Papers by Hui Sun

Efficient Learned Data Compression via Dual-Stream Feature Decoupling (2026.acl-long)

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

Huidong Ma, Xinyan Shi, Sun Hui, Xiaofei Yue, Xiaoguang Liu, Gang Wang, Wentong Cai

Green & Sustainable NLP

Challenge:	Learned data compression has achieved superior compression ratios, but balancing precise probability modeling with system efficiency remains challenging.
Approach:	They propose a Dual-Stream Multi-Scale Decoupler that disentangles local and global contexts to replace deep serial processing with shallow parallel streams.
Outcome:	The proposed method achieves state-of-the-art performance in both compression ratio and throughput while maintaining the lowest latency and memory usage.

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.

Privacy Risks of Intermediate Representations: Attribute Inference in Distributed LLM Inference (2026.findings-acl)

Copied to clipboard

Yang Lyu, Jin Cao, Yang Xiao, Zhe Sun, Ben Niu, Fenghua Li, Hui LI

Responsible & Trustworthy NLP

Challenge:	Distributed LLMs avoid raw inputs by transmitting intermediate hidden states, a practice widely assumed to preserve privacy.
Approach:	They propose a distributed inference framework that transmits intermediate hidden states to avoid sending raw inputs by exposing sensitive user attributes.
Outcome:	The proposed approach achieves Top-1 accuracy of 0.997 on CMS, 0.980 on Skytrax, and 0.986 on ECHR.

A Lifelong Multilingual Multi-granularity Semantic Alignment Approach via Maximum Co-occurrence Probability (2024.lrec-main)

Copied to clipboard

Xin Liu, Hongwei Sun, Shaojie Dai, Bo Lv, Youcheng Pan, Hui Wang, Yue Yu

Multilinguality

Challenge:	Existing methods to mask and predict tokens in multilingual text limit multilingual interaction .
Approach:	They propose a lifelong multilingual multi-granularity semantic alignment approach which continuously extracts massive aligned linguistic units from noisy data via a maximum co-occurrence probability algorithm.
Outcome:	The proposed approach improves translation performance on WMT14 18 benchmarks in twelve directions.

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

Copied to clipboard

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

STELLA: A Multimodal LLM for Protein Functional Annotation via Unified Sequence-Structure Encoding (2026.findings-acl)

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

Hongwang Xiao, Wenjun Lin, Xi Chen, Hui Wang, Kai Chen, Jiashan Li, Yuancheng Sun, Sicheng Dai, Boya Wu, Qiwei Ye

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

Challenge:	a multimodal protein language model (LLM) integrates sequence, structure, and function into functional annotation.
Approach:	They propose a multimodal protein language model that synergistically aligns bimodal representations with the textual modality to advance protein functional annotation.
Outcome:	The proposed model synergizes bimodal representations with the textual modality to advance protein functional annotation.

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

BERT-QE: Contextualized Query Expansion for Document Re-ranking (2020.findings-emnlp)

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

Zhi Zheng, Kai Hui, Ben He, Xianpei Han, Le Sun, Andrew Yates

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

Challenge:	Existing methods to expand query use pseudo relevance feedback (PRF) but they are under-equipped to evaluate the relevance of information pieces used for expansion.
Approach:	They propose a query expansion model that leverages the BERT model to select relevant document chunks for expansion.
Outcome:	The proposed model significantly outperforms existing models on the TREC Robust04 and GOV2 test collections.

Copied to clipboard

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

Dialogue Systems & Conversational Agents

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.

WebUncertainty: Dual-Level Uncertainty Driven Planning and Reasoning For Autonomous Web Agent (2026.findings-acl)

Copied to clipboard

Lingfeng Zhang, Yongan Sun, Jinpeng Hu, Hui Ma, Ying Yang, Kuien Liu, Zenglin Shi, Meng Wang

Reasoning

Challenge:	Existing web agents struggle with complex tasks due to rigid planning strategies and hallucination-prone reasoning.
Approach:	They propose a task-uncertainty-driven Adaptive Planning Mechanism that adaptively selects planning modes to navigate unknown environments.
Outcome:	The proposed framework performs better on the WebArena and WebVoyager benchmarks than existing frameworks.

How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training (2025.findings-acl)

Copied to clipboard

Yixin Ou, Yunzhi Yao, Ningyu Zhang, Hui Jin, Jiacheng Sun, Shumin Deng, Zhenguo Li, Huajun Chen

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

Challenge:	Large Language Models (LLMs) have exceptional capabilities in knowledge-intensive tasks . however, they struggle with knowledge updates due to dynamic nature of world knowledge .
Approach:	They propose to identify computational subgraphs that facilitate knowledge storage and processing . they also identify a phase shift from formation to optimization in LLMs .
Outcome:	The proposed model can capture factual knowledge from pre-training corpus and encapsulate it as extensive parametric knowledge.

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.

The Right Time Matters: Data Arrangement Affects Zero-Shot Generalization in Instruction Tuning (2025.findings-acl)

Copied to clipboard

Bingxiang He, Ning Ding, Cheng Qian, Jia Deng, Ganqu Cui, Lifan Yuan, Haiwen Hong, Huan-ang Gao, Longtao Huang, Hui Xue, Huimin Chen, Zhiyuan Liu, Maosong Sun

Reverse Chain: A Generic-Rule for LLMs to Master Multi-API Planning (2024.findings-naacl)

Challenge:	Existing work on instruction tuning has focused on task level, without considering that tasks are artificially defined and, to LLMs, merely consist of tokens and representations.
Approach:	They propose a training data arrangement framework that allows for continual learning and loss reduction.
Outcome:	The proposed framework promotes continual learning and loss reduction on unseen tasks.

Copied to clipboard

Yinger Zhang, Hui Cai, Xierui Song, Yicheng Chen, Rui Sun, Jing Zheng

Enhancing the Prototype Network with Local-to-Global Optimization for Few-Shot Relation Extraction (2025.findings-naacl)

Challenge:	Existing approaches to enable large language models to implement function calling are limited in their tool-use capabilities.
Approach:	They propose a controllable, target-driven approach to empower LLMs to operate external APIs only via prompts.
Outcome:	The proposed approach limits LLMs to executing simple tasks, e.g., API Selection and Argument Completion.

Copied to clipboard

Hui Sun, Rongxin Chen

Information Extraction & Text Mining

Challenge:	Relation Extraction (RE) is a task that aims to extract semantic relationships from unstructured text.
Approach:	They propose a local optimization strategy that indirectly optimizes the prototypical networks by optimizing the other information contained within the prototypes.
Outcome:	The proposed model improves on the FewRel 1.0 and FewRela 2.0 datasets.

History Semantic Graph Enhanced Conversational KBQA with Temporal Information Modeling (2023.acl-long)

Copied to clipboard

Hao Sun, Yang Li, Liwei Deng, Bowen Li, Binyuan Hui, Binhua Li, Yunshi Lan, Yan Zhang, Yongbin Li

Natural Language Interfaces

Challenge:	Existing methods for conversational KBQA assume the independence of utterances and model them in isolation.
Approach:	They propose a History Semantic Graph Enhanced KBQA model that models long-range semantic dependencies in conversation history while maintaining low computational cost.
Outcome:	The proposed model outperforms baselines on a widely used question type dataset.

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

Copied to clipboard

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

Benchmarking Hallucination in Large Language Models Based on Unanswerable Math Word Problem (2024.lrec-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

YuHong Sun, Zhangyue Yin, Qipeng Guo, Jiawen Wu, Xipeng Qiu, Hui Zhao

Reasoning

Challenge:	Large language models (LLMs) are highly effective in various natural language processing tasks, but can produce unreliable conjectures in ambiguous contexts, which is known as hallucination.
Approach:	They propose a method to evaluate LLM hallucination in Question Answering based on the unanswerable math word problem (UMWP) . they combine text similarity and mathematical expression detection to determine whether LLM considers the question unanswered.
Outcome:	The proposed method combines text similarity and mathematical expression detection to determine whether the LLM considers the question unanswerable.

EmotionTalk: An Interactive Chinese Multimodal Emotion Dataset With Rich Annotations (2026.findings-acl)

Copied to clipboard

Haoqin Sun, Jinghua Zhao, Xuechen Wang, Shiwan Zhao, Jiaming Zhou, Hui Wang, Xi Yang, Yequan Wang, Yonghua Lin

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

Challenge:	Existing datasets face issues such as low quality, limited scale, and incomplete modalities, hindering model performance.
Approach:	They propose to use Chinese multimodal datasets to capture authentic emotional interplay from 19 professional actors.
Outcome:	The EmotionTalk dataset spans 23.6 hours of dyadic conversations across diverse scenarios.

Copied to clipboard

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

RoChBert: Towards Robust BERT Fine-tuning for Chinese (2022.findings-emnlp)

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

Zihan Zhang, Jinfeng Li, Ning Shi, Bo Yuan, Xiangyu Liu, Rong Zhang, Hui Xue, Donghong Sun, Chao Zhang

Unraveling the Mechanics of Learning-Based Demonstration Selection for In-Context Learning (2025.acl-long)

Challenge:	Pre-trained language models (e.g., BERT) have been proved vulnerable to adversarial texts.
Approach:	They propose to fuse Chinese phonetic and glyph features into pre-trained models by using a more comprehensive adversarial graph.
Outcome:	The proposed framework outperforms existing methods in significant ways on a wide range of tasks while remaining accurate on benign texts.

Copied to clipboard

Hui Liu, Wenya Wang, Hao Sun, Chris Xing Tian, Chenqi Kong, Xin Dong, Haoliang Li

AdaTP: Attention-Debiased Token Pruning for Video Large Language Models (2025.findings-emnlp)

Challenge:	Recent learning-based demonstration selection methods have proven beneficial to in-context learning (ICL) by choosing more useful exemplars.
Approach:	They propose two methods to capture task-agnostic similarities between input and output of LLMs.
Outcome:	The proposed methods integrate task-agnostic similarities of different levels between input and output of exemplars and test cases to eliminate costly data collection.

Copied to clipboard

Fengyuan Sun, Leqi Shen, Hui Chen, Sicheng Zhao, Jungong Han, Guiguang Ding

S2SQL: Injecting Syntax to Question-Schema Interaction Graph Encoder for Text-to-SQL Parsers (2022.findings-acl)

Challenge:	Existing visual token compression methods rely on attention scores but have inherent biases . global and local attention biased scores cause excessive computational overhead .
Approach:	They propose a token pruning pipeline that targets global and local attention biases . the pipeline is designed to reduce computational overhead of Video Large Language Models based on visual tokens compiled from multiple video frames .
Outcome:	The proposed method significantly reduces the computational overhead of Video Large Language Models while retaining the performance of vanilla models.

Copied to clipboard

Binyuan Hui, Ruiying Geng, Lihan Wang, Bowen Qin, Yanyang Li, Bowen Li, Jian Sun, Yongbin Li

DebugBench: Evaluating Debugging Capability of Large Language Models (2024.findings-acl)

Challenge:	Existing graph-based encoders for text-to-SQL do not model the syntax of natural language questions.
Approach:	They propose to inject Syntax to question-Schema graph encoder for text-to-SQL parsers and employ the decoupling constraint to induce diverse relational edge embedding.
Outcome:	The proposed approach outperforms all existing methods when pre-training models are used, resulting in a performance ranks first on the Spider leaderboard.

Copied to clipboard

Runchu Tian, Yining Ye, Yujia Qin, Xin Cong, Yankai Lin, Yinxu Pan, Yesai Wu, Hui Haotian, Liu Weichuan, Zhiyuan Liu, Maosong Sun

Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models (2025.acl-long)

Challenge:	Large language models (LLMs) have demonstrated exceptional coding capabilities, but their debugging capabilities remain relatively unexplored.
Approach:	They propose a debugging benchmark consisting of 4,253 LLMs with four major bug categories and 18 minor types in C++, Java, and Python.
Outcome:	The proposed benchmark covers four major bug categories and 18 minor types in C++, Java, and Python.

Copied to clipboard

Yancheng He, Shilong Li, Jiaheng Liu, Yingshui Tan, Weixun Wang, Hui Huang, Xingyuan Bu, Hangyu Guo, Chengwei Hu, Boren Zheng, Zhuoran Lin, Dekai Sun, Zhicheng Zheng, Wenbo Su, Bo Zheng

From Scores to Preferences: Redefining Evaluation Paradigm for Speech Quality Reward Modeling (2026.findings-acl)

Challenge:	Current frontier models sometimes generate false outputs or answers that are not substantiated by evidence.
Approach:	They propose Chinese SimpleQA, a Chinese benchmark to evaluate LLMs' factuality . they focus on Chinese language over 6 major topics with 99 diverse subtopics .
Outcome:	The Chinese SimpleQA benchmark evaluates the factuality ability of LLMs . the questions and answers are short and easy-to-evaluate .

Copied to clipboard

Yifei Cao, Changhao Jiang, Jiabao Zhuang, Jiajun Sun, Ming Zhang, Zhiheng Xi, Hui Li, Shihan Dou, Yuran Wang, Yunke Zhang, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang

TDNN: A Two-stage Deep Neural Network for Prompt-independent Automated Essay Scoring (P18-1)

Challenge:	Experimental results show that the MOS-aware GRM significantly improves fine-grained speech quality discrimination.
Approach:	They propose a MOS-aware reward model that incorporates MOS gap into reward function during reinforcement learning.
Outcome:	The proposed model significantly improves fine-grained speech quality discrimination.

Copied to clipboard

Cancan Jin, Ben He, Kai Hui, Le Sun

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

Challenge:	Existing automated essay scoring (AES) models rely on rated essays for the target prompt as training data.
Approach:	They propose a shallow deep neural network to learn a prompt-dependent rating model using rated essays for non-target prompts as training data.
Outcome:	The proposed model improves on the standard ASAP dataset.

Copied to clipboard

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

Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging (2025.acl-long)

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

Tingfeng Hui, Zhenyu Zhang, Shuohuan Wang, Yu Sun, Hua Wu, Sen Su

Responsible & Trustworthy NLP

Challenge:	Existing methods for tuning large language models from dense to MoE face significant data requirements and require large-scale post-training.
Approach:	They propose an upcycling instruction tuning approach for tuning a dense pre-trained model into a MoE instruction model using genetic algorithm and parameter merging.
Outcome:	The proposed approach improves the performance of large language models with a small amount of seed data and improves their scaling.

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

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

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

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