Papers by Hong Li

Uncertainty Quantification for Clinical Outcome Predictions with (Large) Language Models (2025.findings-naacl)

Challenge:	Existing approaches for multi-hop reasoning are lacking for local graph reasoning . existing approaches neglect local semantic structures in utterances .
Approach:	They propose a question-aware global-to-local graph reasoning approach that expands the canonical Interlocutor-Utterance graph by introducing a query node.
Outcome:	The proposed approach outperforms existing methods on Molweni and FriendsQA.

Copied to clipboard

Zizhang Chen, Peizhao Li, Xiaomeng Dong, Pengyu Hong

SP3: Enhancing Structured Pruning via PCA Projection (2024.findings-acl)

Challenge:	Language models (LMs) have significant potential for clinical prediction tasks . however, unreliable decisions can result in significant costs due to compromised patient safety and ethical concerns .
Approach:	They propose to combine ensembling and multi-tasking approaches to reduce uncertainty in EHRs by using multi-tapping methods.
Outcome:	The proposed framework reduces model uncertainty in white-box and black-box settings, and improves model transparency in both settings.

Copied to clipboard

Yuxuan Hu, Jing Zhang, Zhe Zhao, Chen Zhao, Xiaodong Chen, Cuiping Li, Hong Chen

Better Process Supervision with Bi-directional Rewarding Signals (2025.findings-acl)

Challenge:	Structured pruning is a widely used technique for reducing the size of pre-trained language models, but current methods overlook the potential of compressing the hidden dimension d in PLMs.
Approach:	They propose a structured pruning approach that projectes features into a space defined by principal components before masking the hidden dimension d in pre-trained language models.
Outcome:	Experiments on benchmarks show that SP3 can reduce d by 70%, compress 94% of the BERTbase model, and maintain over 96% accuracy.

Copied to clipboard

Wenxiang Chen, Wei He, Zhiheng Xi, Honglin Guo, Boyang Hong, Jiazheng Zhang, Nijun Li, Tao Gui, Yun Li, Qi Zhang, Xuanjing Huang

FC-KBQA: A Fine-to-Coarse Composition Framework for Knowledge Base Question Answering (2023.acl-long)

Challenge:	Existing processes that reward for each step are one-directional and lack a mechanism to model the distance to the final target.
Approach:	They propose a process supervision model that evaluates the correctness of previous steps and the probability of future success.
Outcome:	The proposed model outperforms existing supervision models like ORM and PRM on reasoning tasks and improves solution re-design.

Copied to clipboard

Lingxi Zhang, Jing Zhang, Yanling Wang, Shulin Cao, Xinmei Huang, Cuiping Li, Hong Chen, Juanzi Li

DuReader_robust: A Chinese Dataset Towards Evaluating Robustness and Generalization of Machine Reading Comprehension in Real-World Applications (2021.acl-short)

Challenge:	Existing methods for question answering over knowledge bases (KBQA) suffer from generalization issues due to coarse-grained modeling of the logical expression.
Approach:	They propose a fine-to- coarse-grained framework for KBQA to ensure generalization and executability of the logical expression.
Outcome:	The proposed framework derives new state-of-the-art performance on GrailQA and WebQSP, and runs 4 times faster than baseline.

Copied to clipboard

Hongxuan Tang, Hongyu Li, Jing Liu, Yu Hong, Hua Wu, Haifeng Wang

Two Directions for Clinical Data Generation with Large Language Models: Data-to-Label and Label-to-Data (2023.findings-emnlp)

Challenge:	In order to comprehensively verify the robustness and generalization of MRC models, we construct a real-world Chinese dataset - DuReader_robust .
Approach:	They introduce a real-world Chinese dataset to evaluate the robustness and generalization of MRC models from three aspects: over-sensitivity, over-stability and generalisation.
Outcome:	The proposed model fails to perform well on the challenge test set and may provide suggestions for future model development.

Copied to clipboard

Rumeng Li, Xun Wang, Hong Yu

P-INT: A Path-based Interaction Model for Few-shot Knowledge Graph Completion (2021.findings-emnlp)

Challenge:	Large language models (LLMs) can generate natural language texts for various domains and tasks, but their potential for clinical text mining is under-explored.
Approach:	They propose a pragmatic taxonomy for AD sign and symptom progression based on expert knowledge and train a system to detect AD-related signs and symptoms from EHRs.
Outcome:	The proposed taxonomy outperforms existing methods using only the gold dataset and silver datasets.

Copied to clipboard

Jingwen Xu, Jing Zhang, Xirui Ke, Yuxiao Dong, Hong Chen, Cuiping Li, Yongbin Liu

KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and Kirundi (2020.coling-main)

Challenge:	Existing methods to encode and match entity pairs have only a few observed reference entity pairs.
Approach:	They propose a model that infers and leverages paths that can expressively encode the relation of two entities.
Outcome:	The proposed model outperforms the state-of-the-art models by 11.2– 14.2% in terms of Hits@1.

Copied to clipboard

Rubungo Andre Niyongabo, Qu Hong, Julia Kreutzer, Li Huang

Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering (2022.acl-long)

Challenge:	low-resource African languages are traditionally left behind because of the lack of well-annotated data and effective preprocessing.
Approach:	They propose two news datasets for multi-class classification of news articles in two low-resource African languages.
Outcome:	The proposed datasets show that training embeddings on the higher-resourced Kinyarwanda yields successful cross-lingual transfer to Kirundi.

Copied to clipboard

Jing Zhang, Xiaokang Zhang, Jifan Yu, Jian Tang, Jie Tang, Cuiping Li, Hong Chen

OpenHuEval: Evaluating Large Language Model on Hungarian Specifics (2025.findings-acl)

Challenge:	Existing retrieval methods for knowledge base question answering are either heuristic or interwoven with the reasoning, causing reasoning on the partial subgraphs.
Approach:	They propose a subgraph retrieval framework that decouples the retrieval from the subsequent reasoning process and trains subgraphs for easier reasoning.
Outcome:	The proposed framework improves retrieval and QA performance over existing methods.

Copied to clipboard

Haote Yang, Xingjian Wei, Jiang Wu, Noémi Ligeti-Nagy, Jiaxing Sun, Yinfan Wang, Győző Zijian Yang, Junyuan Gao, Jingchao Wang, Bowen Jiang, Shasha Wang, Nanjun Yu, Zihao Zhang, Shixin Hong, Hongwei Liu, Wei Li, Songyang Zhang, Dahua Lin, Lijun Wu, Gábor Prószéky, Conghui He

CREAD: Combined Resolution of Ellipses and Anaphora in Dialogues (2021.naacl-main)

Challenge:	Recent advances in Large Language Models (LLMs) represent significant strides toward artificial general intelligence (AGI).
Approach:	They introduce OpenHuEval, the first benchmark for LLMs focusing on the Hungarian language and specifics.
Outcome:	The framework reveals intrinsic patterns and mechanisms of LLMs in non-English languages, with Hungarian serving as an example.

Copied to clipboard

Bo-Hsiang Tseng, Shruti Bhargava, Jiarui Lu, Joel Ruben Antony Moniz, Dhivya Piraviperumal, Lin Li, Hong Yu

Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models (2025.coling-main)

Challenge:	Traditionally, anaphora resolution and ellipses resolution are limited in dialogues . despite rapid progress in dialogue systems, several difficulties remain .
Approach:	They propose a joint learning framework for modeling coreference resolution and query rewriting for complex, multi-turn dialogues.
Outcome:	The proposed model outperforms the state-of-the-art model on a rewritten dialogue dataset.

Copied to clipboard

Jiahui Li, Yongchang Hao, Haoyu Xu, Xing Wang, Yu Hong

Robustness in NLP

Challenge:	Despite advances in training Large Language Models, they remain vulnerable to jailbreak, an adversarial attack method.
Approach:	They propose an adversarial jailbreak algorithm that exploits the gradient information of the suffix tokens to accelerate the optimization process.
Outcome:	The proposed model achieves 1.5x speedup while maintaining high attack success rates.

Knowledge-augmented Self-training of A Question Rewriter for Conversational Knowledge Base Question Answering (2022.findings-emnlp)

Copied to clipboard

Xirui Ke, Jing Zhang, Xin Lv, Yiqi Xu, Shulin Cao, Cuiping Li, Hong Chen, Juanzi Li

Data Interpreter: An LLM Agent for Data Science (2025.findings-acl)

Challenge:	Recent rise of conversational applications has promoted the development of conversation KBQA (ConvKBQA).
Approach:	They propose a framework to produce a full-fledged rewritten question based on conversation history and then reason the answer by existing single-turn KBQA models.
Outcome:	The proposed framework produces a full-fledged rewritten question based on the conversation history and reasoned the answer by existing single-turn KBQA models.

Copied to clipboard

Sirui Hong, Yizhang Lin, Bang Liu, Bangbang Liu, Binhao Wu, Ceyao Zhang, Danyang Li, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, Li Zhang, Lingyao Zhang, Min Yang, Mingchen Zhuge, Taicheng Guo, Tuo Zhou, Wei Tao, Robert Tang, Xiangtao Lu, Xiawu Zheng, Xinbing Liang, Yaying Fei, Yuheng Cheng, Yongxin Ni, Zhibin Gou, Zongze Xu, Yuyu Luo, Chenglin Wu

Unregulated Chinese-to-English Data Expansion Does NOT Work for Neural Event Detection (2022.coling-1)

Challenge:	Large Language Models (LLMs) excel in various domains but face challenges when applied to data science workflows due to their complex, multi-stage nature.
Approach:	They propose a hierarchical graph-based agent that represents complexity and a progressive strategy for step-by-step verification, refinement, and consistent context management.
Outcome:	The proposed agent surpasses state-of-the-art baselines on the MATH dataset and performs better on InfiAgent-DABench.

Copied to clipboard

Zhongqiu Li, Yu Hong, Jie Wang, Shiming He, Jianmin Yao, Guodong Zhou

Multilinguality

Challenge:	Experimental results show that cross-language data expansion results in performance degradation.
Approach:	They leverage cross-language data expansion and retraining to enhance neural Event Detection on English ACE corpus.
Outcome:	The proposed method improves ED performance by 1.6% over the straight data combination.

Can Large Language Models Understand Context? (2024.findings-eacl)

Copied to clipboard

Yilun Zhu, Joel Moniz, Shruti Bhargava, Jiarui Lu, Dhivya Piraviperumal, Site Li, Yuan Zhang, Hong Yu, Bo-Hsiang Tseng

LlamaCare: An Instruction Fine-Tuned Large Language Model for Clinical NLP (2024.lrec-main)

Challenge:	Existing evaluation methodologies for Large Language Models (LLMs) have been inadequate to evaluate their ability to understand contextual features.
Approach:	They propose a benchmark to assess large language models' ability to understand context by adapting existing datasets to suit their evaluation.
Outcome:	The proposed model performs better under the in-context learning pretraining scenario than state-of-the-art models.

Copied to clipboard

Rumeng Li, Xun Wang, Hong Yu

Self-Error-Instruct: Generalizing from Errors for LLMs Mathematical Reasoning (2025.acl-long)

Challenge:	Large language models have shown remarkable abilities in generating natural texts . applying LLMs to clinical domain still poses significant challenges .
Approach:	They propose a method of instruction fine-tuning for adapting large language models to clinical domains . they generate instructions, inputs, and outputs covering a wide spectrum of clinical services .
Outcome:	The proposed method outperforms baseline LLMs on clinical tasks . it requires domain adaptation, task-specific learning, and reliability .

Copied to clipboard

Erxin Yu, Jing Li, Ming Liao, Qi Zhu, Boyang Xue, Minghui Xu, Baojun Wang, Lanqing Hong, Fei Mi, Lifeng Shang

GrantRel: Grant Information Extraction via Joint Entity and Relation Extraction (2021.findings-acl)

Challenge:	Existing approaches to learning from errors synthesize training data by extrapolating from isolated bad cases, thereby failing to generalize the extensive patterns inherent within these cases.
Approach:	They propose a framework that synthesizes more generalized training data from isolated bad cases by extrapolating from isolated cases.
Outcome:	The proposed framework synthesizes more generalized training data to address these model weaknesses.

Copied to clipboard

Junyi Bian, Li Huang, Xiaodi Huang, Hong Zhou, Shanfeng Zhu

LEAF: Towards Lightweight Explainable Hateful Video Detection via Self-Grounding CoT Guided Stage-Wise Distillation (2026.findings-acl)

Challenge:	a funder name refers to an agency, organization, or program providing financial support for the research.
Approach:	They propose a funding sentence classifier and a relation extraction framework to extract grant information from scientific articles.
Outcome:	The proposed framework outperforms state-of-the-art BERT-based RE baselines against the PubMed Central and arXiv test sets.

Copied to clipboard

Jian Lang, Rongpei Hong, Meihui Zhong, Kaiju Li, Ting Zhong, Qiang Gao, Fan Zhou

Fast and Accurate End-to-End Span-based Semantic Role Labeling as Word-based Graph Parsing (2022.coling-1)

Challenge:	Existing methods for detecting hateful videos rely on opaque models with no insight into their decisions.
Approach:	They propose a lightweight, explainable video detection framework that distills "explainability" from LMMs into efficient Smaller Multimodal Models (SMMs) they use a self-grounded chain-of-thought mechanism to generate unbiased supervision signals for videos .
Outcome:	The proposed framework outperforms existing methods in detection accuracy and explainability on three video benchmarks.

Copied to clipboard

Shilin Zhou, Qingrong Xia, Zhenghua Li, Yu Zhang, Yu Hong, Min Zhang

SEP-MLDC: A Simple and Effective Paradigm for Multi-Label Document Classification (2025.findings-naacl)

Challenge:	Using end-to-end span-based SRL, we propose a word-based graph parsing task for word-level representation of spans . compared with word-driven SRL, span-Based SRL is more complex due to difficulties in determining argument boundaries.
Approach:	They propose to cast end-to-end span-based SRL as a word-based graph parsing task . they propose a constrained Viterbi procedure to ensure the legality of the output graph .
Outcome:	The proposed model can parse 669/252 sentences per second without and with pre-trained models.

Copied to clipboard

Han Liu, Shuqin Li, Xiaotong Zhang, Yuanyuan Wang, Feng Zhang, Hongyang Chen, Hong Yu

Information Retrieval

Challenge:	Existing methods focus on optimizing document features, overlooking the potential of high-quality label features to enhance classification performance.
Approach:	They propose a multi-label document classification paradigm that utilizes large language models to expand the label content and generate pseudo-samples for the tail categories.
Outcome:	The proposed method significantly outperforms state-of-the-art models.

Beyond Semantic Similarity: Appraisal-Guided Chain-of-Thought Reasoning and Retrieval for Multimodal Emotional Support Conversations (2026.findings-acl)

Copied to clipboard

Yuqi Chu, Lizi Liao, Jinggui Liang, Boyang Li, Richang Hong

SeNsER: Learning Cross-Building Sensor Metadata Tagger (2020.findings-emnlp)

Challenge:	Existing retrieval-augmented generation paradigms rely on semantic similarity to retrieve historical dialogues that are surface analogous but therapeutically incongruent.
Approach:	They propose to use appraisal-guided reasoning chains to generate appraisal-based reasoning chains and apply a dual-signal verification mechanism to verify and correct them.
Outcome:	Extensive experiments on two ESC benchmarks show that the proposed model significantly outperforms state-of-the-art models.

Copied to clipboard

Yang Jiao, Jiacheng Li, Jiaman Wu, Dezhi Hong, Rajesh Gupta, Jingbo Shang

Challenge:	Sensor metadata tagging is a key component of smart building applications.
Approach:	They propose a framework that learns a sensor metadata tagger for a new building based on its raw metadata and some existing fully annotated building.
Outcome:	The proposed framework learns a sensor metadata tagger for a new building based on its raw metadata and some existing fully annotated building.

Limitations of Language Models in Arithmetic and Symbolic Induction (2023.acl-long)

Copied to clipboard

Jing Qian, Hong Wang, Zekun Li, Shiyang Li, Xifeng Yan

PCQPR: Proactive Conversational Question Planning with Reflection (2024.emnlp-main)

Challenge:	Recent work has shown that large pretrained Language Models (LMs) can perform remarkably well on a range of NLP tasks but they have limitations on basic symbolic manipulation tasks such as copy, reverse, and addition.
Approach:	They propose to use explicit positional markers, fine-grained computation steps, and LMs with callable programs to teach large pretrained Language Models.
Outcome:	The proposed model can perform 100% accuracy in OOD and repeating symbols.

Copied to clipboard

Shasha Guo, Lizi Liao, Jing Zhang, Cuiping Li, Hong Chen

Efficient and Effective Internal Memory Retrieval for LLM-Based Healthcare Prediction (2026.findings-acl)

Challenge:	Current CQG methods focus on immediate context without strategic consideration of the specified conversational outcome.
Approach:	They propose a method that uses a planning algorithm inspired by Monte Carlo Tree Search to generate contextually relevant questions.
Outcome:	The proposed approach surpasses existing methods in e-learning and customer service fields . it generates contextually appropriate questions strategically devised to reach a specified outcome .

Copied to clipboard

Mingchen Li, Jiatan Huang, Zonghai Yao, Hong yu

AdaDHP: Fine-Grained Fine-Tuning via Dual Hadamard Product and Adaptive Parameter Selection (2025.acl-long)

Challenge:	Existing approaches to ground large language models in external knowledge are limited by hallucinations and a lack of granular medical context.
Approach:	They propose a framework that replaces external retrieval with internal, key-based knowledge access by encoding clinical information directly into the model’s parameter space.
Outcome:	The proposed framework achieves state-of-the-art performance across four benchmark healthcare outcome prediction datasets.

Copied to clipboard

Han Liu, Changya Li, Xiaotong Zhang, Feng Zhang, Fenglong Ma, Wei Wang, Hong Yu

Diversifying Question Generation over Knowledge Base via External Natural Questions (2024.lrec-main)

Challenge:	Increasing number of parameters can be challenging under resource-constrained environments.
Approach:	They propose a parameter-efficient fine-tuning method with fewer parameters and finer granularity that can adaptively select important parameters for each task.
Outcome:	The proposed method can fine-tune important parameters for each task, while maintaining the same weights.

Copied to clipboard

Shasha Guo, Jing Zhang, Xirui Ke, Cuiping Li, Hong Chen

Text Generation

Challenge:	Existing methods on knowledge base question generation focus on refining the quality of a single generated question.
Approach:	They propose a new diversity evaluation metric which measures the diversity among top-k generated questions for each instance while ensuring their relevance to the ground truth.
Outcome:	The proposed model outperforms pre-trained language model baselines and text-davinci-003 in diversity while achieving comparable performance with ChatGPT.

Corrupted but Not Broken: Understanding and Mitigating the Negative Impacts of Corrupted Data in Visual Instruction Tuning (2025.emnlp-main)

Copied to clipboard

Yunhao Gou, Hansi Yang, Zhili Liu, Kai Chen, Yihan Zeng, Lanqing Hong, Zhenguo Li, Qun Liu, Bo Han, James Kwok, Yu Zhang

SGSH: Stimulate Large Language Models with Skeleton Heuristics for Knowledge Base Question Generation (2024.findings-naacl)

Challenge:	Visual Instruction Tuning (VIT) aims to enhance Multimodal Large Language Models (MLLMs), but its effectiveness is often compromised by corrupted datasets with issues such as hallucinated content and poor OCR quality.
Approach:	They propose a corruption-robust training paradigm that surpasses existing strategies for mitigating the effects of corrupted data.
Outcome:	The proposed training paradigm surpasses existing strategies for mitigating the effects of corrupted data.

Copied to clipboard

Shasha Guo, Lizi Liao, Jing Zhang, Yanling Wang, Cuiping Li, Hong Chen

Using a Penalty-based Loss Re-estimation Method to Improve Implicit Discourse Relation Classification (2020.coling-main)

Challenge:	Existing methods have significantly boosted the performance of Knowledge Base Question Generation (KBQG) through pre-trained language models thanks to the richly endowed semantic knowledge.
Approach:	They propose a framework to Stimulate GPT-3.5 with Skeleton Heuristics to enhance KBQG by combining skeleton heuristic guidance with a soft prompting approach.
Outcome:	The proposed framework incorporates "skeleton heuristics" which provides more fine-grained guidance associated with each input to stimulate LLMs to generate optimal questions.

Copied to clipboard

Xiao Li, Yu Hong, Huibin Ruan, Zhen Huang

Text Classification

Challenge:	inessential words are unintentionally misjudged as attention-worthy words and assigned heavier attention weights than should be.
Approach:	They propose a penalty-based method to regulate the attention learning process by integrating penalty coefficients into the computation of loss by means of overstability of attention weight distributions.
Outcome:	The proposed method improves on the Penn Discourse TreeBank corpus and is competitive compared to the state-of-the-art methods.

DSM: Question Generation over Knowledge Base via Modeling Diverse Subgraphs with Meta-learner (2022.emnlp-main)

Copied to clipboard

Shasha Guo, Jing Zhang, Yanling Wang, Qianyi Zhang, Cuiping Li, Hong Chen

SOLAR: Serendipity Optimized Language Model Aligned for Recommendation (2025.findings-emnlp)

Challenge:	Existing methods on knowledge base question generation learn a one-size-fits-all model by training together all subgraphs without distinguishing the diverse semantics of subgraph.
Approach:	They propose a graph contrastive learning-based retriever to model diverse subgraphs with meta-learner to learn semantics-specific and semantics agnostic knowledge on and across these tasks.
Outcome:	The proposed approach reduces learning difficulty and improves performance on two widely-adopted benchmarks on KBQG.

Copied to clipboard

Zichen Yuan, Lifan Sun, Yucen Zhuang, Yue Wang, Xinyuan Song, Tianqi Xu, Siyuan Li, Junchen Fu, Youhua Li, Sirui Hong, Jiaqi Chen, Joemon M. Jose, Yongxin Ni

Multi-Agent Comedy Club: Investigating Community Discussion Effects on LLM Humor Generation (2026.findings-acl)

Challenge:	Large Language Models have shown strong potential in recommendation tasks . however, their application to serendipity-oriented recommendations remains challenging .
Approach:	They propose a domain-adaptive instruction tuning method that aligns Large Language Models with recommendation tasks.
Outcome:	The proposed framework bridges the domain gap between LLMs and recommendation tasks.

Copied to clipboard

Shiwei Hong, Lingyao Li, Ethan Z. Rong, Chenxinran Shen, Zhicong Lu

Winnowing Knowledge for Multi-choice Question Answering (2021.findings-emnlp)

Challenge:	Existing studies on the use of multi-turn interaction and feedback for LLM writing focus on prompts and localized feedback.
Approach:	They build a controlled multi-agent sandbox that instantiates a small standup comedy community and allows it to manipu-late whether public reception is generated, logged, and fed back into later rounds.
Outcome:	The proposed model improves craft/clarity and social response with occasional increases in aggressive humor.

Copied to clipboard

Yeqiu Li, Bowei Zou, Zhifeng Li, Ai Ti Aw, Yu Hong, Qiaoming Zhu

QueueEDIT: Structural Self-Correction for Sequential Model Editing in LLMs (2026.findings-acl)

Challenge:	Existing reasoning models suffer from noises in retrieved knowledge . encoding methods that use commonsense knowledge are less effective .
Approach:	They propose a method which conducts interception and soft filtering to reduce noise . they use commonsense knowledge from Wikipedia and ConceptNet to encode questions and options .
Outcome:	The proposed method improves on commonsense question answering tasks compared to baselines . it is able to conduct interception and soft filtering to shield the encoder from noise .

Copied to clipboard

Taolin Zhang, Haidong Kang, Dongyang Li, Qizhou Chen, Xiaofeng He, Chengyu Wang, Richang Hong

Logits-Based Finetuning (2025.emnlp-main)

Challenge:	Recent studies have shown that large language models (LLMs) can be effective for correcting factual inaccuracies but can still suffer from hallucinations.
Approach:	They propose a queue-based self-correction framework that addresses parameter bias during sequential model editing.
Outcome:	The proposed framework outperforms baseline models while maintaining competitive performance in single-turn editing.

Copied to clipboard

Jingyao Li, Senqiao Yang, Sitong Wu, Han Shi, Chuanyang Zheng, Hong Xu, Jiaya Jia

SURE: Safety Understanding and Reasoning Enhancement for Multimodal Large Language Models (2025.emnlp-main)

Challenge:	Existing methods for developing compact and efficient large language models lack token-level dependencies and linguistic diversity.
Approach:	They propose a logits-based fine-tuning framework that integrates supervised learning and knowledge distillation to build enriched training targets using teacher logits and ground truth labels.
Outcome:	The proposed method outperforms existing methods on a large-scale logits dataset and a series of science-focused models.

Copied to clipboard

Yuxin Gou, Xiaoning Dong, Qin Li, Shishen Gu, Richang Hong, Wenbo Hu

Dual-Reasoner: Bridging Interleaved Atomicity and Streaming Latency via Thinking-while-Talking (2026.findings-acl)

Challenge:	Existing multimodal large language models incorporate visual and textual information, but introduces new and complex safety risks.
Approach:	They propose a safety reasoning framework that integrates visual modalities into multimodal models to help them resist jailbreak attacks.
Outcome:	The proposed framework improves model safety while avoiding over-defense . it is based on a large-scale safety reasoning dataset .

Copied to clipboard

Yangzhuo Li, Shengpeng Ji, Yifu Chen, Tianle Liang, Haoyu Yang, null Junboli, Jun Fang, Lin Li, Qingyang Hong

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

Challenge:	Existing methods to integrate Chain-of-Thought into spoken dialogue models incur prohibitive latency.
Approach:	They propose a Streaming Masking Mechanism to ensure uninterrupted audio streaming . they use a quadruple-constraint system to reconstruct logical atomicity .
Outcome:	Experimental results show that Dual-Reasoner improves speech generation performance with low latency.

Copied to clipboard

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

Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs (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

Yubo Gao, Haotian Wu, Hong Chen, Junquan Huang, Yibo Yan, Jungang Li, Zihao Dongfang, Sicheng Tao, PS Tan, Jie Zhang, Xuming Hu

QuickLLaMA: Query-aware Inference Acceleration for Large Language Models (2025.coling-main)

Challenge:	Existing efficiency methods for Chain-of-Thought (CoT) generate excessively long rationales without commensurate accuracy gains.
Approach:	They propose a training framework that operationalizes this principle through coarse-to-fine budgeting.
Outcome:	Experiments on GSM8K and MATH500 show that HAB surpasses standard CoT in accuracy and reduces token usage, achieving stronger performance-efficiency trade-off than baselines.

Copied to clipboard

Jingyao Li, Han Shi, Sitong Wu, Chuanyang Zheng, Zhenguo Li, Xin Jiang, Hong Xu, Jiaya Jia

AIGuard: A Benchmark and Lightweight Detection for E-commerce AIGC Risks (2025.findings-acl)

Challenge:	Large Language Models (LLMs) struggle with capturing long-distance dependencies within sequences to deeply understand semantics.
Approach:	They propose a system that captures relevant information within a fixed window size and provides precise answers to queries.
Outcome:	The proposed system can read Harry Potter within 30s and accurately answer the questions.

Copied to clipboard

Wenhua Zhang, Weicheng Li, Xuanrong Rao, Lixin Zou, Xiangyang Luo, Chubin Zhuang, Yongjie Hong, Zhen Qin, Hengyu Chang, Chenliang Li, Bo Zheng

Is the Attention Matrix Really the Key to Self-Attention in Multivariate Long-Term Time Series Forecasting? (2026.acl-long)

Challenge:	Existing detection methods lack real-world scenarios and corresponding risk datasets . current MLLMs lack knowledge and have limited capability to detect the risk of AIGC content.
Approach:	They propose a benchmark for AIGC risk detection in real-world e-commerce . it includes 253,420 image-text pairs across four critical categories .
Outcome:	The proposed method achieves 9.68% higher recall than leading multimodal models while using only 25% of training resources.

Copied to clipboard

Xinyu Li, Kexi Chen, Jiajie Shen, Ying Zheng, Hong Lu, Jin Zhao, Xin Wang

Speech-to-Speech Translation with Discrete-Unit-Based Style Transfer (2024.acl-srw)

Challenge:	In multivariate long-term time series forecasting, it is widely believed that the effectiveness of self-attention arises from its attention matrix.
Approach:	They propose a multi-branch MLP that isolates the ‘multi-brain mapping with element-wise operation’ structure from the Transformer and shows that it achieves competitive performance.
Outcome:	The proposed model outperforms three classic and three latest Transformer models and shows that it achieves competitive performance.

Copied to clipboard

Yongqi Wang, Bai Jionghao, Rongjie Huang, Ruiqi Li, Zhiqing Hong, Zhou Zhao

Multilinguality

Challenge:	Existing methods to translate spoken utterances from one language to another are unable to preserve speaker timbre of source speech.
Approach:	They propose a pipeline with style-transfer capability on the basis of self-supervised speech representations and codec units.
Outcome:	The proposed model achieves zero-shot cross-lingual style transfer on previously unseen source languages.

Dynamic Model-Bank Test-Time Adaptation for Automatic Speech Recognition (2025.emnlp-main)

Copied to clipboard

Yanshuo Wang, Yanghao Zhou, Yukang Lin, Haoxing Chen, Jin Zhang, Wentao Zhu, Jie Hong, Xuesong Li

How to Determine the Most Powerful Pre-trained Language Model without Brute Force Fine-tuning? An Empirical Survey (2023.findings-emnlp)

Challenge:	Existing ASR TTA methods struggle with instability under continual and long-term distribution shifts.
Approach:	They propose a continuous adaptive model-bank framework that adapts to domain shifts in ASR test-time scenarios.
Outcome:	Experiments on diverse, continuously shifting ASR benchmarks show that DMSUTA outperforms existing continual TTA baselines.

Copied to clipboard

Jun Bai, Xiaofeng Zhang, Chen Li, Hanhua Hong, Xi Xu, Chenghua Lin, Wenge Rong

Interview Evaluation: A Novel Approach for Automatic Evaluation of Conversational Question Answering Models (2023.emnlp-main)

Challenge:	Transferability estimation has been a topic of great interest in computer vision fields . a lack of a comprehensive comparison between these estimation methods is a problem .
Approach:	They conduct a thorough survey of existing methods to find the most suitable model . they also outline difficulties of consideration of training details and applicability to text generation .
Outcome:	The proposed methods perform well with superiorities in effectiveness and efficiency.

Copied to clipboard

Xibo Li, Bowei Zou, Yifan Fan, Yanling Li, Ai Ti Aw, Yu Hong

ODD: A Benchmark Dataset for the Natural Language Processing Based Opioid Related Aberrant Behavior Detection (2024.naacl-long)

Challenge:	Existing evaluation methods for CQA use pre-collected human-human conversations . previous methods use model-predicted dialogue history instead of ground truth .
Approach:	They propose an automatic evaluation approach that uses the model's dialogue history to evaluate models.
Outcome:	The proposed method improves on existing models and their evaluations on QuAC and CoQA.

Copied to clipboard

Sunjae Kwon, Xun Wang, Weisong Liu, Emily Druhl, Minhee Sung, Joel Reisman, Wenjun Li, Robert Kerns, William Becker, Hong Yu

Fingerprinting LLMs via Prompt Injection (2026.acl-long)

Challenge:	Opioid related aberrant behaviors (ORABs) present novel risk factors for opioid overdose.
Approach:	They propose to use a biomedical natural language processing benchmark dataset to classify ORABs from patients’ EHR notes into nine categories: confirmed aberrant behavior, suggested aberrant behaviors, Opioids, indication, diagnosed opioid dependency, Benzodiazepines, medication changes, and Central Nervous System-related.
Outcome:	The proposed dataset outperforms two state-of-the-art models in most categories and the gains are especially higher among uncommon classes.

Copied to clipboard

Yuepeng Hu, Zhengyuan Jiang, Mengyuan Li, Osama Ahmed, Zhicong Huang, Cheng Hong, Neil Zhenqiang Gong

DualAlign: Generating Clinically Grounded Synthetic Data (2026.findings-acl)

Challenge:	Existing provenance detection methods for large language models are infeasible for already published models and compare outputs using hand-crafted or random prompts.
Approach:	They propose a detection framework that constructs fingerprints by exploiting LLMs’ inherent vulnerability to prompt injection.
Outcome:	The proposed framework achieves high true positive rates while keeping false positive rates near zero.

Copied to clipboard

Rumeng Li, null XWang, Hong yu

NoteChat: A Dataset of Synthetic Patient-Physician Conversations Conditioned on Clinical Notes (2024.findings-acl)

Challenge:	Large language models (LLMs) can generate fluent clinical text, but ensuring that such outputs are clinically grounded and useful for downstream modeling remains challenging.
Approach:	They propose a disease-agnostic framework for generating privacy-preserving, clinically faithful synthetic EHR narratives.
Outcome:	The proposed framework produces context-aware, symptom-rich sentences that more closely reflect real-world clinical documentation.

Copied to clipboard

Junda Wang, Zonghai Yao, Zhichao Yang, Huixue Zhou, Rumeng Li, Xun Wang, Yucheng Xu, Hong Yu

Theorem Prover as a Judge for Synthetic Data Generation (2025.acl-long)

Challenge:	NoteChat is a cooperative multi-agent framework for generating patient-physician dialogues . evaluator finds it outperforms state-of-the-art models for generating clinical notes . clinical documentation is largely done by physicians at both steps .
Approach:	They propose a cooperative multi-agent framework leveraging Large Language Models to generate patient-physician dialogues.
Outcome:	The proposed framework outperforms state-of-the-art models for generating clinical notes . it can engage patients directly and help clinical documentation, a leading cause of physician burnout .

Copied to clipboard

Joshua Ong Jun Leang, Giwon Hong, Wenda Li, Shay B Cohen

AEQ-Bench: Measuring Empathy of Omni-Modal Large Models (2026.findings-acl)

Challenge:	Recent studies show that large language models are increasingly capable of tackling mathematical problems.
Approach:	They propose an approach that iteratively refines theorem prover formalisation to mitigate errors.
Outcome:	The proposed method increases execution rate on the Lean prover from 60% to 87%, while human annotation is replaced with theorem prover feedback.

Copied to clipboard

Xuan Luo, Lewei Yao, Lanqing Hong, Kai Chen, Dehua Tao, Daxin Tan, Yukun Deng, Ruifeng Xu, Jing Li

CoSafe: Evaluating Large Language Model Safety in Multi-Turn Dialogue Coreference (2024.emnlp-main)

Challenge:	Existing benchmarks focus on cognitive abilities, such as knowledge retrieval, complex reasoning, and instruction following, largely overlooking empathy evaluation.
Approach:	They propose to benchmark two core empathetic capabilities of omnimodal large models (OLMs) generating empatries by comprehending affective cues from multi-modal inputs and judging empathy of audio responses without relying on text transcription.
Outcome:	The proposed benchmark outperforms existing models with audio output capabilities but is unreliable for evaluating fine-grained paralinguistic expressiveness.

Copied to clipboard

Erxin Yu, Jing Li, Ming Liao, Siqi Wang, Gao Zuchen, Fei Mi, Lanqing Hong

Robustness in NLP

Challenge:	Existing studies have not noticed the safety risks of large language models . authors evaluated 1,400 questions in multi-turn dialogue coreference .
Approach:	They are the first to evaluate LLM safety in multi-turn dialogue coreference . they created a dataset of 1,400 questions and tested five open-source models .
Outcome:	The study shows that model safety decreases in multi-turn dialogue coreference scenarios . the highest success rate was with the LLaMA2-Chat-7b model, while the lowest was with mistral-7B-Instruct model .

RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs in Medicine (2026.findings-acl)

Copied to clipboard

Jiatan Huang, Mingchen Li, Zonghai Yao, Dawei Li, Yuxin Zhang, Zhichao Yang, Yongkang Xiao, Feiyun Ouyang, Xiaohan Li, Shuo Han, Hong yu

Amanda: Adaptively Modality-Balanced Domain Adaptation for Multimodal Emotion Recognition (2024.findings-acl)

Challenge:	Existing methods for retrieving medical textual knowledge Graphs struggle to perform well, a study finds . existing methods struggle to provide accurate answers to complex questions, he says .
Approach:	They synthesize user queries integrating diverse topological structures, relational information, and complex textual descriptions.
Outcome:	a new dataset for medical textual knowledge graphs shows that existing methods struggle to perform well . main bottlenecks lie in the scarcity of existing medical TKGs and the limited expressiveness of their topological structures .

Copied to clipboard

Xinxin Zhang, Jun Sun, Simin Hong, Taihao Li

Adaptive Gating in Mixture-of-Experts based Language Models (2023.emnlp-main)

Challenge:	Emotion recognition is a multimodal learning method that can be used for data scarcity.
Approach:	They propose to use Adaptively modality-balanced domain adaptation to balance the alignment of different modalities for multimodal emotion recognition.
Outcome:	The proposed model outperforms competing models on common datasets on multimodal emotion recognition.

Copied to clipboard

Jiamin Li, Qiang Su, Yitao Yang, Yimin Jiang, Cong Wang, Hong Xu

Generating Classical Chinese Poems from Vernacular Chinese (D19-1)

Challenge:	Existing models employ a fixed gating network where each token is computed by the same number of experts.
Approach:	They propose a flexible training strategy that allows tokens to be processed by a variable number of experts based on expert probability distribution.
Outcome:	The proposed model reduces training time and inference quality while maintaining sparsity while maintaining inference accuracy.

Copied to clipboard

Zhichao Yang, Pengshan Cai, Yansong Feng, Fei Li, Weijiang Feng, Elena Suet-Ying Chiu, Hong Yu

Text Generation

Challenge:	Existing models for classical Chinese poetry generation only allow users to use keywords to interfere with the meaning of generated poems.
Approach:	They propose a model to generate classical Chinese poems from vernacular . their model uses unsupervised machine translation to generate Chinese poems . human evaluation shows it can generate high-quality poems comparable to amateur poems - authors .
Outcome:	The proposed model improves the perplexity and BLEU of the proposed model compared with typical models and human evaluation shows it generates high-quality poems comparable to amateur poems.

Understanding and Patching Compositional Reasoning in LLMs (2024.findings-acl)

Copied to clipboard

Zhaoyi Li, Gangwei Jiang, Hong Xie, Linqi Song, Defu Lian, Ying Wei

Culture-Aware Machine Translation in Large Language Models: Benchmarking and Investigation (2026.acl-long)

Challenge:	LLMs have marked a revolutonary shift, yet they falter when faced with compositional reasoning tasks.
Approach:	They propose a lightweight method to patch compositional reasoning errors via editing the located MHSA modules in LLMs.
Outcome:	The proposed method can be used to patch compositional reasoning errors using MHSA modules located within the layers of the LLMs.

Copied to clipboard

Zekun Yuan, Yangfan Ye, Xiaocheng Feng, Baohang Li, Qichen Hong, Yunfei Lu, Dandan Tu, Bing Qin

Controllable Dialogue Simulation with In-context Learning (2022.findings-emnlp)

Challenge:	Existing studies on large language models focus on literal-level translation quality, such as adequacy and fluency.
Approach:	They propose a Culture-Aware Novel-Driven Parallel Dataset for Machine Translation and a multi-dimensional evaluation framework for assessing cultural translation quality.
Outcome:	The proposed model improves evaluation reliability in LLM-as-a-judge scenarios under culture-aware constraints.

Copied to clipboard

Zekun Li, Wenhu Chen, Shiyang Li, Hong Wang, Jing Qian, Xifeng Yan

HiRAS: A Hierarchical Multi-Agent Framework for Paper-to-Code Generation and Execution (2026.findings-acl)

Challenge:	Existing methods to generate annotated dialogues require crowdsourcing, which is expensive and time-consuming.
Approach:	They propose a dialogue simulation method based on large language model in-context learning that generates new dialogues and annotations in a controllable way.
Outcome:	The proposed method can expand a small set of dialogue data with minimum or zero human involvement and parameter update.

Copied to clipboard

Hanhua Hong, Yizhi LI, Jiaoyan Chen, Sophia Ananiadou, Xiaoli Li, Jung-jae Kim, Chenghua Lin

Text Generation

Challenge:	Existing approaches to automate computational research use fixed sequential agent pipelines with weak global coordination, which limits their robustness and overall performance.
Approach:	They propose a hierarchical multi-agent framework for end-to-end paper reproduction that employs supervisory manager agents to coordinate specialised agents across fine-grained stages.
Outcome:	The proposed framework improves the paper2code benchmark and significantly reduces hallucination in the evaluation.

A Generation-based Deductive Method for Math Word Problems (2023.emnlp-main)

Copied to clipboard

Yuxuan Hu, Jing Zhang, Haoyang Li, Cuiping Li, Hong Chen

DetectiveNN: Imitating Human Emotional Reasoning with a Recall-Detect-Predict Framework for Emotion Recognition in Conversations (2024.findings-emnlp)

Challenge:	Existing generation methods suffer from repeated sub-expression generation and deductive methods are restricted to dealing with binary operations.
Approach:	They propose a multivariate directed acyclic graph (mDAG) which generates the topological ordering of mDAg by equipping a generation model with a re-encoder to keep the deductive property but avoid the expensive enumeration of deductive methods.
Outcome:	The proposed model performs well on the widely used benchmarks and solves multivariate operators on the CMWPA benchmark.

Copied to clipboard

Simin Hong, Jun Sun, Taihao Li

Versatile Framework for Song Generation with Prompt-based Control (2025.findings-emnlp)

Challenge:	Existing methods for Emotion Recognition in conversations are insufficient in understanding the rich historical emotional context.
Approach:	They propose a novel model that utilizes a "recall-detect-predict" framework to imitate human emotional reasoning by 'recalling' past interactions of a speaker to collect emotional cues.
Outcome:	The proposed model outperforms existing methods on three benchmark datasets and significantly outperformed existing methods.

Copied to clipboard

Yu Zhang, Wenxiang Guo, Changhao Pan, Zhiyuan Zhu, Ruiqi Li, Jingyu Lu, Rongjie Huang, Ruiyuan Zhang, Zhiqing Hong, Ziyue Jiang, Zhou Zhao

BENTO: A Visual Platform for Building Clinical NLP Pipelines Based on CodaLab (2020.acl-demos)

Challenge:	Existing methods for song generation fail to generate vocals with prompt-based control and proper alignment.
Approach:	VersBand is a multi-task song generation framework for synthesizing high-quality songs with prompt-based control.
Outcome:	Experimental results show that VersBand performs better than baseline models across multiple song generation tasks.

Copied to clipboard

Yonghao Jin, Fei Li, Hong Yu

Visual Data in NLP

Challenge:	CodaLab has limited support for creating reusable tools that can be easily applied to different datasets and composed into pipelines.
Approach:	They propose a workflow management platform with a graphic user interface built on top of CodaLab to facilitate the process of building clinical NLP pipelines.
Outcome:	The proposed workflow management platform, BENTO, is designed for clinical NLP tasks and can be easily used by researchers and developers.

Leveraging Estimated Transferability Over Human Intuition for Model Selection in Text Ranking (2024.emnlp-main)

Copied to clipboard

Jun Bai, Zhuofan Chen, Zhenzi Li, Hanhua Hong, Jianfei Zhang, Chen Li, Chenghua Lin, Wenge Rong

Bacteria Biotope Relation Extraction via Lexical Chains and Dependency Graphs (D19-57)

Challenge:	Existing methods for text ranking are based on intuition, but their estimated transferability may not align well with the objectives of text ranking.
Approach:	They propose to compute expected rank as transferability, explicitly reflecting the model’s ranking capability.
Outcome:	The proposed method shows significant improvements over previous classification-oriented TE methods, human intuition, and ChatGPT with minor time consumption.

Copied to clipboard

Wuti Xiong, Fei Li, Ming Cheng, Hong Yu, Donghong Ji

Conversational Semantic Parsing for Dialog State Tracking (2020.emnlp-main)

Challenge:	In this paper, we describe our approach for the Bacteria Biotopes relation extraction subtask in the BioNLP Shared Task 2019 .
Approach:	They propose a novel approach for dependency graph construction based on lexical chains . they then propose 'neuro network' model which uses short-term memories and syntax information .
Outcome:	The proposed approach achieves the best F1 (66.3%) in the official evaluation participated by 7 teams.

Copied to clipboard

Jianpeng Cheng, Devang Agrawal, Héctor Martínez Alonso, Shruti Bhargava, Joris Driesen, Federico Flego, Dain Kaplan, Dimitri Kartsaklis, Lin Li, Dhivya Piraviperumal, Jason D. Williams, Hong Yu, Diarmuid Ó Séaghdha, Anders Johannsen

Do Large Language Models Align with Core Mental Health Counseling Competencies? (2025.findings-naacl)

Challenge:	Language understanding for task-based dialog systems is often termed "dialog state tracking" (DST) whereas semantic parsing is the task of converting a single-turn utterance to a graphstructured meaning representation, DST is more complex.
Approach:	They propose a framework for dialog state tracking that incorporates semantic compositionality, cross-domain knowledge sharing and co-reference.
Outcome:	The proposed framework improves on state-of-the-art approaches for dialog state tracking (DST) it incorporates semantic compositionality, cross-domain knowledge sharing and co-reference.

Copied to clipboard

Viet Cuong Nguyen, Mohammad Taher, Dongwan Hong, Vinicius Konkolics Possobom, Vibha Thirunellayi Gopalakrishnan, Ekta Raj, Zihang Li, Heather J. Soled, Michael L. Birnbaum, Srijan Kumar, Munmun De Choudhury

BrowseComp-Plus: A Fair and Disentangled Evaluation Benchmark for Deep Search Agents (2026.acl-long)

Challenge:	Large language models are promising for mental health, but their alignment with core counseling competencies remains underexplored.
Approach:	They propose a benchmark to evaluate 22 general-purpose and medical-finetuned LLMs across five key competencies.
Outcome:	The proposed model outperforms generalist models in Intake, Assessment & Diagnosis but struggles with core counseling attributes and professional practice & ethics.

Copied to clipboard

Zijian Chen, Xueguang Ma, Shengyao Zhuang, Ping Nie, Kai Zou, Sahel Sharifymoghaddam, Andrew Liu, Joshua Green, Kshama Patel, Ruoxi Meng, Mingyi Su, Yanxi Li, Haoran Hong, Xinyu Shi, Xuye Liu, Hosna Oyarhoseini, Nandan Thakur, Crystina Zhang, Luyu Gao, Wenhu Chen, Jimmy Lin

Prompt-Singer: Controllable Singing-Voice-Synthesis with Natural Language Prompt (2024.naacl-long)

Challenge:	Existing benchmarks for deep search agents rely on blackbox web search APIs . dynamic and opaque web APIs hinder reproducibility and fair comparisons - authors .
Approach:	They propose a benchmark that employs a fixed corpus for controlled retrieval for deep search agents.
Outcome:	The new benchmark shows that agents that combine large language models with retrieval tools excel at complex, reasoning-intensive queries.

Copied to clipboard

Yongqi Wang, Ruofan Hu, Rongjie Huang, Zhiqing Hong, Ruiqi Li, Wenrui Liu, Fuming You, Tao Jin, Zhou Zhao

CoRAG: Enhancing Hybrid Retrieval-Augmented Generation through a Cooperative Retriever Architecture (2025.findings-emnlp)

Challenge:	Recent singing-voice-synthesis methods lack ability to control style attributes of synthesized singing.
Approach:	They propose a singing-voice-synthesis method that enables attribute controlling on singer gender, vocal range and volume with natural language.
Outcome:	The proposed method achieves favorable control ability and audio quality.

Copied to clipboard

Zaiyi Zheng, Song Wang, Zihan Chen, Yaochen Zhu, Yinhan He, Liangjie Hong, Qi Guo, Jundong Li

PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference (2025.acl-long)

Challenge:	Existing methods only retrieve related documents from local neighbors or subgraphs in the knowledge base, which often miss relevant information located further away from a global view.
Approach:	Hybrid-RAG combines textual documents and graph-structured relational information for RAG . existing methods only retrieve related documents from local neighbors or subgraphs in the knowledge base .
Outcome:	Hybrid-RAG combines textual documents and graph-structured relational information . existing methods only retrieve related documents from local neighbors or subgraphs in the knowledge base .

Copied to clipboard

Jiaming Ji, Donghai Hong, Borong Zhang, Boyuan Chen, Josef Dai, Boren Zheng, Tianyi Alex Qiu, Jiayi Zhou, Kaile Wang, Boxun Li, Sirui Han, Yike Guo, Yaodong Yang

Challenge:	Using large-scale annotation data, large language models can generate noise, errors and biases, leading to unexpected behaviours.
Approach:	They propose a dataset to promote safety alignment in large language models . they separate helpfulness and harmlessness annotations for question-answering pairs .
Outcome:	The proposed dataset provides 44.6k prompts and 265k question-answer pairs with safety meta-labels for 19 harm categories and three severity levels, with answers generated by Llama-family models.

Widget Captioning: Generating Natural Language Description for Mobile User Interface Elements (2020.emnlp-main)

Copied to clipboard

Yang Li, Gang Li, Luheng He, Jingjie Zheng, Hong Li, Zhiwei Guan

MuRAR: A Simple and Effective Multimodal Retrieval and Answer Refinement Framework for Multimodal Question Answering (2025.coling-demos)

Challenge:	Existing tools for examining and fixing missing captions are lacking in mobile UIs.
Approach:	They propose a task for automatically generating language descriptions for UI elements from multimodal input including both the image and structural representations of user interfaces.
Outcome:	The proposed task can generate captions from image and structural representations of UI elements.

Copied to clipboard

Zhengyuan Zhu, Daniel Lee, Hong Zhang, Sai Sree Harsha, Loic Feujio, Akash Maharaj, Yunyao Li

Pru-CoT: Towards Efficient Reasoning Distillation via Pruning Chain-of-Thought (2026.findings-acl)

Challenge:	Recent advances in retrieval-augmented generation have demonstrated impressive performance on the question-answering task.
Approach:	They propose a retrieval-augmented generation framework that generates an initial text answer and retrieves multimodal data relevant to the snippets of the initial text.
Outcome:	The proposed framework can be easily integrated into an enterprise chatbot to produce multimodal answers with minimal modifications.

Copied to clipboard

Han Liu, Shuotian Ma, Hui Li, Xiaotong Zhang, Fenglong Ma, Hong Yu

Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld’s Episode Theory (2025.emnlp-main)

Challenge:	Existing heuristics fail to capture global causal logic due to rigid rules and limited search spaces.
Approach:	They propose a framework that extracts the essential logical structure from reasoning chains.
Outcome:	Experiments show that Pru-CoT models generate more compact reasoning paths compared to models trained on verbose data.

Copied to clipboard

Ming Li, Nan Zhang, Chenrui Fan, Hong Jiao, Yanbin Fu, Sydney Peters, Qingshu Xu, Robert Lissitz, Tianyi Zhou

Linguistics & Cognitive NLP

Challenge:	Large Reasoning Models (LRMs) generate extensive chain-of-thought reasoning, but we lack a principled framework for understanding how these thoughts are structured.
Approach:	They propose a method to analyze the reasoning traces of Large Reasoning Models using Schoenfeld’s Episode Theory.
Outcome:	The proposed framework provides a theoretically grounded methodology for interpreting LRM cognition and enables future work on more controllable and transparent reasoning systems.

Capturing Conversational Interaction for Question Answering via Global History Reasoning (2022.findings-naacl)

Copied to clipboard

Jin Qian, Bowei Zou, Mengxing Dong, Xiao Li, AiTi Aw, Yu Hong

Can LLMs Estimate Student Struggles? Human-AI Difficulty Alignment with Proficiency Simulation for Item Difficulty Prediction (2026.findings-acl)

Challenge:	Existing studies have studied history-dependent reasoning for question answering . utilizing global conversation history for enhancement is gaining interest .
Approach:	They propose to establish long-distance dependency among global utterances in multi-turn conversation.
Outcome:	The proposed method improves on QuAC by 1%, yielding the F1 score of 73.7%.

Copied to clipboard

Ming Li, Han Chen, Yunze Xiao, Jian Chen, Hong Jiao, Tianyi Zhou

Cognitive Modeling

Challenge:	Accurate estimation of item (question or task) difficulty suffers from the cold start problem.
Approach:	They propose to use large-scale empirical analysis to examine human-AI Difficulty Alignment . they find that models struggle to simulate the capability limitations of students .
Outcome:	The proposed model size is not reliably helpful for human-AI alignment . high performance often impedes accurate difficulty estimation, the authors say .

Self-Supervised Singing Voice Pre-Training towards Speech-to-Singing Conversion (2024.findings-acl)

Copied to clipboard

Ruiqi Li, Rongjie Huang, Yongqi Wang, Zhiqing Hong, Zhou Zhao

Speech & Audio in NLP

Challenge:	Existing studies on speech-to-singing voice conversion (STS) are limited by the scarcity of paired speech-song data and the suboptimal quality of outputs.
Approach:	They propose a self-supervised singing voice pre-training model that transforms a speech-to-singing voice into a paired singing voice.
Outcome:	The proposed model improves both STS and singing voice synthesis tasks by combining spoken language and a self-supervised singing voice pre-training model.

Getting More Juice Out of Your Data: Hard Pair Refinement Enhances Visual-Language Models Without Extra Data (2025.naacl-long)

Copied to clipboard

Haonan Wang, Minbin Huang, Runhui Huang, Lanqing Hong, Hang Xu, Tianyang Hu, Xiaodan Liang, Zhenguo Li, Hong Cheng, Kenji Kawaguchi

EMA: An Episodic Memory Agent for Efficient and Selective Memory (2026.findings-acl)

Challenge:	Contrastive Language-Image Pre-training (CLIP) is a standard for cross-modal image-text representation learning.
Approach:	They propose a framework that enhances pre-trained CLIP models by exploiting challenging text-image pairs within existing datasets.
Outcome:	The proposed framework improves CLIP models by exploiting text-image pairs in training.

Copied to clipboard

Hongyi Lan, Jiaqi Song, Zhengjia Zhong, Hui Li, Hong Liu, Xianming Lin, Rongrong Ji

Looking Beyond the One: Operationalizing and Eliciting Visual Ambiguity in VLLMs (2026.acl-long)

Challenge:	Existing memory-augmented methods often incorporate full dialog histories without filtering, resulting in information redundancy and inference latency.
Approach:	They propose a framework that abstracts conversational context into Episodic Memory Units (EMUs) they propose EMA, MemDecider and a filtering decision module to reduce noise and improve overall performance.
Outcome:	The proposed framework reduces token consumption by 11.48% while improving performance on two widely-used benchmarks.

Copied to clipboard

Yuchong Chen, Bowei Zou, Yuhan Chen, Yifan Fan, Xinyu Li, Shujun Cao, Yu Hong

Visual Data in NLP

Challenge:	Visual question answering systems typically collapse ambiguity, committing to a single interpretation during decoding and evaluation.
Approach:	They operationalize ambiguity as the existence of multiple answer-supporting regions in an image . they show that ambiguities are already encoded in their internal representations .
Outcome:	The proposed approach makes ambiguity observable without exhaustive annotations . ambiguities are already encoded in models, but not reliably expressed in outputs despite hidden states .

CopyNE: Better Contextual ASR by Copying Named Entities (2024.acl-long)

Copied to clipboard

Shilin Zhou, Zhenghua Li, Yu Hong, Min Zhang, Zhefeng Wang, Baoxing Huai

Mastering the Craft of Data Synthesis for CodeLLMs (2025.naacl-long)

Challenge:	Existing approaches to transcribe contextual named entities (NEs) treat entities as tokens and generate them token-by-token, which may result in incomplete transcriptions of entities.
Approach:	They propose a mechanism that can copy entities from the NE dictionary and reduce errors during entity transcription.
Outcome:	The proposed mechanism can copy entities from the NE dictionary, reducing errors during entity transcription, ensuring the completeness of the entity.

Copied to clipboard

Meng Chen, Philip Arthur, Qianyu Feng, Cong Duy Vu Hoang, Yu-Heng Hong, Mahdi Kazemi Moghaddam, Omid Nezami, Duc Thien Nguyen, Gioacchino Tangari, Duy Vu, Thanh Vu, Mark Johnson, Krishnaram Kenthapadi, Don Dharmasiri, Long Duong, Yuan-Fang Li

Challenge:	Large language models (LLMs) have shown impressive performance in code understanding and generation.
Approach:	They propose a systematic review of large language models and their taxonomy and propose specialized LLMs for code-related tasks.
Outcome:	The proposed models have shown to be highly effective in coding tasks.

Mixture of insighTful Experts (MoTE): The Synergy of Reasoning Chains and Expert Mixtures in Self-Alignment (2025.acl-long)

Copied to clipboard

Zhili Liu, Yunhao Gou, Kai Chen, Lanqing Hong, Jiahui Gao, Fei Mi, Yu Zhang, Zhenguo Li, Xin Jiang, Qun Liu, James Kwok

Robust Singing Voice Transcription Serves Synthesis (2024.acl-long)

Challenge:	Recent studies show that reasoning abilities contribute significantly to model safety, while integrating Mixture-of-Experts (MoE) architectures can further enhance alignment.
Approach:	They propose a framework that synergistically combines reasoning chains and expert mixtures to improve self-alignment.
Outcome:	The proposed framework improves model safety, jailbreak resistance, and over-refusal capabilities, achieving performance comparable to OpenAI’s state-of-the-art o1 model.

Copied to clipboard

Ruiqi Li, Yu Zhang, Yongqi Wang, Zhiqing Hong, Rongjie Huang, Zhou Zhao

Robustness in NLP

Challenge:	Current AST methods struggle with accuracy and robustness when used for practical annotation.
Approach:	They propose a model that converts singing recordings into note sequences for automatic annotation of singing datasets.
Outcome:	The proposed model outperforms baseline models on enlarged, automatically annotated datasets.

A Pretraining Numerical Reasoning Model for Ordinal Constrained Question Answering on Knowledge Base (2021.findings-emnlp)

Copied to clipboard

Yu Feng, Jing Zhang, Gaole He, Wayne Xin Zhao, Lemao Liu, Quan Liu, Cuiping Li, Hong Chen

SAM Decoding: Speculative Decoding via Suffix Automaton (2025.acl-long)

Challenge:	Existing knowledge bases (KBs) can explicitly facilitate the QA process.
Approach:	They propose a numerical reasoning model pretraining NumGNN and NumTransformer, guided by explicit self-supervision signals, to enhance numerical reasoning ability for IR-based KBQA models.
Outcome:	Extensive experiments on two KBQA benchmarks confirm the effectiveness of the proposed model.

Copied to clipboard

Yuxuan Hu, Ke Wang, Xiaokang Zhang, Fanjin Zhang, Cuiping Li, Hong Chen, Jing Zhang

GuideLLM: Exploring LLM-Guided Conversation with Applications in Autobiography Interviewing (2025.naacl-long)

Challenge:	Speculative decoding (SD) methods are inefficient and rely on single retrieval resources.
Approach:	They propose a retrieval-based speculative decoding method that adapts the suffix automaton for efficient draft generation by utilizing the generating text sequence and static text corpus.
Outcome:	The proposed method can find the longest suffix match and can be integrated with existing methods to generalize to broader domains.

Copied to clipboard

Jinhao Duan, Xinyu Zhao, Zhuoxuan Zhang, Eunhye Grace Ko, Lily Boddy, Chenan Wang, Tianhao Li, Alexander Rasgon, Junyuan Hong, Min Kyung Lee, Chenxi Yuan, Qi Long, Ying Ding, Tianlong Chen, Kaidi Xu

Distill-C: Enhanced NL2SQL via Distilled Customization with LLMs (2025.naacl-industry)

Challenge:	Large Language Models (LLMs) have demonstrated their effectiveness in human-guided dialogues, but tasks in the real world are more complex and require greater autonomy from LLMs.
Approach:	They propose to characterize LLM-guided conversation into three fundamental components: Goal Navigation, Context Management, Empathetic Engagement and implement an interviewing environment for the evaluation of LLMs.
Outcome:	The proposed LLM outperforms baseline LLMs in interviewing quality and autobiography generation quality.

Copied to clipboard

Cong Duy Vu Hoang, Gioacchino Tangari, Clemence Lanfranchi, Dalu Guo, Paul Cayet, Steve Siu, Don Dharmasiri, Yuan-Fang Li, Long Duong, Damien Hilloulin, Rhicheek Patra, Sungpack Hong, Hassan Chafi

Federated Incremental Named Entity Recognition (2025.coling-main)

Challenge:	Domain- and customer-specific requirements complicate the problem of NL2SQL customization.
Approach:	They propose a distilled customization framework tailored for NL2SQL tasks.
Outcome:	The proposed framework outperforms teacher models on three benchmarks and achieves an average improvement of 36% in execution accuracy.

Copied to clipboard

Zesheng Liu, Qiannan Zhu, Cuiping Li, Hong Chen

Bold Claims or Self-Doubt? Factuality Hallucination Type Detection via Belief State (2025.findings-emnlp)

Challenge:	Existing methods for named entity recognition are based on pre-fixed entity types, resulting in catastrophic forgetting.
Approach:	They propose a model which allows for catastrophic forgetting of old entity types . they propose adaptive pseudo labeling and a prototypical relation distillation loss .
Outcome:	The proposed model overcomes catastrophic forgetting problem on old entity types with semantic shift.

Copied to clipboard

Dongyu Zhang, Qingqing Hong, Bingxuan Hou, Jiayi Lin, Chenyang Zhang, Jialin Li, Junli Wang

Improving Context Fidelity via Native Retrieval-Augmented Reasoning (2025.emnlp-main)

Challenge:	Existing studies focus on detecting the presence of hallucinations but lack a systematic classification approach, which hinders deeper exploration of their characteristics.
Approach:	They propose a method to categorize hallucinations into two types: Overconfident and Unaware .
Outcome:	The proposed method categorizes factuality hallucination into two types: Overconfident and Unaware Hallucinations.

Copied to clipboard

Suyuchen Wang, Jinlin Wang, Xinyu Wang, Shiqi Li, Xiangru Tang, Sirui Hong, Xiao-Wen Chang, Chenglin Wu, Bang Liu

AMATA: Adaptive Multi-Agent Trajectory Alignment for Knowledge-Intensive Question Answering (2026.acl-long)

Challenge:	Existing approaches to fidelity to contexts rely on expensive supervised fine-tuning to generate evidence post-answer or train models to perform web searches without improving utilization of the given context.
Approach:	They propose a native retrieval-augmented reasoning framework that integrates in-context evidence with the model’s own retrieval capabilities.
Outcome:	The proposed approach outperforms supervised fine-tuning, retrieval-augmented generation methods, and external retrieval solutions on multiple real-world and counterfactual QA benchmarks.

Copied to clipboard

Taolin Zhang, Dongyang Li, Chen Chen, Qizhou Chen, Jiuheng Wan, Xiaofeng He, Chengyu Wang, Richang Hong

Question Answering

Challenge:	Empirical results show that AMATA outperforms baseline approaches, knowledge-augmented frameworks, and LLMs on knowledge-intensive QA benchmarks.
Approach:	They propose an Adaptive Multi-Agent Trajectory Alignment framework that integrates external knowledge to improve response interpretability and factual grounding.
Outcome:	The proposed framework outperforms baseline approaches, knowledge-augmented frameworks, and LLM-based trajectory systems on five established knowledge-intensive QA benchmarks.

StitchLLM: Serving LLMs, One Block at a Time (2025.acl-long)

Copied to clipboard

Bodun Hu, Shuozhe Li, Saurabh Agarwal, Myungjin Lee, Akshay Jajoo, Jiamin Li, Le Xu, Geon-Woo Kim, Donghyun Kim, Hong Xu, Amy Zhang, Aditya Akella

VenusFactory: An Integrated System for Protein Engineering with Data Retrieval and Language Model Fine-Tuning (2025.acl-demo)

Challenge:	Existing techniques like distillation and pruning are not efficient for large language models.
Approach:	They propose a dynamic model routing framework that uses a powerful bottom model to process all queries and a lightweight routing mechanism to allocate computational resources appropriately.
Outcome:	The proposed framework improves system throughput while minimizing performance degradation.

Copied to clipboard

Yang Tan, Chen Liu, Jingyuan Gao, Wu Banghao, Mingchen Li, Ruilin Wang, Lingrong Zhang, Huiqun Yu, Guisheng Fan, Liang Hong, Bingxin Zhou

Text-to-Song: Towards Controllable Music Generation Incorporating Vocal and Accompaniment (2024.acl-long)

Challenge:	Pre-trained protein language models have been used in protein engineering, but their adoption is limited due to data collection, task benchmarking, and application challenges.
Approach:	They propose a versatile engine that integrates biological data retrieval, standardized task benchmarking, and modular fine-tuning of PLMs.
Outcome:	The proposed engine integrates biological data retrieval, task benchmarking, and modular fine-tuning of PLMs.

Copied to clipboard

Zhiqing Hong, Rongjie Huang, Xize Cheng, Yongqi Wang, Ruiqi Li, Fuming You, Zhou Zhao, Zhimeng Zhang

LoRACoE: Improving Large Language Model via Composition-based LoRA Expert (2025.emnlp-main)

Challenge:	Existing studies focus on singing voice synthesis and music generation independently.
Approach:	They propose a novel task called Text-to-Song synthesis which incorporates both vocal and accompaniment generation.
Outcome:	The proposed method can synthesize songs with comparable quality and style consistency.

Copied to clipboard

Guanyu Li, Zhiheng Xi, Zhihao Zhang, Boyang Hong, Tao Gui, Qi Zhang, Xuanjing Huang