not explicitly modeled.
Approach:	They propose a regularization-based transfer learning method for IE via an instructed graph decoder which decodes various complex structures into a graph uniformly based on corresponding instructions.
Outcome:	The proposed method can learn common knowledge from existing datasets and transfer it to a new dataset with new labels.

Copied to clipboard

Xuanwen Ding, Jie Zhou, Liang Dou, Qin Chen, Yuanbin Wu, Arlene Chen, Liang He

Sentiment Analysis

Challenge:	Existing studies focus on improving the performance of domain-specific models based on the target dataset.
Approach:	They propose a Large Language Model-based Continual Learning (LLM-CL) model for ABSA that learns the target domain’s ability while maintaining the history domains’ abilities.
Outcome:	The proposed model obtains new state-of-the-art over 19 datasets.

ChatMap: Mining Human Thought Processes for Customer Service Chatbots via Multi-Agent Collaboration (2025.findings-acl)

Copied to clipboard

Xinyi Jiang, Tianyi Hu, Yuheng Qin, Guoming Wang, Zhou Huan, Kehan Chen, Gang Huang, Rongxing Lu, Siliang Tang

MentalSeek-Dx: Towards Progressive Hypothetico-Deductive Reasoning for Real-world Psychiatric Diagnosis (2026.acl-long)

Challenge:	Existing methods for enhancing dialogue performance rely on summarizing behavior . e-commerce chatbots need to align their dialogue strategies with human behavior to achieve coherent, human-like conversations with customers.
Approach:	They propose a method to extract core patterns from dialogue data and integrate them into models by mining service thought processes using a multi-agent aPproach.
Outcome:	The proposed method outperforms manual methods and outperfies baselines on Taobao in China.

Copied to clipboard

Xiao Sun, null Ymyang, Xinyi Jiang, Yu Tian, Junnan Zhu, Jiang Zhong, Qin Lei, Jingwang Huang, Haoyang Zeng, Xinyu Zhou, Xin Xiao, Kaiwen Wei

SimulSpeech: End-to-End Simultaneous Speech to Text Translation (2020.acl-main)

Challenge:	Mental health disorders represent a burgeoning global public health challenge . lack of ecological validity and fine-grained diagnostic supervision limits their utility .
Approach:	They propose a medical-specialized LLM trained to internalize clinical reasoning process through supervised trajectory construction and curriculum-based reinforcement learning.
Outcome:	The proposed model achieves state-of-the-art with only 14B parameters, establishing a clinically grounded framework for reliable psychiatric diagnosis.

Copied to clipboard

Yi Ren, Jinglin Liu, Xu Tan, Chen Zhang, Tao Qin, Zhou Zhao, Tie-Yan Liu

Text Generation

Challenge:	SimulSpeech is an end-to-end simultaneous speech to text translation system . conventional approaches to simultaneous speech translation divide the translation process into two stages .
Approach:	They develop an end-to-end simultaneous speech to text translation system which translates speech in source language to text in target language concurrently.
Outcome:	The proposed system achieves reasonable BLEU scores and lower delay compared to full-sentence translation model.

Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answering (2025.acl-long)

Copied to clipboard

Linhao Ye, Lang Yu, Zhikai Lei, Qin Chen, Jie Zhou, Liang He

Information Retrieval

Challenge:	Existing retrieval-augmented generation methods are insufficient for multi-hop question answering . however, they tend to generate hallucinations due to semantic mismatching .
Approach:	They propose to optimize question semantic space for dynamic retrieval-augmented multi-hop question answering by optimizing the semantic embeddings.
Outcome:	The proposed method outperforms existing RAG methods in both in- and out-of-domain settings.

Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation (2025.findings-emnlp)

Copied to clipboard

Dongwon Jung, Qin Liu, Tenghao Huang, Ben Zhou, Muhao Chen

Information Retrieval

Challenge:	Retrieval-augmented generation (RAG) improves large language models by incorporating non-parametric knowledge through evidence retrieved from external sources.
Approach:	They propose a training-free evidence compression technique that makes retrieved evidence more familiar to the target model while seamlessly integrating parametric knowledge from the model.
Outcome:	The proposed technique outperforms the most recent evidence compression baselines across open-domain QA datasets while achieving high compression rates.

Exploring Mode Connectivity for Pre-trained Language Models (2022.emnlp-main)

Copied to clipboard

Yujia Qin, Cheng Qian, Jing Yi, Weize Chen, Yankai Lin, Xu Han, Zhiyuan Liu, Maosong Sun, Jie Zhou

Knowledge Inheritance for Pre-trained Language Models (2022.naacl-main)

Challenge:	Recent years have witnessed the prevalent application of pre-trained language models (PLMs) in NLP. From the perspective of parameter space, PLMs provide generic initialization, starting from which high-performance minima could be found.
Approach:	They investigate the geometric connections of different minima through the lens of mode connectivity, which measures whether two minima can be connected with a low-loss path.
Outcome:	The proposed model can be used to find low-loss paths between two minima, and to understand how their mode connectivity affects their task knowledge.

Copied to clipboard

Yujia Qin, Yankai Lin, Jing Yi, Jiajie Zhang, Xu Han, Zhengyan Zhang, Yusheng Su, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

Revisiting Over-Smoothness in Text to Speech (2022.acl-long)

Challenge:	Existing large-scale pre-trained language models are mainly trained from scratch individually, ignoring that many well-taught PLMs are available.
Approach:	They propose a pre-training framework called knowledge inheritance and propose auxiliary supervision to efficiently learn larger PLMs.
Outcome:	The proposed framework can be used to train large-scale language models with huge parameters and a large dataset can be adapted to domain adaptation and knowledge transfer.

Copied to clipboard

Yi Ren, Xu Tan, Tao Qin, Zhou Zhao, Tie-Yan Liu

C-World: A Computer Use Agent Environment Creator (2026.acl-long)

Challenge:	Non-autoregressive text to speech models ignore correlation in time and frequency domains, causing blurry results.
Approach:	They revisit the problem of over-smoothness in non-autoregressive text to speech models . they use methods that reduce complexity of data distributions and improve modeling methods .
Outcome:	The proposed models achieve better voice quality and faster inference speed than autoregressive models.

Copied to clipboard

Ziqiao Xi, Shuang Liang, Qi Liu, Jiaqing Zhang, Letian Peng, Fang Nan, Meshal Nayim, Tianhui Zhang, Rishika Mundada, Lianhui Qin, Biwei Huang, Kun Zhou

Challenge:	C-World enables users to build agent environments on demand.
Approach:	They propose a system that enables users to build agent environments on demand.
Outcome:	The proposed system outperforms baselines on 119k samples and achieves Spearman = 0.883 ranking correlation with real execution.

Breaking Language Barriers: Cross-Lingual Continual Pre-Training at Scale (2024.emnlp-main)

Copied to clipboard

Wenzhen Zheng, Wenbo Pan, Xu Xu, Libo Qin, Li Yue, Ming Zhou

Don’t Say No: Jailbreaking LLM by Suppressing Refusal (2025.findings-acl)

Challenge:	Large Language Models (LLMs) have made significant strides towards Artificial General Intelligence, but training them from scratch is prohibitively expensive.
Approach:	They propose to continuously pre-train LLMs from existing pre-trained LLM models by using a set of parameters instead of randomly initializing them.
Outcome:	The proposed approach saves significant resources and accelerates convergence and performance.

Copied to clipboard

Yukai Zhou, Jian Lou, Zhijie Huang, Zhan Qin, Sibei Yang, Wenjie Wang

Robustness in NLP

Challenge:	Large Language Models (LLMs) are vulnerable to "jailbreaking" attacks where crafted prompts manipulate them into producing toxic content.
Approach:	They propose to improve the target loss objective by combining a cosine decay schedule method with refusal suppression to achieve higher success rates.
Outcome:	The proposed approach outperforms baseline attacks and achieves state-of-the-art attack success rates.

ProQA: Structural Prompt-based Pre-training for Unified Question Answering (2022.naacl-main)

Copied to clipboard

Wanjun Zhong, Yifan Gao, Ning Ding, Yujia Qin, Zhiyuan Liu, Ming Zhou, Jiahai Wang, Jian Yin, Nan Duan

RedCoder: Automated Multi-Turn Red Teaming for Code LLMs (2026.acl-long)

Challenge:	Existing QA research on question answering is focused on specific question types, knowledge domains, or reasoning skills.
Approach:	They propose a unified QA paradigm that solves various tasks through a single model.
Outcome:	The proposed model improves QA-centric ability on 11 QA benchmarks.

Copied to clipboard

Wenjie Jacky Mo, Qin Liu, Xiaofei Wen, Dongwon Jung, Hadi Askari, Wenxuan Zhou, Zhe Zhao, Muhao Chen

Programming Languages in NLP

Challenge:	Existing red-teaming approaches for code generation rely on extensive human effort and are prone to generating malicious code under adversarial environments.
Approach:	They propose a red-teaming agent that engages victim models in multi-turn conversations to elicit vulnerable code.
Outcome:	Experiments show that RedCoder outperforms red-teaming methods in inducing vulnerabilities in code generation.

Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents (2024.acl-long)

Copied to clipboard

Cheng Qian, Bingxiang He, Zhong Zhuang, Jia Deng, Yujia Qin, Xin Cong, Zhong Zhang, Jie Zhou, Yankai Lin, Zhiyuan Liu, Maosong Sun

DB-LLM: Accurate Dual-Binarization for Efficient LLMs (2024.findings-acl)

Challenge:	Current language model-driven agents lack mechanisms for effective user participation, which is crucial given the vagueness commonly found in user instructions.
Approach:	They propose a benchmark to inspect users’ implicit intentions through explicit queries and a model expert as the upstream in agent design to enhance user-agent interaction.
Outcome:	The proposed approach excels at identifying vague user tasks, recovering and summarizing critical missing information, setting precise and necessary agent execution goals, and minimizing redundant tool usage, thus boosting overall efficiency.

Copied to clipboard

Hong Chen, Chengtao Lv, Liang Ding, Haotong Qin, Xiabin Zhou, Yifu Ding, Xuebo Liu, Min Zhang, Jinyang Guo, Xianglong Liu, Dacheng Tao

Green & Sustainable NLP

Challenge:	Existing methods for ultra-low bit quantization cause severe accuracy drops . a novel Dual-Binarization method is proposed for efficient Large Language Models .
Approach:	They propose a Dual-Binarization method that takes 2-bit-width and binarization into account . they propose DB-LLM, which uses a 2-bit binarized weighted model to represent weights efficiently .
Outcome:	The proposed method surpasses the current State-of-the-Art in ultra-low bit quantization and achieves 20% reduction in computational consumption compared to the SOTA method under the same bit-width.

TLSA: LLM-Guided Text-Label Space Alignment with Contrastive Learning for Generalized Category Discovery (2026.acl-long)

Copied to clipboard

Wenxi Xu, Chuan Qin, Xi Chen, Chuyu Fang, Yuanchun Zhou, Hengshu Zhu

A Multi-Format Transfer Learning Model for Event Argument Extraction via Variational Information Bottleneck (2022.coling-1)

Challenge:	Existing methods for generalized category discovery suffer from weak text–label alignment, inconsistent objectives across known and novel categories, and poor discrimination of semantically similar clusters.
Approach:	They propose a unified framework that enforces contrastive alignment between text and label representations within a shared semantic space.
Outcome:	The proposed framework outperforms state-of-the-art methods on four benchmark datasets.

Copied to clipboard

Jie Zhou, Qi Zhang, Qin Chen, Qi Zhang, Liang He, Xuanjing Huang

mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding (2024.findings-emnlp)

Challenge:	Event argument extraction (EAE) aims to extract arguments with given roles from texts.
Approach:	They propose a multi-format transfer learning model with variational information bottleneck to learn from existing datasets.
Outcome:	The proposed model improves on three benchmark datasets and obtains state-of-the-art performance on EAE.

Copied to clipboard

Anwen Hu, Haiyang Xu, Jiabo Ye, Ming Yan, Liang Zhang, Bo Zhang, Ji Zhang, Qin Jin, Fei Huang, Jingren Zhou

Learning Auxiliary Tasks Improves Reference-Free Hallucination Detection in Open-Domain Long-Form Generation (2025.acl-short)

Challenge:	Existing Multimodal Large Language Models lack general structure understanding abilities for text-rich document images.
Approach:	They propose to use unified structure learning to boost the performance of MLLMs by encoding structure information into text-rich images.
Outcome:	The proposed model achieves state-of-the-art on 10 visual document understanding benchmarks.

Copied to clipboard

Chengwei Qin, Wenxuan Zhou, Karthik Abinav Sankararaman, Nanshu Wang, Tengyu Xu, Alexander Radovic, Eryk Helenowski, Arya Talebzadeh, Aditya Tayade, Sinong Wang, Shafiq Joty, Han Fang, Hao Ma

mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding (2025.acl-long)

Challenge:	Existing methods for detecting hallucination in long-form tasks focus on limited domains or rely heavily on external fact-checking tools, which may not always be available.
Approach:	They propose a new paradigm that augments fine-tuning with an auxiliary task for the model to jointly learn with the main task of hallucination detection.
Outcome:	The proposed method outperforms existing methods for detecting hallucination in open-domain long-form generation and is more accurate than random guessing.

Copied to clipboard

Anwen Hu, Haiyang Xu, Liang Zhang, Jiabo Ye, Ming Yan, Ji Zhang, Qin Jin, Fei Huang, Jingren Zhou

Visual Data in NLP

Challenge:	Multimodal Large Language Models (MLLMs) have improved document understanding performance but generate thousands of visual tokens for a single document image, leading to excessive GPU memory and slower inference times.
Approach:	They propose a high-resolution document compression module to generate 324 tokens for a single document image.
Outcome:	The proposed module reduces first token latency by more than 50% and improves document comprehension performance.

ChildMandarin: A Comprehensive Mandarin Speech Dataset for Young Children Aged 3-5 (2025.acl-long)

Copied to clipboard

Jiaming Zhou, Shiyao Wang, Shiwan Zhao, Jiabei He, Haoqin Sun, Hui Wang, Cheng Liu, Aobo Kong, Yujie Guo, Xi Yang, Yequan Wang, Yonghua Lin, Yong Qin

Domain Generalization via Causal Adjustment for Cross-Domain Sentiment Analysis (2024.lrec-main)

Challenge:	Automatic speech recognition systems have advanced significantly with models like Whisper, Conformer, and self-supervised frameworks such as Wav2vec 2.0.
Approach:	They propose to use Mandarin speech datasets to analyze pronunciation and tone of children aged 3 to 5 and evaluate their models on speaker verification (SV) They find that the datasets are more robust than those used by adult speech recognition systems and are open-source and available for all academic purposes.
Outcome:	The proposed dataset includes 41.25 hours of speech with carefully crafted manual transcriptions, collected from 397 speakers across various provinces in China, with balanced gender representation.

Copied to clipboard

Siyin Wang, Jie Zhou, Qin Chen, Qi Zhang, Tao Gui, Xuanjing Huang

Sentiment Analysis

Challenge:	Existing approaches to domain adaptation fail to generalize well on unknown test data.
Approach:	They propose a backdoor adjustment-based causal model to disentangle domain-specific and domain-invariant representations that play essential roles in tackling domain shift.
Outcome:	The proposed model disentangles domain-specific and domain-invariant representations that play essential roles in tackling domain shift.

DiaHalu: A Dialogue-level Hallucination Evaluation Benchmark for Large Language Models (2024.findings-emnlp)

Copied to clipboard

Kedi Chen, Qin Chen, Jie Zhou, He Yishen, Liang He

Sparse Black-Box Multimodal Attack for Vision-Language Adversary Generation (2023.findings-emnlp)

Challenge:	Existing benchmarks for hallucination detection are intentionally generated by large language models (LLMs) however, many focus on factuality while ignoring faithfulness.
Approach:	They propose a dialogue-level hallucination evaluation benchmark for large language models . they integrate the topic into prompts and facilitate a dialog between two LLMs .
Outcome:	The proposed benchmark covers four common multi-turn dialogue domains and five hallucination subtypes, extended from factuality and faithfulness hallucines.

Copied to clipboard

Zhen Yu, Zhou Qin, Zhenhua Chen, Meihui Lian, Haojun Fu, Weigao Wen, Hui Xue, Kun He

Let’s Rectify Step by Step: Improving Aspect-based Sentiment Analysis with Diffusion Models (2024.lrec-main)

Challenge:	Existing adversarial attacks using imperceptible perturbations are challenging to simulate . e-commerce product restrictions and hate speech monitoring are examples of such attacks .
Approach:	They propose a black-box adversarial attack that leverages sparse perturbations to simulate adversarials exhibited by illegal merchants in the black- box scenario.
Outcome:	The proposed method outperforms existing attacks and unimodal attacks by treating images and text in discrete space and outperforming existing models.

Copied to clipboard

Shunyu Liu, Jie Zhou, Qunxi Zhu, Qin Chen, Qingchun Bai, Jun Xiao, Liang He

Sentiment Analysis

Challenge:	Empirical evaluations conducted on eight benchmark datasets underscore the compelling advantages offered by DiffusionABSA when compared against robust baseline models.
Approach:	They propose a diffusion model which extracts aspects step by step and learns a denoising process that progressively restores them in a reverse manner.
Outcome:	Empirical evaluations on eight benchmark datasets underscore the compelling advantages offered by DiffusionABSA when compared against robust baseline models.

From Implicit Graph Encoding to Explicit Evidence: A Training-Free LLM Framework for Temporal Knowledge Graph Reasoning (2026.findings-acl)

Copied to clipboard

Guo Tang, Ke Cheng, Huiming Fan, Heng Chang, Wenxiang Zheng, Xianhao Ou, Junjia Xiang, Ming Liu, Yujun Zhou, Li Lanyu, Bing Qin

From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systems (2025.findings-emnlp)

Challenge:	Existing Large Language Models (LLMs) struggle with implicit modality alignment and suboptimal graph linearization.
Approach:	They propose a training-free, test-time adaptive framework that reframes TKG prediction as explicit evidence-driven reasoning.
Outcome:	ExE-LLM outperforms fully trained graph neural networks on four benchmarks . it achieves SOTA performance in inductive settings, significantly outperforming fully trained neural networks .

Copied to clipboard

Zekun Zhou, Xiaocheng Feng, Lei Huang, Xiachong Feng, Ziyun Song, Ruihan Chen, Liang Zhao, Weitao Ma, Yuxuan Gu, Baoxin Wang, Dayong Wu, Guoping Hu, Ting Liu, Bing Qin

MetaScale: Test-Time Scaling with Evolving Meta-Thoughts (2026.findings-acl)

Challenge:	rapid development of artificial intelligence (AI) technologies has inspired researchers to explore how AI can accelerate and enhance research.
Approach:	They organize the relevant studies into three main categories: hypothesis formulation, hypothesis validation, and manuscript publication.
Outcome:	The authors summarize the current state of research in three main areas: hypothesis formulation, hypothesis validation, and manuscript publication.

Copied to clipboard

Qin Liu, Wenxuan Zhou, Nan Xu, James Y. Huang, Fei Wang, Sheng Zhang, Hoifung Poon, Muhao Chen

DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding (2026.findings-acl)

Challenge:	Existing approaches impose fixed cognitive structures that enhance performance in specific tasks but lack adaptability across diverse scenarios.
Approach:	They propose a test-time scaling framework based on meta-thoughts to improve performance . meta-thinkts are adaptive thinking strategies tailored to a given task .
Outcome:	Experimental results show that MetaScale outperforms standard inference approaches . it can scale more effectively with increasing sampling budgets and produces more structured responses .

Copied to clipboard

Jiaming Zhou, Xuxin Cheng, Shiwan Zhao, Yuhang Jia, Cao Liu, Ke Zeng, Xunliang Cai, Yong Qin

RSA-Bench: Benchmarking Audio Large Models in Real-World Acoustic Scenarios (2026.findings-acl)

Challenge:	Autoregressive (AR) large audio language models are expensive in data and computation . prior work shows diffusion-based LALMs can improve audio understanding under matched settings .
Approach:	They propose a diffusion-based LALM that upgrades the speech encoder and employs dual semantic and acoustic adapters.
Outcome:	a new model improves over existing autoregressive large language models and is competitive to strong AR models . the proposed model can make use of limited training data and improve inference efficiency . a recent study shows that diffusion-based models can improve audio understanding .

Copied to clipboard

Yibo Zhang, Kaiwen Luo, Liang Lin, Shilinlu Yan, Jin Wang, Yaoqi Guo, Yitian Chen, Yalan Qin, Zhenhong Zhou, Kun Wang, Li Sun

AudioPrivacy: Parallel Audio Dataset for Speaker Profiling with Diverse Audio Types and Rich Attributes (2026.findings-acl)

Challenge:	Existing evaluations rely on synthetic Gaussian noise or simplistic single-source interference, failing to capture the intricate, multi-layered acoustic dynamics that characterize authentic physical environments.
Approach:	They propose a robustness benchmark to stress-test Audio Large Models (ALLMs) using high-fidelity auditory scene simulations.
Outcome:	The proposed model performs well on a wide range of tasks, including automatic speech recognition, speech translation, and audio-based reasoning.

Copied to clipboard

Jiabei He, Yanzhe Zhang, Jiaming Zhou, Hui Wang, Haoqin Sun, Yong Qin

Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring (2025.naacl-long)

Challenge:	Speech signals convey abundant speaker-related metadata, yet current privacy research focuses on identity-centric voiceprint protection, leaving sensitive Speaker Attribute Privacy (SAP) underexplored.
Approach:	They propose a large-scale Chinese dataset to evaluate speaker-related privacy leakage . the dataset includes 227.3 hours of audio from 1,000 speakers .
Outcome:	The proposed model systematically evaluates speaker-related privacy leakage in everyday scenarios.

Copied to clipboard

Honglin Mu, Han He, Yuxin Zhou, Yunlong Feng, Yang Xu, Libo Qin, Xiaoming Shi, Zeming Liu, Xudong Han, Qi Shi, Qingfu Zhu, Wanxiang Che

MARCH: Multi-Agent Reinforced Check for Hallucination (2026.acl-long)

Challenge:	Existing black-box jailbreak methods often rely on model feedback . existing methods may be intercepted by content moderators during the search process .
Approach:	They propose a method that guides malicious prompt construction by local training a mirror model of the target black-box model through benign data distillation.
Outcome:	The proposed method achieves a 92% attack success rate and 80% stealth rate on a subset of AdvBench.

Copied to clipboard

Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie Hu, Yu Qin, null Erchao.zec, Xiaoxi Jiang, null Guanjunjiang

Knowing-but-Doing: Diagnosing and Defending Role-Play-Driven LLMs Jailbreaks via Moral Disengagement (2026.findings-acl)

Challenge:	Existing methods to detect hallucinations suffer from inherent confirmation bias, where the verifier inadvertently reproduces the errors of the original generation.
Approach:	They propose a framework that enforces rigorous factual alignment by leveraging deliberate information asymmetry by combining a pipeline of three specialized agents: a Solver, a Proposer, and a Checker.
Outcome:	Extensive experiments across hallucination benchmarks demonstrate that MARCH substantially reduces hallucinism rates.

Copied to clipboard

Haiming Qin, Jianxun Lian, Qimin Zhong, Mingyang Zhou, Hao Liao, Naipeng Chao

Specialization without Sparsity: Efficient and Expressive Split-Path Experts for LLM Fine-Tuning (2026.findings-acl)

Challenge:	Large Language Models (LLMs) are increasingly used in role-play scenarios, but their safety implications remain under-characterized.
Approach:	They propose a diagnostic benchmark for role-play jailbreaks based on Bandura’s Moral Disengagement theory and propose 'MD-Trace' based defense that reduces attack success while maintaining Role Fidelity.
Outcome:	The proposed framework improves safety behavior for benign personas while increasing unsafe compliance for malicious ones.

Copied to clipboard

Ganghao Liu, Qin Zhou, Zhe Wang, Xuehan Lu, Haihua Huang, Yunfei Tong, Heng Tian

MLDebugging: Towards Benchmarking Code Debugging Across Multi-Library Scenarios (2025.findings-acl)

Challenge:	Parameter-efficient fine-tuning (PEFT) is a low-cost alternative to full fine-timing due to the massive overhead.
Approach:	They propose a Mixture-of-Experts approach that enhances specialization while maintaining low resource overhead.
Outcome:	The proposed approach outperforms or matches state-of-the-art methods on GLUE, GSM8K, MBPP, and a text rewriting task from SmolTalk.

Copied to clipboard

JinYang Huang, Xiachong Feng, Qiguang Chen, Hanjie Zhao, Zihui Cheng, Jiesong Bai, Jingxuan Zhou, Min Li, Libo Qin

Programming Languages in NLP

Challenge:	MLDebugging is a benchmark designed to assess debugging challenges within multi-library Python code.
Approach:	They propose to introduce a benchmark to assess debugging challenges within multi-library Python code using 126 Python libraries.
Outcome:	The proposed benchmark covers 126 Python libraries and a wide range of multi-library code issues.

PsychEval: A Multi-Session and Multi-Therapy Benchmark for High-Realism AI Psychological Counselor (2026.findings-acl)

Copied to clipboard

Qianjun Pan, Junyi Wang, Jie Zhou, Yutao Yang, Junsong Li, Kaiyin Xu, Yougen Zhou, Yihan Li, JingYuan Zhao, Qin Chen, Ningning Zhou, Kai Chen, Liang He

Challenge:	Existing models focus on a single therapy, but complex cases require flexible strategies among various therapies.
Approach:	They propose a multi-session, multi-therapy, and highly realistic benchmark . it is designed to address three key challenges: 1) can we train a highly realistic AI counselor? 2) How to systematically evaluate an AI counselor?"
Outcome:	The proposed benchmark is annotated with extensive professional skills and includes over 677 meta-skills and 4577 atomic skills.

TamEdit: Trajectory-Aware Meta-Learning for Specificity-Preserving Continual Knowledge Editing (2026.acl-long)

Copied to clipboard

Shiqiang Tian, Cheng Ding, Qin Chen, Jie Zhou, Liang He

Align Attention Heads Before Merging Them: An Effective Way for Converting MHA to GQA (2025.findings-emnlp)

Challenge:	Existing methods for continual knowledge editing focus on single edits or preventing knowledge forgetting.
Approach:	They propose a meta-learning method that preserves specificity for continual knowledge editing by capturing relationships between different single edits within the trajectory.
Outcome:	Experiments show that TamEdit outperforms baselines in continual editing while preserving general capabilities.

Copied to clipboard

Qingyun Jin, Xiaohui Song, Feng Zhou, Zengchang Qin

Challenge:	Large language models (LLMs) have demonstrated exceptional performance across diverse natural language processing tasks.
Approach:	They propose a method for converting multi-head attention into grouped-query attention with any compression ratio of KV heads.
Outcome:	The proposed method can compress up to 87.5% KV heads of LLaMA2-7B model and 75% Kv heads of Sheared-LLa MA-1.3B with acceptable performance degradation.

P-React: Synthesizing Topic-Adaptive Reactions of Personality Traits via Mixture of Specialized LoRA Experts (2025.findings-acl)

Copied to clipboard

Yuhao Dan, Jie Zhou, Qin Chen, Junfeng Tian, Liang He

Challenge:	Existing studies on personalized large language models focus on modeling explicit character profiles, while ignoring the underlying personality traits that truly shape behaviors and decision-making.
Approach:	They propose a personalized large language model (LLM) that captures implicit Big Five personality traits and integrates a Personality Specialization Loss to capture individual trait expressions.
Outcome:	The proposed model improves on Big Five personality traits and integrates a Personality Specialization Loss (PSL) to capture individual trait expressions.

CGIM: A Cycle Guided Interactive Learning Model for Consistency Identification in Task-oriented Dialogue (2022.coling-1)

Copied to clipboard

Libo Qin, Qiguang Chen, Tianbao Xie, Qian Liu, Shijue Huang, Wanxiang Che, Zhou Yu

ChildTalk: A Multi-Dialect Chinese Child Speech Corpus with Full-Length Child–Caregiver Conversations for Speech Recognition (2026.findings-acl)

Challenge:	Consistency identification in task-oriented dialog usually consists of three subtasks . a proposed model for consistency identification in dialog is based on an explicit interaction paradigm .
Approach:	They propose a cycle guided interactive learning model that makes information exchange explicit from all the three tasks.
Outcome:	The proposed model achieves state-of-the-art performance pushing the overall score to 56.3% (5.0% point absolute improvement)

Copied to clipboard

Jiaming Zhou, Yujie Guo, Shiwan Zhao, Yao Lu, Jianye Wang, Haoqin Sun, Hui Wang, Yong Qin

Detecting Adversarial Samples through Sharpness of Loss Landscape (2023.findings-acl)

Challenge:	Automatic speech recognition (ASR) for children remains challenging due to developmental variability and the scarcity of high-quality corpora.
Approach:	They propose a large-scale Chinese child speech corpus that contains 112.5 hours of speech from 498 children and 500 caregivers.
Outcome:	The proposed model improves in-domain and cross-domain performance on children's speech.

Copied to clipboard

Rui Zheng, Shihan Dou, Yuhao Zhou, Qin Liu, Tao Gui, Qi Zhang, Zhongyu Wei, Xuanjing Huang, Menghan Zhang

Robustness in NLP

Challenge:	Existing studies have shown that adversarial samples are more vulnerable than normal ones to textual adversarials.
Approach:	They propose a simple and effective sharpness-based detector that can distinguish adversarial samples by maximizing the loss increment within the region where the inference sample is located.
Outcome:	The proposed method outperforms previous detection methods by large margins on three text classification tasks.

Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Information (2024.findings-emnlp)

Copied to clipboard

Yongheng Zhang, Qiguang Chen, Jingxuan Zhou, Peng Wang, Jiasheng Si, Jin Wang, Wenpeng Lu, Libo Qin

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

Challenge:	Chain-of-Thought (CoT) is a key technique for enhancing the performance of Large Language Models.
Approach:	They propose a framework that optimizes outputs by utilizing wrong information and multi-perspective verification.
Outcome:	The proposed framework surpasses all baselines on 8 datasets and 5 LLMs.

Copied to clipboard

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

Learning Intrinsic Dimension via Information Bottleneck for Explainable Aspect-based Sentiment Analysis (2024.lrec-main)

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

Copied to clipboard

Zhenxiao Cheng, Jie Zhou, Wen Wu, Qin Chen, Liang He

ChatMusician: Understanding and Generating Music Intrinsically with LLM (2024.findings-acl)

Challenge:	Gradient-based explanation methods are increasingly used to interpret neural models in natural language processing (NLP) however, in the context of Aspect-based Sentiment Analysis, only specific dimensions are pertinent.
Approach:	They propose a Gradient-based explanation framework that leverages an information bottleneck to refine word embeddings into a concise intrinsic dimension, maintaining essential features and omitting unrelated information.
Outcome:	The proposed framework improves both the models’ performance and explanations’ clarity by identifying sentiment-aware features.

Copied to clipboard

Ruibin Yuan, Hanfeng Lin, Yi Wang, Zeyue Tian, Shangda Wu, Tianhao Shen, Ge Zhang, Yuhang Wu, Cong Liu, Ziya Zhou, Liumeng Xue, Ziyang Ma, Qin Liu, Tianyu Zheng, Yizhi Li, Yinghao Ma, Yiming Liang, Xiaowei Chi, Ruibo Liu, Zili Wang, Chenghua Lin, Qifeng Liu, Tao Jiang, Wenhao Huang, Wenhu Chen, Jie Fu, Emmanouil Benetos, Gus Xia, Roger Dannenberg, Wei Xue, Shiyin Kang, Yike Guo

AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora (2026.acl-long)

Challenge:	Despite LLMs' impressive capabilities in musical knowledge, music reasoning remains an unsolved task.
Approach:	They propose an open-source large language model (LLM) that integrates intrinsic musical abilities into LLaMA2 and GPT-3.5.
Outcome:	The proposed model can understand and generate music with a pure text tokenizer without external multi-modal neural structures or tokenizers.

Copied to clipboard

Jiaxin Bai, Wei Fan, Qi Hu, Qing Zong, Chunyang Li, Hong Ting Tsang, Hongyu Luo, Yauwai Yim, Haoyu Huang, Xiao Zhou, Feng Qin, Tianshi Zheng, Xi Peng, Xin Yao, Huiwen Yang, Leijie Wu, JI Yi, Gong Zhang, Renhai Chen, Yangqiu Song

An Effective Deployment of Contrastive Learning in Multi-label Text Classification (2023.findings-acl)

Challenge:	Existing knowledge graph construction frameworks require predefined schemas, limiting their scalability and domain coverage.
Approach:	They propose a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas.
Outcome:	The proposed framework outperforms state-of-the-art models on multi-hop QA tasks and enhances LLM factuality.

Copied to clipboard

Nankai Lin, Guanqiu Qin, Gang Wang, Dong Zhou, Aimin Yang

DLPO: Towards a Robust, Efficient, and Generalizable Prompt Optimization Framework from a Deep-Learning Perspective (2025.findings-emnlp)

Challenge:	Existing studies on contrastive learning in natural language processing tasks have not explored the effectiveness of the technology.
Approach:	They propose five novel contrastive losses for multi-label text classification tasks that exploit the complexity of the input logic and the semantic representation space.
Outcome:	The proposed contrastive losses improve multi-label text classification tasks and can be adapted for multi-task tasks.

Copied to clipboard

Dengyun Peng, Yuhang Zhou, Qiguang Chen, JinHao Liu, Jingjing Chen, Libo Qin, Wanxiang Che

On Transferability of Prompt Tuning for Natural Language Processing (2022.naacl-main)

Challenge:	Existing methods for prompt optimization still face challenges in robustness, efficiency, and generalization.
Approach:	They propose 7 new approaches inspired by traditional deep learning paradigms for prompt optimization that integrate text-based gradient optimization.
Outcome:	The proposed methods integrate deep learning paradigms into text-based gradient optimization.

Copied to clipboard

Yusheng Su, Xiaozhi Wang, Yujia Qin, Chi-Min Chan, Yankai Lin, Huadong Wang, Kaiyue Wen, Zhiyuan Liu, Peng Li, Juanzi Li, Lei Hou, Maosong Sun, Jie Zhou

End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions (2023.emnlp-main)

Challenge:	Pre-trained language models (PLMs) can achieve comparable performance to full-parameter fine-tuning by tuning a few soft prompts, but require much more training time than fine-timing.
Approach:	They empirically investigate the transferability of soft prompts across different downstream tasks and PLMs to determine what decides prompt transferability.
Outcome:	The proposed method can achieve comparable performance to full-parameter fine-tuning by tuning a few soft prompts, but requires much more training time than fine-timing.

Copied to clipboard

Libo Qin, Wenbo Pan, Qiguang Chen, Lizi Liao, Zhou Yu, Yue Zhang, Wanxiang Che, Min Li

SmartTrim: Adaptive Tokens and Attention Pruning for Efficient Vision-Language Models (2024.lrec-main)

Challenge:	End-to-end task-oriented dialogue (EToD) can generate responses in an end-to end fashion without modular training, which attracts escalating popularity.
Approach:	They present a systematic review of EToD and propose a unified perspective to summarize existing approaches and recent trends.
Outcome:	The proposed approaches can generate responses in an end-to-end fashion without modular training, which attracts escalating popularity.

Copied to clipboard

Zekun Wang, Jingchang Chen, Wangchunshu Zhou, Haichao Zhu, Jiafeng Liang, Liping Shan, Ming Liu, Dongliang Xu, Qing Yang, Bing Qin

CodeBERT: A Pre-Trained Model for Programming and Natural Languages (2020.findings-emnlp)

Challenge:	Experimental results show that SmartTrim accelerates the original model by 2-3 times with minimal performance degradation.
Approach:	They propose an adaptive acceleration framework which prunes redundant token representations and attention heads within each layer of the original model.
Outcome:	The proposed framework accelerates the original model by 2-3 times with minimal performance degradation across vision-language tasks.

Copied to clipboard

Zhangyin Feng, Daya Guo, Duyu Tang, Nan Duan, Xiaocheng Feng, Ming Gong, Linjun Shou, Bing Qin, Ting Liu, Daxin Jiang, Ming Zhou

Semantic Parsing with Syntax- and Table-Aware SQL Generation (P18-1)

Challenge:	Large pre-trained models have improved performance on a variety of natural language processing tasks.
Approach:	They develop a bimodal pre-trained model for programming language (PL) and natural language (NL) it incorporates a hybrid objective function that detects replaced tokens from generators.
Outcome:	The proposed model performs better on two NL-PL applications by fine-tuning model parameters.

Copied to clipboard

Yibo Sun, Duyu Tang, Nan Duan, Jianshu Ji, Guihong Cao, Xiaocheng Feng, Bing Qin, Ting Liu, Ming Zhou

ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks (2025.emnlp-main)

Challenge:	Existing approaches generate a SQL query word-by-word but results are incorrect or not executable due to mismatch between question words and table contents.
Approach:	They propose a generative model to map natural language questions into SQL queries.
Outcome:	The proposed model significantly improves state-of-the-art execution accuracy from 69.0% to 74.4% on a large question- SQL dataset.

Copied to clipboard

Heng Zhou, Hejia Geng, Xiangyuan Xue, Li Kang, Yiran Qin, Zhiyong Wang, Zhenfei Yin, Lei Bai

Exclusion of Thought: Mitigating Cognitive Load in Large Language Models for Enhanced Reasoning in Multiple-Choice Tasks (2025.acl-long)

Challenge:	Multi-agent systems (MAS) are limited by poor flexibility and scalability, with underdeveloped optimization strategies.
Approach:	They propose a task graph generation and a reward-driven two-stage agent selection process to integrate multi-agent systems to improve their reasoning capabilities.
Outcome:	The proposed model outperforms existing methods on Math-MAS and SciBench-MAS SciBech, while other methods completely fail.

Copied to clipboard

Qihang Fu, Yongbin Qin, Ruizhang Huang, Yanping Chen, Yulin Zhou, Lintao Long

WebCPM: Interactive Web Search for Chinese Long-form Question Answering (2023.acl-long)

Challenge:	Multiple-choice questions (MCQs) are widely used and vital assessment format for evaluating large language models (LLMs).
Approach:	They propose a reasoning prompt strategy that redirects the model's attention away from erroneous options and eliminates incorrect options.
Outcome:	The proposed reasoning prompt reduces cognitive load by steering the model’s attention away from erroneous options, enabling the model to focus more effectively on reasonable answers.

Copied to clipboard

Yujia Qin, Zihan Cai, Dian Jin, Lan Yan, Shihao Liang, Kunlun Zhu, Yankai Lin, Xu Han, Ning Ding, Huadong Wang, Ruobing Xie, Fanchao Qi, Zhiyuan Liu, Maosong Sun, Jie Zhou

Information Retrieval

Challenge:	Long-form question answering requires two procedures: information retrieval and information synthesis.
Approach:	They propose a Chinese long-form question answering dataset called WebCPM . the dataset is based on a web search interface that engages with a search engine in real time .
Outcome:	The proposed dataset generates answers that are no worse than human-written ones . the dataset is the first Chinese LFQA dataset .

Toward Consistent World Models with Multi-Token Prediction and Latent Semantic Enhancement (2026.acl-long)

Copied to clipboard

Qimin Zhong, Hao Liao, Haiming Qin, Mingyang Zhou, Rui Mao, Wei Chen, Naipeng Chao

WebAnchor: Anchoring Agent Planning to Stabilize Long-Horizon Web Reasoning (2026.findings-acl)

Challenge:	Existing methods to learn internal world models rely on one-step supervision . however, standard MTP suffers from structural hallucinations .
Approach:	They propose a method which anchors predictions to ground-truth hidden state trajectories.
Outcome:	The proposed method bridges the gap between discrete tokens and continuous state representations, reducing structural hallucinations, and improving robustness to perturbations.

Copied to clipboard

Xinmiao Yu, Liwen Zhang, Xiaocheng Feng, Pengjun Xie, Jingren Zhou, Bing Qin, Yong Jiang

CCHall: A Novel Benchmark for Joint Cross-Lingual and Cross-Modal Hallucinations Detection in Large Language Models (2025.acl-long)

Challenge:	Existing methods for reinforcement learning (RL)-based agents struggle with long-horizon planning and strategy coherence.
Approach:	They propose a reinforcement learning framework that decouples planning and execution.
Outcome:	The proposed framework outperforms baseline and first-step RL frameworks on four benchmarks.

Copied to clipboard

Yongheng Zhang, Xu Liu, Ruoxi Zhou, Qiguang Chen, Hao Fei, Wenpeng Lu, Libo Qin

Understanding Large Language Model Vulnerabilities to Social Bias Attacks (2025.acl-long)

Challenge:	Existing studies on hallucinations in large language models are limited to a single scenario, either cross-lingual or cross-modal.
Approach:	They propose a joint Cross-lingual and Cross-modal hallucinations benchmark to fill this gap . they incorporate cross-lingual, cross-modal scenarios to assess hallucinic capabilities .
Outcome:	The proposed benchmark incorporates both cross-lingual and cross-modal hallucination scenarios to assess the cross-linguistic and crossmodal capabilities of LLMs.

Copied to clipboard

Jiaxu Zhao, Meng Fang, Fanghua Ye, Ke Xu, Qin Zhang, Joey Tianyi Zhou, Mykola Pechenizkiy

Better Zero-Shot Reasoning with Role-Play Prompting (2024.naacl-long)

Challenge:	Large Language Models (LLMs) have demonstrated remarkable linguistic capabilities across tasks . however, there is a growing concern about their potential to perpetuate social biases .
Approach:	They evaluate LLMs across gender, racial, and religious bias types . they also explore cross-bias and multiple-biases attacks .
Outcome:	The proposed models are more susceptible to gender bias attacks than racial or religious biases.

Copied to clipboard

Aobo Kong, Shiwan Zhao, Hao Chen, Qicheng Li, Yong Qin, Ruiqi Sun, Xin Zhou, Enzhi Wang, Xiaohang Dong

Low-Resource NLP

Challenge:	Recent years have witnessed a paradigm shift in natural language processing, driven by large language models such as GPT-3, PaLM, and Llama.
Approach:	They propose a strategy for role-play prompting and assess its performance under the zero-shot setting.
Outcome:	The proposed method outperforms the standard zero-shot prompting approach across 12 reasoning benchmarks.

Decoding Susceptibility: Modeling Misbelief to Misinformation Through a Computational Approach (2024.emnlp-main)

Copied to clipboard

Yanchen Liu, Mingyu Ma, Wenna Qin, Azure Zhou, Jiaao Chen, Weiyan Shi, Wei Wang, Diyi Yang

Attending via both Fine-tuning and Compressing (2021.findings-acl)

Challenge:	Existing studies on susceptibility to misinformation rely on self-reported beliefs, which can be subject to bias, expensive to collect, and challenging to scale for downstream applications.
Approach:	They propose a computational approach to efficiently model users’ latent susceptibility levels by using demographic factors and political ideology as inputs.
Outcome:	The proposed model shows that political leanings and other psychological factors exhibit varying degrees of association with susceptibility to COVID-19 misinformation.

Copied to clipboard

Jie Zhou, Yuanbin Wu, Qin Chen, Xuanjing Huang, Liang He

Explainability & Interpretability in NLP

Challenge:	Existing studies show that attention mechanisms can improve models' interpretation, but they are not explicable.
Approach:	They propose a framework consisting of a learner and a compressor to purify attention scores . they propose to fine-tune and compress the attention mechanism to obtain a more faithful explanation .
Outcome:	The proposed framework improves performance and interpretability on eight benchmark datasets.

PersonaArena: Dynamic Simulation for Evaluating and Enhancing Persona-Level Role-Playing in Large Language Models (2026.findings-acl)

Copied to clipboard

Wenlong Shi, Jianxun Lian, Mingqi Wu, Haiming Qin, Mingyang Zhou, Xing Xie, Naipeng Chao, Hao Liao

ESCoT: Towards Interpretable Emotional Support Dialogue Systems (2024.acl-long)

Challenge:	Existing research focuses on character-level settings and static evaluation formats fail to capture the complexity of everyday social interactions.
Approach:	They propose a dynamic simulation framework for evaluating and improving persona-level role-playing in large language models (LLMs).
Outcome:	The proposed framework leverages user-generated social content to construct a nuanced persona bank and elicits multi-turn, context-rich interactions within simulated social environments.

Copied to clipboard

Tenggan Zhang, Xinjie Zhang, Jinming Zhao, Li Zhou, Qin Jin

Treble Counterfactual VLMs: A Causal Approach to Hallucination (2025.findings-emnlp)

Challenge:	Emotion-focused and strategy-driven chain-of-thought (ESCoT) is a new paradigm for emotional support dialogues.
Approach:	They propose an emotional support response generation scheme to improve interpretability . they generate a dataset and develop a model to generate dialogue responses with better interpretability.
Outcome:	The proposed scheme can generate dialogue responses with better interpretability.

Copied to clipboard

Li Li, Jiashu Qu, Linxin Song, Yuxiao Zhou, Yuehan Qin, Tiankai Yang, Yue Zhao

ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning (2021.acl-long)

Challenge:	Existing studies link hallucination to data or representation biases, but their causal origins remain unclear.
Approach:	They propose a causal framework to analyze and mitigate hallucination in vision-language models by using counterfactual analysis to estimate the Natural Direct Effect (NDE) of each modality and their interaction.
Outcome:	The proposed framework significantly reduces hallucination while preserving task performance while retaining reliability.

Copied to clipboard

Yujia Qin, Yankai Lin, Ryuichi Takanobu, Zhiyuan Liu, Peng Li, Heng Ji, Minlie Huang, Maosong Sun, Jie Zhou

Hierarchical Reward Modeling for Fault Localization in Large Code Repositories (2025.findings-emnlp)

Challenge:	Existing pre-training objectives do not explicitly model relational facts in text . Experimental results show that ERICA can improve typical PLMs on several language understanding tasks, including relation extraction, entity typing and question answering.
Approach:	They propose a contrastive learning framework ERICA to obtain a deep understanding of entities and relations in text.
Outcome:	The proposed framework can improve PLMs on several language understanding tasks, especially under low-resource settings.

Copied to clipboard

Jiwei Zhang, Jianxun Lian, Haiming Qin, Mingyang Zhou, KeZhong Lu, Rui Mao, Hao Liao

Challenge:	Large Language Models (LLMs) have limited fault localization capabilities due to limited context length.
Approach:	They propose a hierarchical localization reward model to evaluate and select the most accurate fault localization candidates from the outputs of LLMs.
Outcome:	The proposed model improves the final line-level localization recall by 12% on the SWE-Bench-Lite dataset.

A Survey of Inductive Reasoning for Large Language Models (2026.acl-long)

Copied to clipboard

Kedi Chen, Dezhao Ruan, Yuhao Dan, Yaoting Wang, Siyu Yan, Xuecheng Wu, Yinqi Zhang, Qin Chen, Jie Zhou, Liang He, Biqing Qi, Linyang Li, Qipeng Guo, Xiaoming Shi, Wei Zhang

Enhancing Chat Language Models by Scaling High-quality Instructional Conversations (2023.emnlp-main)

Challenge:	Inductive reasoning is an important task for large language models (LLMs).
Approach:	They propose a survey of inductive reasoning for large language models . they categorize methods into three main areas: post-training enhancement, test-time exploration, and data augmentation.
Outcome:	The proposed method improves inductive reasoning in large language models.

Copied to clipboard

Ning Ding, Yulin Chen, Bokai Xu, Yujia Qin, Shengding Hu, Zhiyuan Liu, Maosong Sun, Bowen Zhou

LLMBox: A Comprehensive Library for Large Language Models (2024.acl-demos)

Challenge:	a recent study validates the effectiveness of chat language models by fine-tuning instruction data.
Approach:	They propose to use a large-scale dataset of instructional conversations to fine-tune a conversational model on instruction data.
Outcome:	The proposed model outperforms open-source models in key metrics including scale, average length, diversity, coherence, etc.

Copied to clipboard

Tianyi Tang, Hu Yiwen, Bingqian Li, Wenyang Luo, ZiJing Qin, Haoxiang Sun, Jiapeng Wang, Shiyi Xu, Xiaoxue Cheng, Geyang Guo, Han Peng, Bowen Zheng, Yiru Tang, Yingqian Min, Yushuo Chen, Jie Chen, Ranchi Zhao, Luran Ding, Yuhao Wang, Zican Dong, Xia Chunxuan, Junyi Li, Kun Zhou, Xin Zhao, Ji-Rong Wen

MessToClean: Evidence-Grounded Structure-Preserving Reconstruction for Real-World Degraded Exam Paper Images (2026.acl-long)

Challenge:	a library to facilitate the development, use, and evaluation of large language models (LLMs) is presented.
Approach:	They propose a unified library to facilitate the development, use and evaluation of large language models (LLMs).
Outcome:	The proposed library is based on extensive experiments in a variety of evaluation settings.

Copied to clipboard

Jiayi Tuo, Cheng Tang, Zihan Wang, Chenyue Zhou, Yao Li, Yanbiao Ma, Chao Wang, Wei Dai, Mingxuan Wang, Shitong Qin, Ziwei Zhao

R-CHAR: A Metacognition-Driven Framework for Role-Playing in Large Language Models (2025.emnlp-main)

Challenge:	Existing Multimodal Large Language Models (MLLMs) fail under RDEI, leading to disrupted structure and evidence-unsupported hallucinations.
Approach:	They propose a backbone-agnostic, evidence-driven pipeline that treats off-the-shelf MLLMs as interchangeable components to improve stem consistency and figure consistency.
Outcome:	The proposed pipeline improves stem consistency by 1.01-3.18%, figure consistency by 0.50-49.16%, and refusal F1 by 1.06-10.88% across question types.

Copied to clipboard

Haiming Qin, Jiwei Zhang, Wei Zhang, KeZhong Lu, Mingyang Zhou, Hao Liao, Rui Mao

Soft Contextual Data Augmentation for Neural Machine Translation (P19-1)

Challenge:	Existing role-playing structures lack cognitive consistency in complex scenarios . Existing models excel in math and coding tasks but lack coherent reasoning .
Approach:	They propose a metacognition-driven framework that enhances role-playing performance . experimental results show performance improvements across varying scenario complexities .
Outcome:	The proposed framework outperforms existing models in social intelligence tasks and shows strength in long-context comprehension and group-level social interactions.

Copied to clipboard

Fei Gao, Jinhua Zhu, Lijun Wu, Yingce Xia, Tao Qin, Xueqi Cheng, Wengang Zhou, Tie-Yan Liu

Machine Translation

Challenge:	Existing methods for enhancing training data are limited in natural language tasks due to text characteristics.
Approach:	They propose a data augmentation method that softly augments a randomly chosen word in a sentence by its contextual mixture of multiple related words.
Outcome:	The proposed method outperforms baseline methods on small and large scale machine translation datasets.

OAgents: An Empirical Study of Building Effective Agents (2025.findings-emnlp)

Copied to clipboard

He Zhu, Tianrui Qin, King Zhu, Heyuan Huang, Yeyi Guan, Jinxiang Xia, Hanhao Li, Yi Yao, Ningning Wang, Pai Liu, Tianhao Peng, Xin Gui, Li Xiaowan, Yuhui Liu, Xiangru Tang, Jian Yang, Ge Zhang, Xitong Gao, Yuchen Eleanor Jiang, Changwang Zhang, Jun Wang, Jiaheng Liu, Wangchunshu Zhou

QA‐LIGN: Aligning LLMs through Constitutionally Decomposed QA (2025.findings-emnlp)

Challenge:	a recent study shows that agent research practices are far from standard, rigorous . lack of a standard evaluation protocol makes previous works not reproducible, authors say .
Approach:	They conduct an empirical study on the GAIA benchmark to investigate agent design choices . they find that lack of a standard evaluation protocol makes previous works not reproducible .
Outcome:	The proposed framework achieves state-of-the-art performance among open-source projects.

Copied to clipboard

Jacob Dineen, Aswin Rrv, Qin Liu, Zhikun Xu, Xiao Ye, Ming Shen, Zhaonan Li, Shijie Lu, Chitta Baral, Muhao Chen, Ben Zhou

Explainability & Interpretability in NLP

Challenge:	QA-LIGN decomposes monolithic rewards into interpretable principle-specific evaluations . scalar rewards obscure which objectives drive the training signal .
Approach:	a new method decomposes monolithic rewards into interpretable principle-specific evaluations . QA-LIGN reduces attack success rates by up to 68.7% while maintaining a 0.67% false refusal rate .
Outcome:	QA-LIGN reduces attack success rates by up to 68.7% while maintaining a 0.67% false refusal rate . the results outperform DPO and GRPO with state-of-the-art reward models given equivalent training .

Different Tunes Played with Equal Skill: Exploring a Unified Optimization Subspace for Parameter-Efficient Tuning (2022.findings-emnlp)

Copied to clipboard

Jing Yi, Weize Chen, Yujia Qin, Yankai Lin, Ning Ding, Xu Han, Zhiyuan Liu, Maosong Sun, Jie Zhou

Green & Sustainable NLP

Challenge:	Existing delta tuning algorithms freeze most of the parameters and only optimize minimal adaptive parameters.
Approach:	They propose to decompose DETs into a unified optimization subspace and conduct optimization within the subspace.
Outcome:	The proposed DETs achieve comparable performance to the original DET and can be transferred to another DET with non-trivial performance.

False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize (2026.findings-acl)

Copied to clipboard

Cheng Wang, Zeming Wei, Qin Liu, Wenxuan Zhou, Muhao Chen

ELLE: Efficient Lifelong Pre-training for Emerging Data (2022.findings-acl)

Challenge:	Recent work has leveraged probing-based approaches to study the separability of malicious and benign inputs in Large Language Models’ internal representations.
Approach:	They propose to use probing-based methods to study separability of malicious and benign inputs in LLMs' internal representations to detect harmful and benign content.
Outcome:	The proposed methods show that they learn superficial patterns rather than semantic harmfulness.

Copied to clipboard

Yujia Qin, Jiajie Zhang, Yankai Lin, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

LLM-KT: Enhancing Large Language Models with Knowledge Tracing via Multi-Level Plug-and-Play Alignment (2026.findings-acl)

Challenge:	Existing pre-trained language models are typically trained with static data, ignoring that streaming data of various sources may continuously grow.
Approach:	They propose to use function preserved model expansion to expand existing PLM's width and depth to improve efficiency of knowledge acquisition.
Outcome:	The proposed model improves pre-training efficiency and performance over existing models on BERT and GPT.

Copied to clipboard

Ziwei Wang, Jie Zhou, Qin Chen, Bo Jiang, Qingchun Bai, Liang Dou, Liang He

Taming Extreme Tokens: Covariance-Aware GRPO with Gaussian-Kernel Advantage Reweighting (2026.acl-short)

Challenge:	Existing methods to learn behavioral sequences fail to capture complex behavioral patterns due to a lack of deep reasoning capabilities and world knowledge.
Approach:	They propose a framework that integrates the reasoning power of Large Language Models with the sequential modeling strengths of traditional KT methods via multi-level plug-and-play alignment.
Outcome:	Extensive experiments on four standard datasets show that the proposed framework outperforms existing methods on state-of-the-art questions.

Copied to clipboard

Cheng Wang, Qin Liu, Wenxuan Zhou, Muhao Chen

Ranking-Based Autoencoder for Extreme Multi-label Classification (N19-1)

Challenge:	Excessive exploitation can cause the model to become overconfident in its suboptimal solutions, thereby limiting its capabilities to explore novel reasoning strategies.
Approach:	They propose a method that dynamically down-weights extreme token-level updates via a Gaussian kernel and reduces the instability caused by the trade-off.
Outcome:	The proposed method improves downstream performance across reasoning benchmarks and stabilizes entropy as training progresses.

Copied to clipboard

Bingyu Wang, Li Chen, Wei Sun, Kechen Qin, Kefeng Li, Hui Zhou

TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing (2021.acl-demo)

Challenge:	Existing methods to solve label dependency and noisy labeling problems are limited . experimental results show the proposed method is competitive to state-of-the-art methods .
Approach:	They propose a deep learning XML method with word-vector-based self-attention followed by ranking-based AutoEncoder architecture to solve these problems.
Outcome:	The proposed method is competitive to state-of-the-art methods on benchmark datasets.

Copied to clipboard

Xiao Wang, Qin Liu, Tao Gui, Qi Zhang, Yicheng Zou, Xin Zhou, Jiacheng Ye, Yongxin Zhang, Rui Zheng, Zexiong Pang, Qinzhuo Wu, Zhengyan Li, Chong Zhang, Ruotian Ma, Zichu Fei, Ruijian Cai, Jun Zhao, Xingwu Hu, Zhiheng Yan, Yiding Tan, Yuan Hu, Qiyuan Bian, Zhihua Liu, Shan Qin, Bolin Zhu, Xiaoyu Xing, Jinlan Fu, Yue Zhang, Minlong Peng, Xiaoqing Zheng, Yaqian Zhou, Zhongyu Wei, Xipeng Qiu, Xuanjing Huang

Robustness in NLP

Challenge:	Existing approaches to textual robustness evaluation focus on slightly modifying the input data, which maintains the original meaning and results in a different prediction.
Approach:	They propose a multilingual robustness evaluation toolkit for NLP that integrates universal text transformations, task-specific transformations and adversarial attack.
Outcome:	The toolkit includes universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analyses.

SpeechLLM-as-Judges: Towards General and Interpretable Speech Quality Evaluation (2026.acl-long)

Copied to clipboard

Hui Wang, Jinghua Zhao, Yifan Yang, Shujie Liu, Junyang Chen, Yanzhe Zhang, Shiwan Zhao, Jinyu Li, Jiaming Zhou, Haoqin Sun, Yan Lu, Yong Qin