Papers by Hui Huang

From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework (2023.findings-acl)

Challenge:	Existing methods to improve performance of large language models rely on additional training objectives or language-specific parameters.
Approach:	They propose a bidirectional language projection framework that enables efficient multilingual alignment and language shift using the intrinsic parameters.
Outcome:	The proposed framework improves performance of non-dominant languages and improves internal representations.

Copied to clipboard

Yangyi Chen, Hongcheng Gao, Ganqu Cui, Lifan Yuan, Dehan Kong, Hanlu Wu, Ning Shi, Bo Yuan, Longtao Huang, Hui Xue, Zhiyuan Liu, Maosong Sun, Heng Ji

Robustness in NLP

Challenge:	Existing models of robustness evaluation are incomprehensive, impractical, and invalid .
Approach:	They propose a framework for automatic robustness evaluation that shifts towards model-centric evaluation to further exploit the advantages of adversarial attacks.
Outcome:	The proposed framework is based on a model-centric evaluation protocol and a robustness evaluation protocol.

DAFNet: Dynamic Auxiliary Fusion for Sequential Model Editing in Large Language Models (2024.findings-acl)

Copied to clipboard

Taolin Zhang, Qizhou Chen, Dongyang Li, Chengyu Wang, Xiaofeng He, Longtao Huang, Hui Xue’, Jun Huang

PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit (2022.naacl-demo)

Challenge:	Large language models (LLMs) have shown impressive results, but still suffer from hallucination, i.e., the generation of false information.
Approach:	They propose a task of sequential model editing that aims to rectify mistakes continuously.
Outcome:	The proposed method significantly outperforms baselines in single-turn and sequential editing.

Copied to clipboard

Hui Zhang, Tian Yuan, Junkun Chen, Xintong Li, Renjie Zheng, Yuxin Huang, Xiaojie Chen, Enlei Gong, Zeyu Chen, Xiaoguang Hu, Dianhai Yu, Yanjun Ma, Liang Huang

Gradient Consistency-based Parameter Allocation for Multilingual Neural Machine Translation (2024.lrec-main)

Challenge:	PaddleSpeech is an open-source speech toolkit that supports speech-to-text and text-to speech tasks.
Approach:	They describe the design philosophy and core architecture of PaddleSpeech to support several essential speech-to-text and text-to speech tasks.
Outcome:	The proposed framework achieves competitive or state-of-the-art performance on various speech datasets and implements the most popular methods.

Copied to clipboard

Wenshuai Huo, Xiaocheng Feng, Yichong Huang, Chengpeng Fu, Hui Wang, Bing Qin

Revisiting Data Reconstruction Attacks on Real-world Dataset for Federated Natural Language Understanding (2024.lrec-main)

Challenge:	Multilingual neural machine translation models are often prone to parameter interference . a common problem is that the model compromises with the language diversity to find a solution .
Approach:	They propose a method that allocates parameters based on consistency between the gradients of the individual language and the average gradient.
Outcome:	The proposed method reduces parameter interference and improves translation quality.

Copied to clipboard

Zhuo Zhang, Jintao Huang, Xiangjing Hu, Jingyuan Zhang, Yating Zhang, Hui Wang, Yue Yu, Qifan Wang, Lizhen Qu, Zenglin Xu

KEHRL: Learning Knowledge-Enhanced Language Representations with Hierarchical Reinforcement Learning (2024.lrec-main)

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

Dongyang Li, Taolin Zhang, Longtao Huang, Chengyu Wang, Xiaofeng He, Hui Xue

Attn-GS: Attention-Guided Context Compression for Efficient Personalized LLMs (2026.acl-long)

Challenge:	General pre-trained language models (PLMs) leverage relation triples from knowledge graphs (KGs) and integrate external data sources into language models via self-supervised learning.
Approach:	They propose to learn Knowledge-Enhanced language representations with Hierarchical Reinforcement Learning (KEHRL) to detect positions for knowledge injection and integrate external knowledge into the model to avoid injecting inaccurate or irrelevant knowledge.
Outcome:	The proposed model can detect essential positions in texts for knowledge injection and integrate external knowledge into the model to avoid injecting inaccurate or irrelevant knowledge.

Copied to clipboard

Shenglai Zeng, Tianqi Zheng, Chuan Tian, Dante Everaert, Yau-Shian Wang, Yupin Huang, Michael J. Morais, Rohit Patki, Jinjin Tian, Xinnan Dai, Kai Guo, Monica Xiao Cheng, Hui Liu

Green & Sustainable NLP

Challenge:	Existing approaches to personalize large language models (LLMs) rely on heuristic methods to compress user profiles but they ignore how LLMs process and prioritize different profile components.
Approach:	They propose an attention-guided context compression framework that leverages attention feedback from a marking model to mark important personalization sentences and guides a compression model to generate task-relevant compressed user contexts.
Outcome:	The proposed framework outperforms baselines across tasks, token limits, and settings while reducing token usage by 50 times.

Error Classification of Large Language Models on Math Word Problems: A Dynamically Adaptive Framework (2025.findings-emnlp)

Copied to clipboard

Zhangyue Yin, YuHong Sun, Xuanjing Huang, Xipeng Qiu, Hui Zhao

Reasoning

Challenge:	Current error classification methods rely on static and predefined categories to capture error patterns.
Approach:	They propose a framework for automated dynamic error classification in mathematical reasoning that incorporates common error patterns as explicit guidance.
Outcome:	The proposed framework reduces human bias and fine-grained analysis of error patterns.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models (2026.findings-acl)

Copied to clipboard

Hengyuan Zhang, Zhihao Zhang, Ercong Nie, Mingyang Wang, Zunhai Su, Yiwei Wang, Qianli Wang, Shuzhou Yuan, Xufeng Duan, Qibo Xue, Zeping Yu, Chenming Shang, Xiao Liang, Jing Xiong, Hui Shen, Chaofan Tao, Zhengwu Liu, Senjie Jin, Zhiheng Xi, Dongdong Zhang, Sophia Ananiadou, Tao Gui, Ruobing Xie, Hayden Kwok-Hay So, Hinrich Schuetze, Xuanjing Huang, Qi Zhang, Ngai Wong

Explainability & Interpretability in NLP

Challenge:	Existing literature on mechanistic interpretation (MI) treats it as an observational science, leaving practical applications underexplored.
Approach:	They propose a survey structured around the pipeline to identify and improve MI models.
Outcome:	The proposed framework enables tangible improvements in Alignment, Capability, and Efficiency.

Temporal Scaling Law for Large Language Models (2025.emnlp-main)

Copied to clipboard

Yizhe Xiong, Xiansheng Chen, Xin Ye, Hui Chen, Zijia Lin, Haoran Lian, Zhenpeng Su, Wei Huang, Jianwei Niu, Jungong Han, Guiguang Ding

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 studies have found that the test loss of LLMs scales as power-laws with model size, computational budget, and dataset size.
Approach:	They propose a concept of Temporal Scaling Law to study test loss of LLMs . they break down test loss into fine-grained token positions and develop a dynamic hyperbolic-law .
Outcome:	The proposed model predicts the test loss of LLMs as the training steps scale up.

Copied to clipboard

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

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

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

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.

LDIR: Low-Dimensional Dense and Interpretable Text Embeddings with Relative Representations (2025.findings-acl)

Copied to clipboard

Yile Wang, Zhanyu Shen, Hui Huang

Explainability & Interpretability in NLP

Challenge:	Existing text embeddings with high dimensions are difficult to trace and interpret.
Approach:	They propose low-dimensional and interpretable text embeddings with relative representations that encode semantic meanings in a vector space where similar texts are close together in the representation space.
Outcome:	The proposed embeddings outperform existing models on multiple tasks with fewer dimensions and are lowdimensional and dense while maintaining interpretability.

TRELM: Towards Robust and Efficient Pre-training for Knowledge-Enhanced Language Models (2024.lrec-main)

Copied to clipboard

Junbing Yan, Chengyu Wang, Taolin Zhang, Xiaofeng He, Jun Huang, Wei Zhang, Longtao Huang, Hui Xue

STAR: SQL Guided Pre-Training for Context-dependent Text-to-SQL Parsing (2022.findings-emnlp)

Challenge:	Existing methods for incorporating external knowledge into language models do not prioritize learning embeddings for entity-related tokens.
Approach:	They propose a framework for incorporating external knowledge into pre-training models that utilize entity-related tokens.
Outcome:	The proposed framework reduces pre-training time by 50% and outperforms other KEPLMs in knowledge probing tasks and multiple knowledge-aware language understanding tasks.

Copied to clipboard

Zefeng Cai, Xiangyu Li, Binyuan Hui, Min Yang, Bowen Li, Binhua Li, Zheng Cao, Weijie Li, Fei Huang, Luo Si, Yongbin Li

Programming Languages in NLP

Challenge:	Extensive experiments show that STAR outperforms previous pre-training methods and ranks first on the leaderboard . text-to-SQL parsing aims to translate natural language (NL) questions into executable SQL queries .
Approach:	They propose a SQL guided pre-training framework STAR for context-dependent text-to-SQL parsing . they propose two objectives that explore context-dependence of NL utterances and SQL queries .
Outcome:	The proposed framework outperforms existing methods on two downstream benchmarks and ranks first on the leaderboard.

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety (2026.acl-long)

Copied to clipboard

Junxiao Yang, Haoran Liu, Jinzhe Tu, Jiale Cheng, Zhexin Zhang, Shiyao Cui, Jiaqi Weng, Jialing Tao, Hui Xue, Hongning Wang, Han Qiu, Minlie Huang

Challenge:	Large language models (LLMs) have demonstrated better safety performance in high-resource languages than in low-resourced languages.
Approach:	They propose language-agnostic semantic alignment (LASA) which anchors safety alignment directly in semantic bottlenecks.
Outcome:	The proposed approach significantly improves safety across all languages: average attack success rate drops from 24.7% to 2.8% on LLaMA-3.1-8B-Instruct and remains within 3–4% across Qwen2.5 and Qwend3 Instruct models (7B–32B).

ToxiCraft: A Novel Framework for Synthetic Generation of Harmful Information (2024.findings-emnlp)

Copied to clipboard

Zheng Hui, Zhaoxiao Guo, Hang Zhao, Juanyong Duan, Congrui Huang

Legal Fact Prediction: The Missing Piece in Legal Judgment Prediction (2025.emnlp-main)

Challenge:	Existing models for detecting harmful content lack diversity and quality of datasets.
Approach:	They propose a framework for synthesizing toxic information from social media datasets . their framework generates a wide variety of synthetic, yet remarkably realistic, examples of toxic information .
Outcome:	The proposed framework can generate a wide variety of synthetic, yet remarkably realistic, examples of toxic information.

Copied to clipboard

Junkai Liu, Yujie Tong, Hui Huang, Bowen Zheng, Yiran Hu, Peicheng Wu, Chuan Xiao, Makoto Onizuka, Muyun Yang, Shuyuan Zheng

Challenge:	Existing studies use legal facts to predict judgments, but legal facts are difficult to obtain in early stages of litigation.
Approach:	They propose a legal fact prediction task that takes evidence from trial as input to make predictions in the absence of ground-truth legal facts.
Outcome:	The proposed task can predict court rulings without ground-truth legal facts . the first benchmark dataset, LFPBench, is used to evaluate the task .

Out-of-Domain Intent Detection Considering Multi-Turn Dialogue Contexts (2024.lrec-main)

Copied to clipboard

Hao Lang, Yinhe Zheng, Binyuan Hui, Fei Huang, Yongbin Li

Sentiment Analysis

Challenge:	Existing methods for OOD intent detection are limited to single dialogue turns.
Approach:	They propose a context-aware OOD intent detection framework to model multi-turn contexts in OOD context detection tasks using unlabeled data.
Outcome:	The proposed framework improves the F1-OOD score by 29% on multi-turn OOD detection tasks compared to the previous best method.

Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models (2025.findings-acl)

Copied to clipboard

Yingqian Cui, Pengfei He, Jingying Zeng, Hui Liu, Xianfeng Tang, Zhenwei Dai, Yan Han, Chen Luo, Jing Huang, Zhen Li, Suhang Wang, Yue Xing, Jiliang Tang, Qi He

Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learning (2023.findings-acl)

Challenge:	Chain-of-Thought (CoT) reasoning has improved the performance of large language models (LLMs) however, the detailed reasoning process in CoT often incurs long generation times and high computational costs due to the inclusion of unnecessary steps.
Approach:	They propose a method to identify critical reasoning steps using perplexity as a measure of their importance.
Outcome:	The proposed method achieves a better balance between reasoning accuracy and efficiency of CoT.

Copied to clipboard

Ruixiang Tang, Dehan Kong, Longtao Huang, Hui Xue

Teaching According to Talents! Instruction Tuning LLMs with Competence-Aware Curriculum Learning (2025.findings-emnlp)

Challenge:	Large language models (LLMs) have shown great potential for in-context learning, but their robustness and performance on downstream tasks remains limited.
Approach:	They propose to examine the reliance of LLMs on shortcuts or spurious correlations within prompts for downstream tasks and find larger models are more likely to utilize shortcuts in prompts during inference.
Outcome:	The proposed model is “lazy learner” and more likely to use shortcuts in prompts during inference.

Copied to clipboard

Yangning Li, Tingwei Lu, Yinghui Li, Yankai Chen, Wei-Chieh Huang, Wenhao Jiang, Hui Wang, Hai-Tao Zheng, Philip S. Yu

SpanMlt: A Span-based Multi-Task Learning Framework for Pair-wise Aspect and Opinion Terms Extraction (2020.acl-main)

Challenge:	Efficient instruction tuning aims to enhance the ultimate performance of large language models (LLMs) current methods suffer from the curriculum rigidity, resulting in a fixed and potentially sub-optimal learning trajectory.
Approach:	a framework for efficient instruction tuning is proposed to address the issue of curriculum rigidity . current methods rely on static heuristic difficulty metrics and fail to adapt to evolving capabilities .
Outcome:	Efficient instruction tuning aims to enhance the ultimate performance of large language models . current methods suffer from the curriculum rigidity, resulting in a fixed learning trajectory .

Copied to clipboard

He Zhao, Longtao Huang, Rong Zhang, Quan Lu, Hui Xue

Sentiment Analysis

Challenge:	Aspect terms and opinion terms are key problems of fine-grained aspect-based sentiment analysis.
Approach:	They propose a method to extract aspect and opinion terms as pairs from a sentence . they use shared spans to extract the terms under supervision of span boundaries .
Outcome:	The proposed method outperforms state-of-the-art methods on both aspects and opinion terms extraction tasks.

OntoED: Low-resource Event Detection with Ontology Embedding (2021.acl-long)

Copied to clipboard

Shumin Deng, Ningyu Zhang, Luoqiu Li, Chen Hui, Tou Huaixiao, Mosha Chen, Fei Huang, Huajun Chen

Towards Multi-Document Question Answering in Scientific Literature: Pipeline, Dataset, and Evaluation (2025.findings-emnlp)

Challenge:	Existing methods to ED rely on training instances and ignore correlation of event types.
Approach:	They propose a process of event ontology population linking event instances to pre-defined event types in event ontoology and ontological embedding to address these problems.
Outcome:	The proposed framework can be applied to new unseen event types by establishing linkages to existing ones.

Copied to clipboard

Hui Huang, Julien Velcin, Yacine Kessaci

Question Answering

Challenge:	Existing QA systems do not strictly enforce cross-document synthesis or exploit the explicit inter-paper structure that links sources.
Approach:	They propose a pipeline methodology for constructing a multi-document academic QA dataset . they detect communities based on citation networks and leverage Large Language Models .
Outcome:	The proposed method generates QA pairs related to multi-document content automatically and forms coherent communities based on citation networks and large language models.

ProMedical: Hierarchical Fine-Grained Criteria Modeling for Medical LLM Alignment via Explicit Injection (2026.acl-long)

Copied to clipboard

He Geng, Yangmin Huang, Lixian Lai, Qianyun Du, Hui Chu, Zhiyang He, Jiaxue Hu, Xiaodong Tao

Challenge:	Large Language Models (LLMs) are difficult to align with high-stakes medical standards due to dissonance between coarse-grained preference signals and complex protocols.
Approach:	They propose a framework that aligns Large Language Models with medical standards . they use a dataset generated via a human-in-the-loop pipeline to augment medical instructions .
Outcome:	The proposed framework disentangles safety constraints from general proficiency, enabling precise guidance during reinforcement learning.

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

Copied to clipboard

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

Breaking Language Preference in Multilingual RAG via Language-Controllable Retrieval and Language-Agnostic Reasoning (2026.findings-acl)

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

Wenshuai Huo, Xiaocheng Feng, Baohang Li, Chengpeng Fu, Yichong Huang, Hui Wang, Bing Qin

Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt Learning (2024.emnlp-main)

Challenge:	Existing approaches to improve retrieval accuracy and generation quality of large language models suffer from language preference.
Approach:	They propose a framework that explicitly disentangles multilingual RAG into language-controllable retrieval and language-agnostic reasoning.
Outcome:	Experimental results show that the proposed approach outperforms baselines across multilingual benchmarks.

Copied to clipboard

Qizhou Chen, Taolin Zhang, Xiaofeng He, Dongyang Li, Chengyu Wang, Longtao Huang, Hui Xue’

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

Challenge:	Existing methods to correct outdated or erroneous knowledge in large language models (LLMs) are slow and cumbersome, resulting in catastrophic knowledge forgetting and degradation of model performance.
Approach:	They propose a RetriEval-augmented ContInuous Prompt lEarning method that converts knowledge statements into short and informative continuous prompts, prefixed to the LLM’s input query embedding.
Outcome:	The proposed method improves the performance of large language models (LLMs) while maintaining the overall performance of the model.

Copied to clipboard

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

SUN: Exploring Intrinsic Uncertainties in Text-to-SQL Parsers (2022.coling-1)

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

Bowen Qin, Lihan Wang, Binyuan Hui, Bowen Li, Xiangpeng Wei, Binhua Li, Fei Huang, Luo Si, Min Yang, Yongbin Li

Programming Languages in NLP

Challenge:	Existing methods that learn from multiple semantically-equivalent questions are limited to one-to-one mapping .
Approach:	They propose a constraint to explore the underlying complementary semantic information among multiple semantically-equivalent questions and learn robust feature representations with reduced spurious associations.
Outcome:	The proposed method outperforms strong competitors and achieves state-of-the-art results on five benchmark datasets.

PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts (2023.acl-long)

Copied to clipboard

Yunshui Li, Binyuan Hui, ZhiChao Yin, Min Yang, Fei Huang, Yongbin Li

Dialogue Systems & Conversational Agents

Challenge:	Existing research on multi-modal dialogue pre-training is limited due to limited availability of multi-dimensional data . a recent emergence of chatGPT 1 has increased confidence in the potential for this goal .
Approach:	They propose a framework for multi-modal dialogue pre-training that integrates experts to accommodate multi-faceted tasks.
Outcome:	The proposed framework achieves state-of-the-art on eight multi-modal dialog benchmarks.

Iterative Nearest Neighbour Machine Translation for Unsupervised Domain Adaptation (2023.findings-acl)

Copied to clipboard

Hui Huang, Shuangzhi Wu, Xinnian Liang, Zefan Zhou, Muyun Yang, Tiejun Zhao

Low-Resource NLP

Challenge:	Existing methods for supervised domain adaptation of machine translation focus on fine-tuning, which is non-extensible.
Approach:	They propose to perform unsupervised domain adaptation in a non-parametric manner by using in-domain monolingual data and performing nearest neighbour inference on both forward and backward directions.
Outcome:	The proposed method significantly improves the in-domain translation performance and achieves state-of-the-art results among non-parametric methods.

2D-DPO: Scaling Direct Preference Optimization with 2-Dimensional Supervision (2025.findings-naacl)

Copied to clipboard

Shilong Li, Yancheng He, Hui Huang, Xingyuan Bu, Jiaheng Liu, Hangyu Guo, Weixun Wang, Jihao Gu, Wenbo Su, Bo Zheng

Challenge:	Existing methods that optimize for scalar scores or ranking reward ignore multi-dimensional nature of human preferences.
Approach:	They propose to extend the preference of Direct Preference Optimization to two dimensions: segments and aspects.
Outcome:	The proposed framework decomposes the overall objective into multi-segment and multi-aspect objectives.

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

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.

On the Role of Long-tail Knowledge in Retrieval Augmented Large Language Models (2024.acl-short)

Copied to clipboard

Dongyang Li, Junbing Yan, Taolin Zhang, Chengyu Wang, Xiaofeng He, Longtao Huang, Hui Xue’, Jun Huang

One-Shot Learning as Instruction Data Prospector for Large Language Models (2024.acl-long)

Challenge:	Existing RAG methods focus on improving the task performance, without fine-grained process of knowledge.
Approach:	They propose a method that detects long-tail knowledge in large language models by analyzing retrieved documents and enhancing queries indiscriminately with retrieved information.
Outcome:	The proposed method achieves over 4x speedup in average inference time and consistent performance improvement in downstream tasks compared to existing pipelines.

Copied to clipboard

Yunshui Li, Binyuan Hui, Xiaobo Xia, Jiaxi Yang, Min Yang, Lei Zhang, Shuzheng Si, Ling-Hao Chen, Junhao Liu, Tongliang Liu, Fei Huang, Yongbin Li

Integrating Audio, Visual, and Semantic Information for Enhanced Multimodal Speaker Diarization on Multi-party Conversation (2025.acl-long)

Challenge:	Contemporary practices in instruction tuning often hinge on enlarging data scaling without a clear strategy for ensuring data quality.
Approach:	They propose a method that leverages one-shot learning to discern and select high-quality instruction data from extensive datasets.
Outcome:	Nuggets outperforms existing methods on MT-Bench and Alpaca-Eval benchmarks.

Copied to clipboard

Luyao Cheng, Hui Wang, Chong Deng, Siqi Zheng, Yafeng Chen, Rongjie Huang, Qinglin Zhang, Qian Chen, Xihao Li, Wen Wang

Enabling Unsupervised Neural Machine Translation with Word-level Visual Representations (2023.findings-emnlp)

Challenge:	Mainstream speaker diarization systems rely only on acoustic information, making it challenging in complex aural environments.
Approach:	They propose a multimodal approach that integrates audio, visual, and semantic cues to enhance speaker diarization.
Outcome:	The proposed approach outperforms state-of-the-art methods on multi-party conversations . it integrates audio-visual-semantic cues into the clustering process for acoustic speaker embeddings .

Copied to clipboard

Chengpeng Fu, Xiaocheng Feng, Yichong Huang, Wenshuai Huo, Hui Wang, Bing Qin, Ting Liu

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

Challenge:	Unsupervised neural machine translation methods have been observed to make particular errors in comparison to supervised machine translation, such as confusing nouns that pertain to the same semantic category.
Approach:	They propose a method that incorporates images at the word level to augment lexical mappings.
Outcome:	Experiments on a multi-lingual dataset show that the proposed method generates more accurate translations with only monolingual data.

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

AIR: Complex Instruction Generation via Automatic Iterative Refinement (2025.emnlp-main)

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

Wei Liu, Yancheng He, Yu Li, Hui Huang, Chengwei Hu, Jiaheng Liu, Shilong Li, Wenbo Su, Bo Zheng

Text Generation

Challenge:	Existing methods for generating complex instructions are resource-intensive and lack diversity.
Approach:	They propose a framework to generate complex instructions with constraints using a document-generated initial instruction and an iterative refinement framework to incorporate LLM-as-judge guidance.
Outcome:	The proposed framework significantly outperforms existing methods for generating complex instructions, and outperformed existing methods.

Fast Quiet-STaR: Thinking Without Thought Tokens (2025.findings-emnlp)

Copied to clipboard

Wei Huang, Yizhe Xiong, Xin Ye, Zhijie Deng, Hui Chen, Zijia Lin, Guiguang Ding

Reasoning

Challenge:	Large Language Models have achieved impressive performance across a range of tasks, but further gains require more than scaling up model sizes or training data.
Approach:	They propose a method that gradually reduces the number of thought tokens . this method allows models to internalize more abstract reasoning processes .
Outcome:	The proposed framework preserves the benefits of token-level reasoning while reducing computational cost.

Beyond Majority Voting: Towards Fine-grained and More Reliable Reward Signal for Test-Time Reinforcement Learning (2026.acl-long)

Copied to clipboard

Weiqin Wang, Yile Wang, Kehao Chen, Hui Huang

Reasoning

Challenge:	RLVR is a paradigm for improving reasoning ability of large language models . but voting results often induce confirmation bias and suffer from sparse rewards .
Approach:	They propose a framework integrating model confidence and dynamic subgroup partitioning to address these issues.
Outcome:	The proposed framework outperforms recent baselines on multiple models and benchmarks.

Improving Translation Quality Estimation with Bias Mitigation (2023.acl-long)

Copied to clipboard

Hui Huang, Shuangzhi Wu, Kehai Chen, Hui Di, Muyun Yang, Tiejun Zhao

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

Challenge:	State-of-the-art translation Quality Estimation models are biased, relying on monolingual features while ignoring the bilingual semantic alignment.
Approach:	They propose a method to mitigate the bias of translation quality estimation models by contrastive learning between clean and noisy sentence pairs.
Outcome:	The proposed method improves the estimation performance while mitigating the bias.

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

A Semantic Filter Based on Relations for Knowledge Graph Completion (2021.emnlp-main)

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

Zongwei Liang, Junan Yang, Hui Liu, Keju Huang

Structure-Aware Quantized Retrieval for Long-Document Question Answering (2026.findings-acl)

Challenge:	Knowledge graph embedding is a new form of knowledge graphing that allows for better link prediction.
Approach:	They propose to use relational embedding to fit symmetry/antisymmetry and combination relationships.
Outcome:	The proposed model can fit symmetry/antisymmetry and combination relationships.

Copied to clipboard

Hui Huang, Julien Velcin, Yacine Kessaci

Information Retrieval

Challenge:	Traditional long-document QA/RAG pipelines suffer from context fragmentation . Graph Neural Networks (GNNs) can encode hierarchy, but deep GNNs tend to over-smooth representations.
Approach:	They propose a framework that aligns hierarchical graph representations with a universal token vocabulary and integrates explicit structure into retrieval.
Outcome:	The proposed framework captures universal hierarchical patterns rather than overfitting to specific layouts.

AnchorMem: Anchored Facts with Associative Contexts for Building Memory in Large Language Models (2026.findings-acl)

Copied to clipboard

Zhanyu Shen, Sijie Cheng, Zhicheng Guo, Weiqin Wang, Yile Wang, Hui Huang

Breaking the Stage Barrier: A Novel Single-Stage Approach to Long Context Extension for Large Language Models (2025.coling-main)

Challenge:	Existing memory systems rely on summarization to preserve contextual nuances and obscuring key retrieval features.
Approach:	They propose a method that decouples the retrieval unit from the generation context.
Outcome:	The proposed method outperforms baseline models on the LoCoMo benchmark.

Copied to clipboard

Haoran Lian, Junmin Chen, Wei Huang, Yizhe Xiong, Wenping Hu, Guiguang Ding, Hui Chen, Jianwei Niu, Zijia Lin, Fuzheng Zhang, Di Zhang

Ranked Voting based Self-Consistency of Large Language Models (2025.findings-acl)

Challenge:	Recent studies show that Large language models struggle with handling long token sequences due to limited training context size.
Approach:	They propose a single-stage continual pretraining method to equip LLMs with long context modeling capabilities.
Outcome:	The proposed method outperforms existing methods on 4 language modeling benchmarks.

Copied to clipboard

Weiqin Wang, Yile Wang, Hui Huang

Refiner: Restructure Retrieved Content Efficiently to Advance Question-Answering Capabilities (2024.findings-emnlp)

Challenge:	Existing majority voting methods generate only a single answer in each trial, ignoring the possibility of other possible answers.
Approach:	They propose to generate ranked answers in each reasoning process and conduct ranked voting among multiple ranked responses from different responses.
Outcome:	Extensive experiments show that the proposed method outperforms baselines on multiple-choice and open-ended questions.

Copied to clipboard

Zhonghao Li, Xuming Hu, Aiwei Liu, Kening Zheng, Sirui Huang, Hui Xiong

Green & Sustainable NLP

Challenge:	Large Language Models (LLMs) are limited by their parametric knowledge, leading to hallucinations in knowledge-extensive tasks.
Approach:	They propose an end-to-end extract-and-restructure paradigm that leverages a single decoder-only LLM to adaptively extract query-relevant contents verbatim along with the necessary context.
Outcome:	Experiments show that a trained Refiner outperforms state-of-the-art RAG and compressing approaches in multiple tasks.

DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models (2025.naacl-long)

Copied to clipboard

Jianyu Liu, Hangyu Guo, Ranjie Duan, Xingyuan Bu, Yancheng He, Shilong Li, Hui Huang, Jiaheng Liu, Yucheng Wang, Chenchen Jing, Xingwei Qu, Xiao Zhang, Pei Wang, Yanan Wu, Jihao Gu, Yangguang Li, Jianke Zhu

Exploring Dynamic Selection of Branch Expansion Orders for Code Generation (2021.acl-long)

Challenge:	Multimodal Large Language Models (MLLMs) pose unique safety challenges due to their integration of visual and textual data.
Approach:	They propose a method to disentangle risks through step-by-step reasoning within multimodal inputs.
Outcome:	The proposed approach improves safety alignment in MLLMs by fine-tuning and iterative Reinforcement Learning from AI feedback.

Copied to clipboard

Hui Jiang, Chulun Zhou, Fandong Meng, Biao Zhang, Jie Zhou, Degen Huang, Qingqiang Wu, Jinsong Su

Programming Languages in NLP

Challenge:	Existing code generation models model abstract syntax tree (AST) but not suitable for all multi-branch nodes.
Approach:	They propose to equip a Seq2Tree model with a branch selector to determine optimal expansion orders for multi-branch nodes.
Outcome:	The proposed model can determine optimal expansion orders of branches for multi-branch nodes.

SemPA: Improving Sentence Embeddings of Large Language Models through Semantic Preference Alignment (2026.findings-acl)

Copied to clipboard

Ziyang Chen, Zhenxuan Huang, Yile Wang, Weiqin Wang, Lu Yin, Hui Huang

SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding (2022.coling-1)

Challenge:	Existing sentence embedding methods rely on fixed prompt templates or involve modifications to the model architecture, compromising its generative capabilities.
Approach:	They propose a sentence-level direct preference optimization approach that boosts the sentence representations while preserving the generative ability of LLMs.
Outcome:	The proposed method improves representations of semantically meaningful vectors without sacrificing generation capability.

Copied to clipboard

Wanwei He, Yinpei Dai, Binyuan Hui, Min Yang, Zheng Cao, Jianbo Dong, Fei Huang, Luo Si, Yongbin Li

Supervised Prototypical Contrastive Learning for Emotion Recognition in Conversation (2022.emnlp-main)

Challenge:	Existing methods for dialog understanding only consider self-augmented dialogs as positive samples and treat all other dialogs like negative ones.
Approach:	They propose a tree-structured pre-trained conversation model which learns dialog representations from limited labeled dialogs and large-scale unlabeled dialog corpora via semi-supervised contrastive pre-training.
Outcome:	The proposed model can achieve state-of-the-art results on the DialoGLUE benchmark.

Copied to clipboard

Xiaohui Song, Longtao Huang, Hui Xue, Songlin Hu

Multiple Instance Learning for Offensive Language Detection (2022.findings-emnlp)

Challenge:	Existing methods to capture emotions in conversation (ERC) lack the correlation between emotions and semantics, resulting in many challenges.
Approach:	They propose a Supervised Prototypical Contrastive Learning (SPCL) loss for the ERC task . they use a Prototype Network to leverage the supervised contrastive learning approach .
Outcome:	The proposed approach outperforms CoG-BART's proposed approach on three widely used benchmarks and shows that it is effective on multiple scenarios.

Copied to clipboard

Jiexi Liu, Dehan Kong, Longtao Huang, Dinghui Mao, Hui Xue

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

Challenge:	Existing approaches to detect offensive content are expensive and require massive manual effort.
Approach:	They propose an approach capable of utilizing the bag-level labeled data for offensive language detection by an annotation-based model.
Outcome:	The proposed model can detect offensive language on both bag-level and sentence level.

Copied to clipboard

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

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

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

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

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

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

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.

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

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

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

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

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.

AgentMark: Utility-Preserving Behavioral Watermarking for Agents (2026.acl-long)

Copied to clipboard

Kaibo Huang, Jin Tan, Yukun Wei, Wanling Li, Zipei Zhang, Hui Tian, Zhongliang Yang, Linna Zhou

Challenge:	Recent advances in large language models (LLMs) have improved text generation and reasoning.
Approach:	They propose a behavioral watermarking framework that embeds multi-bit identifiers into planning decisions while preserving utility.
Outcome:	The proposed framework embeds multi-bit provenance into planning decisions while preserving utility.

Towards Robust k-Nearest-Neighbor Machine Translation (2022.emnlp-main)

Copied to clipboard

Hui Jiang, Ziyao Lu, Fandong Meng, Chulun Zhou, Jie Zhou, Degen Huang, Jinsong Su

Text Generation

Challenge:	k-Nearest-Neighbor Machine Translation (kNN-MT) is a popular research paradigm in machine translation.
Approach:	They propose a confidence-enhanced kNN-MT model with robust training to reduce noise . they introduce NMT confidence to refine the modeling of important components of kN-MT .
Outcome:	The proposed model improves on four benchmark datasets and is robust to training.

Multimodal Recommendation Dialog with Subjective Preference: A New Challenge and Benchmark (2023.findings-acl)

Copied to clipboard

Yuxing Long, Binyuan Hui, Caixia Yuan, Fei Huang, Yongbin Li, Xiaojie Wang

Dialogue Systems & Conversational Agents

Challenge:	Existing multimodal task-oriented dialog data fails to demonstrate the diverse expressions of user subjective preferences and recommendation acts in the real-life shopping scenario.
Approach:	They propose a multimodal task-oriented dialog dataset with subjective preferences and recommendation acts that is well-annotated with sales experts.
Outcome:	The proposed model is powered by a state-of-the-art multimodal model for these tasks.

Tree-Instruct: A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment (2024.lrec-main)

Copied to clipboard

Yingxiu Zhao, Bowen Yu, Binyuan Hui, Haiyang Yu, Minghao Li, Fei Huang, Nevin L. Zhang, Yongbin Li

Challenge:	Extensive research has highlighted the importance of data complexity as a crucial metric, but the impact of complexity remains relatively unexplored.
Approach:	They propose to add a specified number of nodes to instructions’ semantic trees to enhance the instruction complexity in a controllable manner.
Outcome:	The proposed approach outperforms diverse yet complex instructions under the same token budget and can control the difficulty level of modified instructions.

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

Copied to clipboard

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

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

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.

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