Papers by Hui Xu

Ask-Before-Detection: Identifying and Mitigating Conformity Bias in LLM-Powered Error Detector for Math Word Problem Solutions (2025.acl-long)

Challenge:	Existing DRA methods fail to accurately recover the original text of real-world privacy data.
Approach:	They propose to use a real-world privacy dataset to examine the performance of federated learning (FL) methods.
Outcome:	The proposed method improves on a real-world privacy dataset and shows that the tokens within a recovery sentence are disordered and intertwined with tokens from other sentences in the same training batch.

Copied to clipboard

Hang Li, Tianlong Xu, Kaiqi Yang, Yucheng Chu, Yanling Chen, Yichi Song, Qingsong Wen, Hui Liu

Numerical Reasoning

Challenge:	Recent studies have demonstrated the potential of large language models (LLMs) for automatic error detection in math word problems (MWPs).
Approach:	They propose a framework that generates adaptive reference solutions using LLMs to enhance error detection by reducing conformity bias in MWPs.
Outcome:	The proposed framework mitigates the performance gap between conventional and alternative solutions in MWPs, especially when combined with reasoning-enhancing techniques like chain-of-thought prompting.

MPRF: Interpretable Stance Detection through Multi-Path Reasoning Framework (2025.emnlp-main)

Copied to clipboard

ZhaoDan Zhang, Jin Zhang, Hui Xu, Jiafeng Guo, Xueqi Cheng

An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4 (2025.findings-acl)

Challenge:	Existing stance detection methods treat the task as a classification problem, where models output a stance label without providing interpretable reasoning paths.
Approach:	They propose a framework that generates, evaluates, and integrates multiple reasoning paths to improve accuracy, robustness, and transparency in stance detection.
Outcome:	The proposed framework outperforms existing models on the SEM16, VAST, and PStance datasets and is highly interpretable and reliable.

Copied to clipboard

Hui Huang, Xingyuan Bu, Hongli Zhou, Yingqi Qu, Jing Liu, Muyun Yang, Bing Xu, Tiejun Zhao

LLM-Driven Knowledge Injection Advances Zero-Shot and Cross-Target Stance Detection (2024.naacl-short)

Challenge:	Recent studies have fine-tuned judge models based on open-source LLMs to evaluate the quality of other LLM.
Approach:	They propose to use open-source LLMs to evaluate Large Language Models (LLMs) their empirical results show that the models underperform GPT-4 in several dimensions .
Outcome:	The proposed models outperform GPT-4 on several dimensions including generalizability, fairness and adaptability.

Copied to clipboard

Zhao Zhang, Yiming Li, Jin Zhang, Hui Xu

Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents (2026.acl-long)

Challenge:	Existing methods for stance detection focus on background information and not on the accompanying input texts.
Approach:	They propose to prompt Large Language Models to explicitly extract the relationship between paired text and unseen target as contextual knowledge and inject it into a generation model BART to exploit the rich contexts and semantics.
Outcome:	The proposed model is able to detect stance labels in zero-shot and cross-target scenarios.

Copied to clipboard

Yifei Li, Weidong Guo, Lingling Zhang, Rongman Xu, Muye Huang, Hui Liu, Lijiao Xu, Yu Xu, Jun Liu

Challenge:	Existing benchmarks and evaluation protocols focus on surface-level factual recall.
Approach:	They propose a benchmark for assessing cognitive memory under cue–trigger semantic disconnect.
Outcome:	The proposed framework reveals failures not captured by existing benchmarks.

Towards Fine-Grained and Multi-Granular Contrastive Language-Speech Pre-training (2026.acl-long)

Copied to clipboard

Yifan Yang, Bing Han, Hui Wang, Wei Wang, Ziyang Ma, Long Zhou, Zengrui Jin, Guanrou Yang, Tianrui Wang, Xu Tan, Xie Chen

Error Comparison Optimization for Large Language Models on Aspect-Based Sentiment Analysis (2025.acl-long)

Challenge:	Existing models for fine-grained speaking styles are limited in terms of accuracy, coverage, and naturalness.
Approach:	They propose a model that pre-trains with coarse captions and annotates with a pipeline that grounds captions in audio.
Outcome:	The proposed model outperforms existing models with fine-grained style annotations . it integrates global and fine-granular supervision, enabling unified representations based on the proposed model .

Copied to clipboard

Qianlong Wang, Keyang Ding, Hengxin Gao, Hui Wang, Ruifeng Xu

ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection (2026.findings-acl)

Challenge:	Existing methods for aspect-based sentiment analysis (ABSA) only compare current predictions and labels on each sample, yet fail to perceive and understand its error outputs from different degrees.
Approach:	They propose a framework that can perceive and understand the degree of errors by learning from comparative error pairs.
Outcome:	The proposed framework exceeds baselines and achieves the desired performance.

Copied to clipboard

Yibo Yan, Shen Wang, Jiahao Huo, Hang Li, Boyan Li, Jiamin Su, Xiong Gao, YiFan Zhang, Tianlong Xu, Zhendong Chu, Aoxiao Zhong, Kun Wang, Hui Xiong, Philip S. Yu, Xuming Hu, Qingsong Wen

Modularized Interaction Network for Named Entity Recognition (2021.acl-long)

Challenge:	Current mathematical benchmarks focus on evaluating MLLMs’ problem-solving ability, yet there is a crucial gap in addressing more complex scenarios such as error detection.
Approach:	They propose to evaluate multimodal error detection by evaluating two sub-tasks error step identification and error categorization.
Outcome:	The proposed task evaluates MLLMs' ability to handle multimodal questions compared to text-only models.

Copied to clipboard

Fei Li, Zheng Wang, Siu Cheung Hui, Lejian Liao, Dandan Song, Jing Xu, Guoxiu He, Meihuizi Jia

Information Extraction & Text Mining

Challenge:	Named Entity Recognition (NER) models focus on word-level information, while segment-based models focus only on word level information.
Approach:	They propose a Modularized Interaction Network (MIN) model which utilizes both word-level information and segment-level dependencies.
Outcome:	The proposed model outperforms the current state-of-the-art models on three NER benchmark datasets.

T-MAD: Target-driven Multimodal Alignment for Stance Detection (2025.emnlp-main)

Copied to clipboard

ZhaoDan Zhang, Jin Zhang, Xueqi Cheng, Hui Xu

Boosting Text-to-SQL through Multi-grained Error Identification (2025.coling-main)

Challenge:	Existing methods for Multimodal Stance Detection struggle with generalizing to unseen targets and handling modality inconsistencies.
Approach:	They propose a multimodal stability detection model which captures target-specific relationships and balances modality contributions by iterative reasoning.
Outcome:	Experiments on the MMSD and MultiClimate datasets show that the proposed model outperforms state-of-the-art models with optimal results achieved using RoBERTa, ViT, and an iterative depth of 5.

Copied to clipboard

Bo Xu, Shufei Li, Hongyu Jing, Ming Du, Hui Song, Hongya Wang, Yanghua Xiao

Programming Languages in NLP

Challenge:	Existing methods for error identification often overlook validation of generated results . text-to-SQL is a technology that converts natural language questions into executable SQL queries .
Approach:	They propose to integrate a multi-grained error identification method into existing methods to detect SQL errors.
Outcome:	The proposed method can be integrated as a plugin into various methods, providing effective error identification and correction capabilities.

A Holistic Approach to Reference-Free Evaluation of Machine Translation (2023.acl-short)

Copied to clipboard

Hanming Wu, Wenjuan Han, Hui Di, Yufeng Chen, Jinan Xu

Multilinguality

Challenge:	Traditional machine translation evaluation relies on reference written by humans . reference-free evaluation gets rid of labor-intensive annotations, which can pivot easily to new domains .
Approach:	They propose a reference-free evaluation approach that characterizes evaluation as two aspects: fluency and faithfulness.
Outcome:	The proposed approach outperforms SOTA reference-fee metrics on machine translation datasets.

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

Information Retrieval

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.

LongFaith: Enhancing Long-Context Reasoning in LLMs with Faithful Synthetic Data (2025.findings-acl)

Copied to clipboard

Cehao Yang, Xueyuan Lin, Chengjin Xu, Xuhui Jiang, Shengjie Ma, Aofan Liu, Hui Xiong, Jian Guo

Ruleformer: Context-aware Rule Mining over Knowledge Graph (2022.coling-1)

Challenge:	Long-context processing ability has emerged as a significant challenge for large language models.
Approach:	They propose a pipeline for synthesizing faithful long-context reasoning instruction datasets . they integrate ground truth and citation-based reasoning prompts integrating them .
Outcome:	The proposed pipeline eliminates distractions and improves reasoning chains.

Copied to clipboard

Zezhong Xu, Peng Ye, Hui Chen, Meng Zhao, Huajun Chen, Wen Zhang

Towards Table-to-Text Generation with Pretrained Language Model: A Table Structure Understanding and Text Deliberating Approach (2022.emnlp-main)

Challenge:	Existing work on rule mining focuses on mining rules, but how to select appropriate rules for completion of different triplets has not been discussed.
Approach:	They propose to take context information into consideration when selecting suitable rules . they devise a transformer-based rule mining approach, Ruleformer .
Outcome:	The proposed model takes context information into consideration, which helps select suitable rules for inference tasks.

Copied to clipboard

Miao Chen, Xinjiang Lu, Tong Xu, Yanyan Li, Zhou Jingbo, Dejing Dou, Hui Xiong

Text Generation

Challenge:	Currently, the generalization issues hinder the applicability of neural table-to-text models due to the limited source tables.
Approach:	They propose a table-structureaware text generation model with pretrained language model and propose TASD to bridge the gap between the structured table and text input.
Outcome:	The proposed model bridges the gap between the structured table and text input and generates accurate and fluent descriptive texts on two public datasets.

Separation and Fusion: A Novel Multiple Token Linking Model for Event Argument Extraction (2024.naacl-long)

Copied to clipboard

Jing Xu, Dandan Song, Siu Hui, Zhijing Wu, Meihuizi Jia, Hao Wang, Yanru Zhou, Changzhi Zhou, Ziyi Yang

Information Extraction & Text Mining

Challenge:	Existing methods for event argument extraction (EAE) lack cross-event information and require longer role sequences . et al. (2017): outperforms state-of-the-art methods for EE.
Approach:	They propose a separation-and-fusion paradigm to separate the acquisition of cross-event information and fuse it into the argument extraction of a target event.
Outcome:	The proposed model outperforms the state-of-the-art models on four widely used datasets.

MAQuA: Multi-outcome Adaptive Question-Asking for Mental Health using Item Response Theory (2026.eacl-long)

Copied to clipboard

Vasudha Varadarajan, Hui Xu, Rebecca Astrid Böhme, Mariam Marlen Mirström, Sverker Sikström, H. Andrew Schwartz

DemoNSF: A Multi-task Demonstration-based Generative Framework for Noisy Slot Filling Task (2023.findings-emnlp)

Challenge:	Evaluations of large language models (LLMs) indicate that such assessments are inconsistent and in many cases less accurate than dedicated condition-specific models with established psychometric validity.
Approach:	They propose a multi-outcome modeling and adaptive question-asking framework for simultaneous, multidimensional mental health screening that integrates language responses with item response theory and factor analysis.
Outcome:	Empirical results show that MAQuA reduces the number of assessment questions required for score stabilization by 50–87% compared to random ordering.

Copied to clipboard

Guanting Dong, Tingfeng Hui, Zhuoma GongQue, Jinxu Zhao, Daichi Guo, Gang Zhao, Keqing He, Weiran Xu

COPR: Continual Human Preference Learning via Optimal Policy Regularization (2025.findings-acl)

Challenge:	Recent prompt-based generative frameworks have shown impressive capabilities in sequence labeling tasks.
Approach:	They propose a multi-task demonstration-based generative framework for noisy slot filling that captures input perturbations at different granularities.
Outcome:	The proposed framework outperforms baseline methods and achieves strong generalization.

Copied to clipboard

Han Zhang, Lin Gui, Yu Lei, Yuanzhao Zhai, Yehong Zhang, Zhuo Zhang, Yulan He, Hui Wang, Yue Yu, Kam-Fai Wong, Bin Liang, Ruifeng Xu

Data Poisoning for In-context Learning (2025.findings-naacl)

Challenge:	Reinforcement Learning from Human Feedback (RLHF) is effective for aligning Large Language Models with human preferences, but its complex process limits its ability to continually learn human feedback.
Approach:	They propose a non-RL offline method to convert historical optimal policies into optimization constraints when continually learning new preferences.
Outcome:	The proposed method outperforms strong CL baselines in terms of reward-based evaluations and human assessment.

Copied to clipboard

Pengfei He, Han Xu, Yue Xing, Hui Liu, Makoto Yamada, Jiliang Tang

Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts (2026.acl-long)

Challenge:	In-context learning (ICL) has emerged as a capability of large language models (LLMs) but there is limited understanding of its vulnerability against data poisoning attacks.
Approach:	They propose an attack method that exploits ICL’s unique learning mechanisms by identifying discrete text perturbations that influence LLM hidden states.
Outcome:	The proposed attack method exploits ICL’s learning mechanisms by identifying discrete text perturbations that influence LLM hidden states.

Copied to clipboard

Haolei Xu, Haiwen Hong, Hongxing Li, Rui Zhou, Yang Zhang, Longtao Huang, Hui Xue, Yongliang Shen, Weiming Lu, Yueting Zhuang

EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning (2026.acl-long)

Challenge:	Existing multimodal Mixture-of-Experts models accurately perceive image content yet fail in subsequent reasoning . Seeing but not thinking phenomenon is a puzzling phenomenon .
Approach:	They propose a routing-guided intervention method that enhances domain expert activation.
Outcome:	The proposed method achieves consistent improvements on visual reasoning tasks.

Copied to clipboard

Chuanrui Hu, Xingze Gao, Zuyi Zhou, Dannong Xu, Yi Bai, Xintong Li, Hui Zhang, Tong Li, Chong Zhang, Lidong Bing, Yafeng Deng

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

Challenge:	Existing memory systems for LLMs store isolated records and retrieve fragments . Existing systems store isolated data and fragments, limiting their ability to consolidate evolving experience and resolve conflicts.
Approach:	They propose an engram-inspired memory operating system that implements an 'engram'-inspired lifecycle for computational memory.
Outcome:	Experiments on LoCoMo, LongMemEval, and PersonaMeM-v2 show that EverMemeOS outperforms state-of-the-art methods on memory-augmented reasoning tasks.

Copied to clipboard

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

Mitigating Hallucinations in Multi-modal Large Language Models via Image Token Attention-Guided Decoding (2025.naacl-long)

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

Copied to clipboard

Xinhao Xu, Hui Chen, Mengyao Lyu, Sicheng Zhao, Yizhe Xiong, Zijia Lin, Jungong Han, Guiguang Ding

MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training (2025.acl-long)

Challenge:	Multi-modal large language models (MLLMs) generate plausible but incorrect content, resulting in hallucinations . recent advances in MLLM technology have demonstrated their outstanding performance in a variety of visual tasks, such as object detection.
Approach:	They propose a plug-and-play method which leverages MLLMs’ internal representations to mitigate hallucinations by analyzing input and output tokens.
Outcome:	The proposed method exploits MLLMs’ internal representations to mitigate hallucinations.

Copied to clipboard

Hui Huang, Jiaheng Liu, Yancheng He, Shilong Li, Bing Xu, Conghui Zhu, Muyun Yang, Tiejun Zhao

Syntactically Diverse Adversarial Network for Knowledge-Grounded Conversation Generation (2021.findings-emnlp)

Challenge:	Existing methods for complex instruction-following with elaborate constraints rely on a weaker model, especially GPT-4, limiting their application.
Approach:	They propose a Multi-granularity Self-Contrastive Training framework to improve instruction alignment without relying on a stronger model.
Outcome:	The proposed framework improves instruction-following with elaborate constraints without external supervision on coarse and fine granularity.

Copied to clipboard

Fuwei Cui, Hui Di, Hongjie Ren, Kazushige Ouchi, Ze Liu, Jinan Xu

Dialogue Systems & Conversational Agents

Challenge:	Existing conversation models produce meaningless and generic responses, which significantly reduce the user experience.
Approach:	They propose to fuse knowledge to improve informativeness and adopt latent variables to enhance the diversity of responses.
Outcome:	The proposed model can generate syntactically diverse and knowledge-accurate responses while maintaining the knowledge accuracy.

Select2Reason: Efficient Instruction-Tuning Data Selection for Long-CoT Reasoning (2026.findings-acl)

Copied to clipboard

Cehao Yang, Xueyuan Lin, Xiaojun Wu, Chengjin Xu, Xuhui Jiang, Honghao Liu, Hui Xiong, Jian Guo

AgentGC: Evolutionary Learning-based Lossless Compression for Genomics Data with LLM-driven Multiple Agent (2026.findings-acl)

Challenge:	Large reasoning models exhibit human-like behaviors such as exploration, verification, reflection, and correction.
Approach:	They propose a supervised fine-tuning framework for long chain-of-thoughts reasoning . they leverage a difficulty-aware reward model to estimate the learning value of questions .
Outcome:	The proposed framework performs fine-tuning on large reasoning models on 10% of the data selected.

Copied to clipboard

Sun Hui, Ding Yanfeng, Huidong Ma, Chang Xu, Keyan Jin, Lizheng Zu, Cheng Zhong, Xiaoguang Liu, Gang Wang, Wentong Cai

Cognitive Modeling

Challenge:	Lossless compression has made significant advancements in Genomics Data storage, sharing and management.
Approach:	They propose a novel agent-based GD Compressor with 3 layers with a multi-agent named Leader and Worker.
Outcome:	The proposed method improves on existing methods with low-level modeling and limited adaptability and user-unfriendly interface.

InteMATs: Integrating Granularity-Specific Multilingual Adapters for Cross-Lingual Transfer (2023.findings-emnlp)

Copied to clipboard

Meizhen Liu, Xu Guo, He Jiakai, Jianye Chen, Fengyu Zhou, Siu Hui

Iterative Constrained Back-Translation for Unsupervised Domain Adaptation of Machine Translation (2022.coling-1)

Challenge:	Existing work relies on full-model fine-tuning on large parallel datasets to enhance cross-lingual alignment of MLLMs.
Approach:	They propose an approach that integrates multilingual adapters trained on texts of different levels of granularity into multilingual models.
Outcome:	The proposed approach improves the performance of multilingual language models on low-resource languages.

Copied to clipboard

Hongxiao Zhang, Hui Huang, Jiale Gao, Yufeng Chen, Jinan Xu, Jian Liu

Text Generation

Challenge:	Existing back-translation methods focus on in-domain lexical knowledge, which may lead to poor translation of unseen in- domain words.
Approach:	They propose an iterative constrained back-translation method to incorporate in-domain lexical knowledge into synthetic parallel data from BT.
Outcome:	The proposed method improves the BLEU score by up to 3.08 on four domains.

Extending LLM Context Window with Adaptive Grouped Positional Encoding: A Training-Free Method (2025.acl-long)

Copied to clipboard

Xinhao Xu, Jiaxin Li, Hui Chen, Zijia Lin, Jungong Han, Guiguang Ding

FEDLEGAL: The First Real-World Federated Learning Benchmark for Legal NLP (2023.acl-long)

Challenge:	Existing long-context training data is scarce and requires substantial GPU resources for training.
Approach:	They propose a training-free plug-and-play method to enhance long-context understanding in existing large language models.
Outcome:	The proposed method outperforms existing LLMs on various tasks and surpasses baseline methods.

Copied to clipboard

Zhuo Zhang, Xiangjing Hu, Jingyuan Zhang, Yating Zhang, Hui Wang, Lizhen Qu, Zenglin Xu

LoRE: Enhancing Search Relevance with Progressive Chain-of-Thought and Preference Alignment (2026.findings-acl)

Challenge:	federated learning (FL) is a promising technique for preserving data privacy . however, there is no work on applying FL to legal NLP .
Approach:	They propose to use federated learning to train models in a collaborative way without sharing data . they propose to test the FL benchmark on real-world legal data from Chinese courts .
Outcome:	The proposed benchmark combines five legal NLP tasks and one privacy task on Chinese courts.

Copied to clipboard

Chenji Lu, Zhuo Chen, Hui Zhao, Zhiyuan Zeng, Gang Zhao, Junjie Ren, null Lihaoran, Songyan Liu, Pengjie Wang, Chuan Yu, Jian Xu, Bo Zheng

SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains (2025.naacl-long)

Challenge:	E-commerce search relevance is a critical component of retrieval systems.
Approach:	They propose a large-generative model for search relevance that trains reasoning knowledge, multi-modal understanding and rule awareness into three core competencies.
Outcome:	The proposed model outperforms GPT-5 in Macro-F1 and achieves 27% online gain.

Copied to clipboard

Ran Xu, Hui Liu, Sreyashi Nag, Zhenwei Dai, Yaochen Xie, Xianfeng Tang, Chen Luo, Yang Li, Joyce C. Ho, Carl Yang, Qi He

Natural Language Interfaces

Challenge:	Retrieval-augmented generation (RAG) enhances the question answering abilities of large language models (LLMs) however, adapting general-purpose RAG systems to specialized fields poses unique challenges due to distribution shifts and limited access to domain-specific data.
Approach:	They propose a method that equips large language models with joint capabilities of question answering and question generation for domain adaptation.
Outcome:	Experiments on 11 datasets across three different domains verify the efficacy of SimRAG over baselines by 1.2%–8.6%.

On the Generalization of Training-based ChatGPT Detection Methods (2024.findings-emnlp)

Copied to clipboard

Han Xu, Jie Ren, Pengfei He, Shenglai Zeng, Yingqian Cui, Amy Liu, Hui Liu, Jiliang Tang

How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities (2026.acl-long)

Challenge:	Existing studies show that training-based methods are ineffective to detect LLM generated texts from unseen tasks or topics which are not collected during training.
Approach:	They propose to train classification models to distinguish LLMs from human texts by a distribution shift caused by prompts, text lengths, topics, and language tasks.
Outcome:	The proposed methods can detect LLMs from black-box models, but they suffer from distribution shifts due to a wide range of factors, including prompts, text lengths, topics, and language tasks.

Copied to clipboard

Ziwen Xu, Kewei Xu, Haoming Xu, Haiwen Hong, Longtao Huang, Hui Xue, Ningyu Zhang, Yongliang Shen, Guozhou Zheng, Huajun Chen, Shumin Deng

HFT: Half Fine-Tuning for Large Language Models (2025.acl-long)

Challenge:	Large language models (LLMs) are increasingly deployed in socially sensitive domains, yet their unpredictable behaviors pose significant risks.
Approach:	They propose a hierarchical benchmark for evaluating LLM controllability across three domains: language features, sentiment, and personality.
Outcome:	The proposed framework offers a principled and interpretable framework for safe and controllable LLM behavior serving as a foundation for future research.

Copied to clipboard

Tingfeng Hui, Zhenyu Zhang, Shuohuan Wang, Weiran Xu, Yu Sun, Hua Wu

Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (2024.emnlp-main)

Challenge:	Large language models (LLMs) with one or more fine-tuning phases can unlock various capabilities, but can be catastrophic forgetting during sequential training.
Approach:	They propose a method to regularly reset partial parameters to mitigate forgetting issues by using half fine-tuning instead of full fine-uning.
Outcome:	The proposed approach reduces the risk of catastrophic forgetting during training and the parametric knowledge lost during training may be overwhelmed by incoming training data.

Copied to clipboard

Yuping Lin, Pengfei He, Han Xu, Yue Xing, Makoto Yamada, Hui Liu, Jiliang Tang

CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference (2025.acl-long)

Challenge:	Large language models (LLMs) are susceptible to a type of attack known as jailbreaking, which misleads LLMs to output harmful contents.
Approach:	They propose to leverage hidden representations into existing jailbreak targets to move the attacks along the acceptance direction.
Outcome:	The proposed methods are validated using the objective of existing jailbreak attacks.

Copied to clipboard

Jinglong Luo, Guanzhong Chen, Yehong Zhang, Shiyu Liu, Hui Wang, Yue Yu, Xun Zhou, Yuan Qi, Zenglin Xu

EcomScriptBench: A Multi-task Benchmark for E-commerce Script Planning via Step-wise Intention-Driven Product Association (2025.acl-long)

Challenge:	Existing privacy-preserving Transformer Inference frameworks suffer from high computational overhead and performance losses.
Approach:	They propose a framework that integrates random permutations and SMPC to address the "impossible trinity" CENTAUR resists diverse data reconstruction attacks and boosts inference speed by 5.030.4 times .
Outcome:	CENTAUR achieves an unprecedented balance between privacy, efficiency, and performance.

Copied to clipboard

Weiqi Wang, Limeng Cui, Xin Liu, Sreyashi Nag, Wenju Xu, Chen Luo, Sheikh Muhammad Sarwar, Yang Li, Hansu Gu, Hui Liu, Changlong Yu, Jiaxin Bai, Yifan Gao, Haiyang Zhang, Qi He, Shuiwang Ji, Yangqiu Song

Efficient Knowledge Infusion via KG-LLM Alignment (2024.findings-acl)

Challenge:	Goal-oriented script planning is used by humans to plan for typical activities . however, this capability remains underexplored due to several challenges .
Approach:	They propose a framework that enables product-enriched scripts by associating products with each step based on the semantic similarity between the actions and their purchase intentions.
Outcome:	The proposed framework can generate product-enriched scripts from 2.4 million scripts . human annotations are conducted to provide gold labels for a sampled subset .

Copied to clipboard

Zhouyu Jiang, Ling Zhong, Mengshu Sun, Jun Xu, Rui Sun, Hui Cai, Shuhan Luo, Zhiqiang Zhang

Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data (2025.emnlp-main)

Challenge:	Existing methods for knowledge infusion face knowledge mismatch and poor information compliance of LLMs with knowledge graphs.
Approach:	They propose a three-stage alignment strategy to enhance the LLM's capability to utilize information from knowledge graphs.
Outcome:	The proposed method outperforms baselines on biomedical question-answering datasets and outperformed existing methods.

Copied to clipboard

Shenglai Zeng, Jiankun Zhang, Pengfei He, Jie Ren, Tianqi Zheng, Hanqing Lu, Han Xu, Hui Liu, Yue Xing, Jiliang Tang

MPVStance: Mitigating Hallucinations in Stance Detection with Multi-Perspective Verification (2025.acl-long)

Challenge:	Existing literature suggests that RAG systems may face privacy issues when the retrieval process involves private data.
Approach:	They propose a two-stage synthetic data generation paradigm that uses attributes to preserve contextual information from the original data.
Outcome:	The proposed approach preserves key contextual information from the original data while reducing privacy risks.

Copied to clipboard

ZhaoDan Zhang, Zhao Zhang, Jin Zhang, Hui Xu, Xueqi Cheng

Flexibly Utilize Memory for Long-Term Conversation via a Fragment-then-Compose Framework (2025.emnlp-main)

Challenge:	despite advances in large language models, challenges persist due to hallucination-models generating inaccurate content.
Approach:	They propose a framework that integrates multi-perspective verification with Retrieval-Augmented Generation to address these challenges.
Outcome:	The proposed method outperforms existing models on the SemEval-2016 and VAST datasets.

Copied to clipboard

Cai Ke, Yiming Du, Bin Liang, Yifan Xiang, Lin Gui, Zhongyang Li, Baojun Wang, Yue Yu, Hui Wang, Kam-Fai Wong, Ruifeng Xu

Dialogue Systems & Conversational Agents

Challenge:	Large language models extract useful information from conversation history to enhance the response in long-term conversations.
Approach:	They propose a Fragment-then-Compose framework to optimize memory utilization for long-term open-domain conversation.
Outcome:	The proposed framework can be used to extract useful information from conversation history . it can be adapted to different situations and improve response generation .

Dual Fixed-Size Ordinally Forgetting Encoding (FOFE) for Competitive Neural Language Models (D18-1)

Copied to clipboard

Sedtawut Watcharawittayakul, Mingbin Xu, Hui Jiang

Enhancing Multimodal Named Entity Recognition through Adaptive Mixup Image Augmentation (2025.coling-main)

Challenge:	In this paper, we propose a new approach to employ the fixed-size ordinally-forgetting encoding (FOFE) in neural languages modelling, called dual-FOFE.
Approach:	They propose a new approach to employ the fixed-size ordinally-forgetting encoding (FOFE) in neural languages modelling, called dual-FOFE.
Outcome:	The proposed method significantly reduces the complexity and improves perplexity by 10% over the original FOFE model.

Copied to clipboard

Bo Xu, Haiqi Jiang, Jie Wei, Hongyu Jing, Ming Du, Hui Song, Hongya Wang, Yanghua Xiao

WenetSpeech-Wu: Datasets, Benchmarks, and Models for a Unified Chinese Wu Dialect Speech Processing Ecosystem (2026.findings-acl)

Challenge:	Current named entity recognition methods struggle with text-image mismatch problem due to a lack of visual context.
Approach:	They propose an adaptive mixup image augmentation method that generates augmented images based on matching score between text and image .
Outcome:	The proposed method can be integrated into existing models and demonstrate consistent performance improvements.

Copied to clipboard

Chengyou Wang, Mingchen Shao, Jingbin Hu, Zeyu Zhu, Hongfei Xue, Bingshen Mu, Xin Xu, Xingyi Duan, Binbin Zhang, Zhu Pengcheng, Chuang Ding, Xiaojun Zhang, Hui Bu, Lei Xie

Self-Evaluation of Large Language Model based on Glass-box Features (2024.findings-emnlp)

Challenge:	despite its linguistic significance, the Wu dialect of Chinese has long been hindered by the lack of large-scale speech data, standardized evaluation benchmarks, and publicly available models.
Approach:	They propose to use WenetSpeech-Wu as a large-scale, multi-dimensionally annotated open-source speech corpus for the Wu dialect of Chinese.
Outcome:	The proposed dataset includes 8,000 hours of speech data and strong open-source models . the proposed dataset is competitive and empirically validated .

Copied to clipboard

Hui Huang, Yingqi Qu, Jing Liu, Muyun Yang, Bing Xu, Tiejun Zhao, Wenpeng Lu

Different Data, Different Modalities! Reinforced Data Splitting for Effective Multimodal Information Extraction from Social Media Posts (2022.coling-1)

Challenge:	Existing evaluation methods rely on external evaluators, focusing on training and prompting strategies, but model-aware glass-box features are overlooked.
Approach:	They propose to use model-aware glass-box features to evaluate an LLM's output.
Outcome:	The proposed model-aware features are reliable quality indicators for self-evaluation on public benchmarks.

Copied to clipboard

Bo Xu, Shizhou Huang, Ming Du, Hongya Wang, Hui Song, Chaofeng Sha, Yanghua Xiao

Information Extraction & Text Mining

Challenge:	Recent multimodal information extraction approaches overestimate the significance of images.
Approach:	They propose a general data splitting strategy to divide social media posts into two sets to achieve better performance under information extraction models of the corresponding modalities.
Outcome:	The proposed method outperforms existing models on two different multimodal information extraction tasks.

CLLE: A Benchmark for Continual Language Learning Evaluation in Multilingual Machine Translation (2022.findings-emnlp)

Copied to clipboard

Han Zhang, Sheng Zhang, Yang Xiang, Bin Liang, Jinsong Su, Zhongjian Miao, Hui Wang, Ruifeng Xu

Multilinguality

Challenge:	Existing benchmarks for Continual Language Learning (CLL) are limited due to the complexity of the task and the lack of unified benchmarks.
Approach:	They propose a Continual Language Learning Evaluation benchmark CLLE in multilingual translation.
Outcome:	The proposed method is effective when compared with other strong benchmarks.

CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark (2022.acl-long)

Copied to clipboard

Ningyu Zhang, Mosha Chen, Zhen Bi, Xiaozhuan Liang, Lei Li, Xin Shang, Kangping Yin, Chuanqi Tan, Jian Xu, Fei Huang, Luo Si, Yuan Ni, Guotong Xie, Zhifang Sui, Baobao Chang, Hui Zong, Zheng Yuan, Linfeng Li, Jun Yan, Hongying Zan, Kunli Zhang, Buzhou Tang, Qingcai Chen

Challenge:	a new benchmark for biomedical language understanding is being developed in Chinese . most benchmarks are limited to English, which makes it difficult to replicate success in other languages.
Approach:	They propose to use Chinese biomedical language understanding evaluation benchmarks to evaluate Chinese models.
Outcome:	The proposed benchmarks show that the current models perform worse than the human ceiling.

MoEC: A Memory-Routed Mixture-of-Experts Controller for Adaptive Minecraft Control (2026.acl-long)

Copied to clipboard

Hui Wu, Chao Xu, Jianghui Wang, Ziqiong Liu, Dong Li, Yiwei Dai, Emad Barsoum

Saliency-based Multi-View Mixed Language Training for Zero-shot Cross-lingual Classification (2021.findings-emnlp)

Challenge:	Existing systems rely on a monolithic policy to execute subgoals across varying contexts, causing inconsistent outcomes and scaling only partially mitigates.
Approach:	They propose a memory-routed mixtureof-experts controller for Adaptive Minecraft Control that routes via a subgoal-indexed expert memory and regulates capacity through failure-triggered expert growth and redundancy-aware consolidation.
Outcome:	The proposed controller shows significant gains in adaptability, robustness, and execution consistency over strong baselines.

Copied to clipboard

Siyu Lai, Hui Huang, Dong Jing, Yufeng Chen, Jinan Xu, Jian Liu

Multilinguality

Challenge:	Recent multilingual pre-trained models have been demonstrated effective in many cross-lingual tasks.
Approach:	They propose a framework that leverages code-switched data with multi-view learning to fine-tune XLM-R.
Outcome:	The proposed model achieves state-of-the-art on zero-shot cross-lingual sentiment classification and dialogue state tracking tasks.

Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics (2026.acl-long)

Copied to clipboard

Ziwen Xu, Chenyan WU, Hengyu Sun, Haiwen Hong, Mengru Wang, Yunzhi Yao, Longtao Huang, Hui Xue, Shumin Deng, Zhixuan Chu, Huajun Chen, Ningyu Zhang

GenTool: Enhancing Tool Generalization in Language Models through Zero-to-One and Weak-to-Strong Simulation (2025.findings-acl)

Challenge:	Methods for controlling large language models (LLMs) are often studied in isolation, obscuring connections and making comparison difficult.
Approach:	They propose a preference-utility analysis that separates control effects into preference and utility, and measures both on a shared log-odds scale using polarity-paired contrastive examples.
Outcome:	The proposed approach improves preference while preserving utility.

Copied to clipboard

Jie He, Jennifer Neville, Mengting Wan, Longqi Yang, Hui Liu, Xiaofeng Xu, Xia Song, Jeff Z. Pan, Pei Zhou