Papers by Jin Huang

Chart-MRAG: Benchmarking Multimodal Retrieval Augmented Generation on Chart-based Documents (2026.acl-long)

Challenge:	Existing methods for handwriting generation capture global dependencies and can generate high-quality handwritten samples.
Approach:	They propose a Transformer-based model for ink generation, TrInk, which captures global dependencies.
Outcome:	The proposed model reduces character error rate and word error rate by 35.56% on the IAM-OnDB dataset compared to previous models.

Copied to clipboard

null Ymyang, Jiang Zhong, Li Jin, Xiao Sun, Jingwang Huang, null Gaojinpeng, Qing Liu, Yang Bai, Jingyuan Zhang, Rui Jiang, Qin Lei, Kaiwen Wei

Omni-Chart-600K: A Comprehensive Dataset of Chart Types for Chart Understanding (2025.findings-naacl)

Challenge:	Existing benchmarks focus on simple image-text interactions, overlooking complex visual formats like charts.
Approach:	They propose a semi-automatic framework for generating evaluation samples through multi-modal keypoint extraction, knowledge graph construction, and qa pair synthesis.
Outcome:	The proposed framework generates 4,738 question-answering pairs across 8 domains from real-world documents.

Copied to clipboard

Shulei Wang, Shuai Yang, Wang Lin, Zirun Guo, Sihang Cai, Hai Huang, Ye Wang, Jingyuan Chen, Tao Jin

DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories (2024.findings-acl)

Challenge:	Existing chart-related training methods lack capabilities in information extraction, mathematical reasoning, and understanding of multiple chart types.
Approach:	They propose a two-stage training strategy and method for jointly training a vision encoder tailored for multi-type charts to address the deficiencies in chart types and limited scope of chart tasks in existing datasets.
Outcome:	The proposed dataset includes 21 diverse chart types and tasks, including data retrieval and mathematical reasoning.

Copied to clipboard

Jia Li, Ge Li, Yunfei Zhao, Yongmin Li, Huanyu Liu, Hao Zhu, Lecheng Wang, Kaibo Liu, Zheng Fang, Lanshen Wang, Jiazheng Ding, Xuanming Zhang, Yuqi Zhu, Yihong Dong, Zhi Jin, Binhua Li, Fei Huang, Yongbin Li, Bin Gu, Mengfei Yang

Respond in my Language: Mitigating Language Inconsistency in Response Generation based on Large Language Models (2024.acl-long)

Challenge:	Existing benchmarks are poorly aligned with real-world code repositories and are insufficient to evaluate the coding abilities of Large Language Models (LLMs).
Approach:	They propose a repository-level benchmark named DevEval to evaluate LLMs' coding abilities in real-world code repositories.
Outcome:	The proposed benchmarks show that the LLMs perform better in real-world code repositories than existing benchmarks.

Copied to clipboard

Liang Zhang, Qin Jin, Haoyang Huang, Dongdong Zhang, Furu Wei

Text Generation

Challenge:	Large Language Models (LLMs) show strong instruction understanding ability across multiple languages, but are easily biased towards English in instruction tuning.
Approach:	They propose to use a model with Pseudo-Inconsistent Penalization to prevent the model from generating English responses when given non-English language prompts during training and prior Enhanced decoding to improve the language consistency of the model.
Outcome:	The proposed methods significantly improve the language consistency of the model without multilingual data.

Improving Discriminative Capability of Reward Models in RLHF Using Contrastive Learning (2024.emnlp-main)

Copied to clipboard

Lu Chen, Rui Zheng, Binghai Wang, Senjie Jin, Caishuang Huang, Junjie Ye, Zhihao Zhang, Yuhao Zhou, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang

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

Challenge:	Current methods rely on ranking losses to teach reward model to assess preferences, but they are susceptible to noise and ambiguous data, often failing to deeply understand human intentions.
Approach:	They propose a method that incorporates contrastive learning into the reward modeling process to enhance generalization and stabilize the reinforcement learning training process.
Outcome:	The proposed method enhances generalization of the reward model, stabilizes the reinforcement learning training process, and improves the final alignment with human preferences.

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.

Semantic and Syntactic Enhanced Aspect Sentiment Triplet Extraction (2021.findings-acl)

Copied to clipboard

Zhexue Chen, Hong Huang, Bang Liu, Xuanhua Shi, Hai Jin

Sentiment Analysis

Challenge:	Existing approaches to extract triplets from sentences neglect the mutual information between aspects and have the problem of error propagation.
Approach:	They propose a Semantic and Syntactic Enhanced aspect Sentiment triplet Extraction model to exploit the syntactical and semantic relationships between the triplet elements and jointly extract them.
Outcome:	The proposed model outperforms existing methods on four benchmark datasets and significantly outperformed existing approaches.

STYLE: Improving Domain Transferability of Asking Clarification Questions in Large Language Model Powered Conversational Agents (2024.findings-acl)

Copied to clipboard

Yue Chen, Chen Huang, Yang Deng, Wenqiang Lei, Dingnan Jin, Jia Liu, Tat-Seng Chua

Natural Language Interfaces

Challenge:	Existing methods for addressing ambiguities in conversational search systems are one-size-fits-all and struggle to achieve effective domain transferability.
Approach:	They propose a method to provide search engines with strategies regarding when to ask clarification questions in a post-hoc manner.
Outcome:	The proposed method improves search performance 10% on four unseen domains.

R³A: Reinforced Reasoning for Relevance Assessment for RAG in User-Generated Content Platforms (2026.acl-industry)

Copied to clipboard

Xiaowei Yuan, Lei Jin, Haoxin Zhang, Ziyang Huang, Yan Gao, null Yiwu, Yao Hu, Jun Zhao, Kang Liu

MEEL: Multi-Modal Event Evolution Learning (2024.findings-acl)

Challenge:	Existing approaches to query–document relevance assessment are limited . ambiguous user intent and asymmetric relevance are challenges for RAG platforms .
Approach:	They propose a decomposed reasoning model for relevance assessment that decomposes query intent into intent inference and evidence grounding.
Outcome:	The proposed model outperforms strong baselines on offline benchmarks and achieves significant gains in large-scale online A/B testing.

Copied to clipboard

Zhengwei Tao, Zhi Jin, Junqiang Huang, Xiancai Chen, Xiaoying Bai, Yifan Zhang, Chongyang Tao

A Confidence-based Partial Label Learning Model for Crowd-Annotated Named Entity Recognition (2023.findings-acl)

Challenge:	Existing models fail to grasp the principles governing event evolution in various scenarios.
Approach:	They propose a multi-modal event evolution learning approach to grasp event evolution . they propose an instruction encapsulation process that transforms evolving graphs into instruction-tuning data .
Outcome:	The proposed model grasps the event evolution mechanism yielding advanced MMER ability.

Copied to clipboard

Limao Xiong, Jie Zhou, Qunxi Zhu, Xiao Wang, Yuanbin Wu, Qi Zhang, Tao Gui, Xuanjing Huang, Jin Ma, Ying Shan

Information Extraction & Text Mining

Challenge:	Existing models for named entity recognition (NER) are based on large-scale labeled datasets, which always obtain using crowdsourcing.
Approach:	They propose a CONfidence-based partial Label Learning method to integrate prior and posterior confidences for crowd-annotated named entity recognition models.
Outcome:	The proposed model improves on real-world and synthetic datasets compared with baselines.

Your Reasoning Benchmark May Not Test Reasoning: Revealing Perception Bottleneck in Abstract Reasoning Benchmarks (2026.acl-long)

Copied to clipboard

Xinhe Wang, Jin Huang, Xingjian Zhang, Tianhao Wang, Jiaqi W. Ma

FinMaster: A Holistic Benchmark for Full-Pipeline Financial Management with Large Language Models (2026.findings-acl)

Challenge:	Abstraction and Reasoning Corpus and ARC-AGI are widely used to assess progress in artificial intelligence.
Approach:	They propose a two-stage pipeline that separates perception and reasoning . they propose to test this pipeline against standard end-to-end one-stage evaluation .
Outcome:	The proposed pipeline separates perception and reasoning, and isolates reasoning from bottlenecks.

Copied to clipboard

Junzhe Jiang, Chang Yang, Aixin Cui, Sihan Jin, Yujing Zhang, Yilin Xiao, Ruiyu Wang, Bo Li, Xiao Huang, Danny Dongning Sun, Xinrun Wang

SciAssess: Benchmarking LLM Proficiency in Scientific Literature Analysis (2025.findings-naacl)

Challenge:	Existing benchmarks lack domain-specific data, realistic workflow-level task design, and standardized workflow- level evaluation.
Approach:	a new benchmark evaluates large language models on financial management workflows . the global financial services market is projected to grow to $37 trillion by 2027 .
Outcome:	a new benchmark for large language models on financial management workflows reveals critical capability gaps . accuracy drops from 90% on basic tasks to 40% on complex scenarios requiring multi-step reasoning . the global financial services market reached $25.8 trillion in 2022 and is projected to grow to $37 trillion by 2027 .

Copied to clipboard

Hengxing Cai, Xiaochen Cai, Junhan Chang, Sihang Li, Lin Yao, Wang Changxin, Zhifeng Gao, Hongshuai Wang, Li Yongge, Mujie Lin, Shuwen Yang, Jiankun Wang, Mingjun Xu, Jin Huang, Xi Fang, Jiaxi Zhuang, Yuqi Yin, Yaqi Li, Changhong Chen, Zheng Cheng, Zifeng Zhao, Linfeng Zhang, Guolin Ke

Challenge:	Existing benchmarks fail to adequately evaluate the proficiency of Large Language Models (LLMs) Existing standards do not cover the skills needed to evaluate LLMs in scientific literature analysis.
Approach:	They propose a benchmark to evaluate the proficiency of large language models in scientific literature analysis.
Outcome:	SciAssess evaluates 11 LLMs on multiple tasks across scientific fields.

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

Copied to clipboard

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

OpenEval: Benchmarking Chinese LLMs across Capability, Alignment and Safety (2024.acl-demos)

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

Copied to clipboard

Chuang Liu, Linhao Yu, Jiaxuan Li, Renren Jin, Yufei Huang, Ling Shi, Junhui Zhang, Xinmeng Ji, Tingting Cui, Liutao Liutao, Jinwang Song, Hongying Zan, Sun Li, Deyi Xiong

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

Challenge:	a rapid development of Chinese large language models poses big challenges for efficient LLM evaluation.
Approach:	They propose an evaluation testbed that benchmarks Chinese LLMs across capability, alignment and safety.
Outcome:	The evaluation platform OpenEval benchmarks Chinese LLMs across capability, alignment and safety.

Copied to clipboard

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

Visual Data in NLP

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

InsLogicBench: An Argumentation Logic Grounded Benchmark for Complex Insurance Claims Adjudication (2026.acl-long)

Copied to clipboard

Jin Liu, Yunpeng Liu, Keyi Wang, Jie Shi, Xiao Xu, Wenkang Huang, Xingzhong Xu, Xin Liang, Yanghua Xiao

PaperMentor: A Human-Centered Multi-Agent Writing Tutor for AI Research Papers in Overleaf (2026.acl-demo)

Challenge:	Existing benchmarks for insurance claims adjudication are limited to information retrieval or simple multiple-choice setups.
Approach:	They propose a benchmark that provides complete reasoning traces linking factual inputs, relevant policy clauses, and final verdicts.
Outcome:	The proposed benchmark shows that models often produce correct decisions but fail to provide precise justifications, highlighting a critical discrepancy between decision accuracy and logical reasoning capabilities.

Copied to clipboard

Jiarui Liu, Terry Jingchen Zhang, Ryan Faulkner, Xuanqiang Angelo Huang, Vilém Zouhar, Dominik Glandorf, Isabel Dahlgren, Rishit Dagli, Yuen Chen, Felix Leeb, Van Q. Truong, Punya Syon Pandey, Yves Bicker, Suvajit Majumder, Wenyuan Jiang, Zeju Qiu, Sankalan Pal Chowdhury, Mrinmaya Sachan, Bernhard Schölkopf, Mona T. Diab, Zhijing Jin

Challenge:	Emerging AI-powered writing assistants focus on grammar fixes or simulating peer review with final scores, yet they fall short of providing concrete, actionable suggestions that help students improve their papers during drafting.
Approach:	They propose a human-centered writing assistant system that delivers actionable suggestions as Overleaf-native inline comments while leaving the actual writing entirely to human authors.
Outcome:	The proposed system outperforms a baseline with the skill library and provides actionable suggestions while leaving the actual writing to human authors.

LLMs are Biased Evaluators But Not Biased for Fact-Centric Retrieval Augmented Generation (2025.findings-acl)

Copied to clipboard

Yen-Shan Chen, Jing Jin, Peng-Ting Kuo, Chao-Wei Huang, Yun-Nung Chen

Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement (2023.findings-emnlp)

Challenge:	Recent studies have shown that large language models (LLMs) exhibit significant biases in evaluation tasks, especially in preferentially rating and favoring self-generated content.
Approach:	They propose to simulate two critical phases of retrieval-augmented generation (RAG) frameworks where keyword extraction and factual accuracy take precedence over stylistic elements.
Outcome:	The proposed model emulates two critical phases of the retrieval-augmented generation framework.

Copied to clipboard

Zhiheng Xi, Senjie Jin, Yuhao Zhou, Rui Zheng, Songyang Gao, Jia Liu, Tao Gui, Qi Zhang, Xuanjing Huang

Exploring Quality and Diversity in Synthetic Data Generation for Argument Mining (2025.emnlp-main)

Challenge:	Existing prompting methods have been used to enhance multistep reasoning capabilities of large language models, but they have overlooked the potential of formulating higher-quality problems.
Approach:	They propose a method that starts from the problem side and refines problems to be more comprehensible and solvable for models.
Outcome:	The proposed method achieves notable and consistent effectiveness on five reasoning benchmarks across different models.

Copied to clipboard

Jianzhu Bao, Yuqi Huang, Yang Sun, Wenya Wang, Yice Zhang, Bojun Jin, Ruifeng Xu

Evaluating Readability and Faithfulness of Concept-based Explanations (2024.emnlp-main)

Challenge:	Argument Mining (AM) is hindered by the scarcity of structure-annotated datasets, which are expensive to create manually.
Approach:	They propose to use quality-oriented synthesis and diversity-oriented approach to generate argumentative texts with diverse topics and argument structures.
Outcome:	The proposed approach significantly improves existing models in full-data and low-resource settings.

Copied to clipboard

Meng Li, Haoran Jin, Ruixuan Huang, Zhihao Xu, Defu Lian, Zijia Lin, Di Zhang, Xiting Wang

Explainability & Interpretability in NLP

Challenge:	Existing methods for evaluating concepts from different perspectives lack a unified formalization.
Approach:	They propose a formal definition of concepts generalizing to diverse concept-based explanations’ settings and apply it to other types of explanations or tasks.
Outcome:	Extensive experimental analysis was carried out to determine the evaluation measures for explanation evaluation measures.

Low-Rank HOCA: Efficient High-Order Cross-Modal Attention for Video Captioning (D19-1)

Copied to clipboard

Tao Jin, Siyu Huang, Yingming Li, Zhongfei Zhang

A Comprehensive Evaluation of Quantization Strategies for Large Language Models (2024.findings-acl)

Challenge:	Existing studies on video captioning focus on the association relationships between multiple modalities.
Approach:	They propose a video captioning model with high-order cross-modal attention (HOCA) they propose low-rank HOCA which adopts tensor decomposition to reduce the space requirement .
Outcome:	The proposed model captures cross-modal interaction of different modalities and reduces space requirement.

Copied to clipboard

Renren Jin, Jiangcun Du, Wuwei Huang, Wei Liu, Jian Luan, Bin Wang, Deyi Xiong

ARAIDA: Analogical Reasoning-Augmented Interactive Data Annotation (2024.acl-long)

Challenge:	Quantization studies have focused on instruction-tuned LLMs, leaving their performance on other benchmarks unclear.
Approach:	They propose a framework to evaluate quantized large language models using four dimensions . they propose to reduce the bits needed for model weights or activations with minimal performance loss .
Outcome:	The proposed framework can retain comparable performance to non-quantized LLMs on most benchmarks.

Copied to clipboard

Chen Huang, Yiping Jin, Ilija Ilievski, Wenqiang Lei, Jiancheng Lv

Predicting Clinical Trial Results by Implicit Evidence Integration (2020.emnlp-main)

Challenge:	Empirical studies demonstrate that Araida reduces human correction labor by 11.02% compared to vanilla interactive data annotation methods.
Approach:	They propose an analogical reasoning-based approach that enhances automatic annotation accuracy in the interactive data annotation setting and reduces the need for human corrections.
Outcome:	Empirical studies show that Araida reduces human correction labor by 11.02% compared to vanilla interactive data annotation methods.

Copied to clipboard

Qiao Jin, Chuanqi Tan, Mosha Chen, Xiaozhong Liu, Songfang Huang

Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents (2026.acl-long)

Challenge:	Clinical trials are expensive and time-consuming, and inappropriately designed studies can be devastating in a pandemic.
Approach:	They propose a model that takes a PICO-formatted clinical trial proposal and predicts the outcome from it.
Outcome:	The proposed model outperforms baseline models on a benchmark dataset with 10.7% relative gain over BioBERT.

Copied to clipboard

Ziyi Wang, Yuxuan Lu, Yimeng Zhang, Pei Chen, Ziwei Dong, Jing Huang, Jiri Gesi, Xianfeng Tang, Chen Luo, Qun Liu, Yisi Sang, Hanqing Lu, Manling Li, Jin Lai, Dakuo Wang

UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model (2023.findings-emnlp)

Challenge:	Tool-calling agents are increasingly deployed in real-world customer-facing workflows . but most studies on tool-callers focus on idealized settings with general, fixed, and well-specified tasks.
Approach:	They propose a tool-calling agent-based data pipeline that converts trajectories into user-facing tasks with controlled intent adaptations.
Outcome:	The proposed pipeline can be used to study tool use under three scenarios.

Copied to clipboard

Jiabo Ye, Anwen Hu, Haiyang Xu, Qinghao Ye, Ming Yan, Guohai Xu, Chenliang Li, Junfeng Tian, Qi Qian, Ji Zhang, Qin Jin, Liang He, Xin Lin, Fei Huang

A New Pipeline for Knowledge Graph Reasoning Enhanced by Large Language Models Without Fine-Tuning (2024.emnlp-main)

Challenge:	Existing studies for visually-situated language understanding have shown shallow zero-shot visual text recognition ability when fed a low-resolution image with salient text information.
Approach:	They propose a model for universal OCR-free visually-situated language understanding based on the Multimodal Large Language Model (MLLM) their model is jointly finetuned on a wide range of visually situated language understanding tasks via a unified instruction format.
Outcome:	The proposed model achieves state-of-the-art ocr-free performance in 8 out of 10 visually-situated language understanding tasks across 5 domains: documents, tables, charts, natural images, and webpage screenshots.

Copied to clipboard

Zhongwu Chen, Long Bai, Zixuan Li, Zhen Huang, Xiaolong Jin, Yong Dou

VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models (2024.emnlp-main)

Challenge:	Conventional knowledge Graph Reasoning models learn the embeddings of KG components over the structure of a KG.
Approach:	They propose a pipeline to integrate knowledge from LLMs into KGs without fine-tuning . they propose knowledge alignment, KG reasoning and entity reranking to enhance conventional models .
Outcome:	The proposed pipeline can enhance the performance of conventional KGR models in incomplete and general situations.

Copied to clipboard

Jiapeng Wang, Chengyu Wang, Kunzhe Huang, Jun Huang, Lianwen Jin

Test of Time: Rethinking Temporal Signal of Benchmark Contamination (2026.acl-long)

Challenge:	Existing studies have shown that CLIP models with short summary texts cannot process extensive textual descriptions due to its text encoder's reliance on positional embeddings with length 77.
Approach:	They propose a Contrastive Language-Image Pre-training (CLIP) model which aims to unleash the long-description understanding capability of video CLIP models.
Outcome:	The proposed model can learn the distribution of feature space while expanding the long description capability.

Copied to clipboard

Terry Jingchen Zhang, Gopal Dev, Ning Wang, Max Obreiter, Punya Syon Pandey, Keenan Samway, Wenyuan Jiang, Yinya Huang, Bernhard Schölkopf, Mrinmaya Sachan, Zhijing Jin

Challenge:	Existing work on benchmarks containing publicly available information has been interpreted as a temporal signal for benchmark contamination.
Approach:	They show that LLM-transformed questions can produce remarkably different temporal patterns compared to fill-in-the-blank questions directly retrieved from the very same documents.
Outcome:	The proposed model can produce different temporal patterns compared to fill-in-the-blank questions retrieved from the same documents.

EvoHyper: Evolving Hypergraph Topologies for Unified Collaboration in Multi-Agent Communication (2026.findings-acl)

Copied to clipboard

Heng Zhang, Yihao Zhong, Lubin Gan, Zhihe Chen, Jiajun Wu, Yuling Shi, Xiaodong Gu, Hao Zhang, Haochen You, Jin Huang

Challenge:	Existing methods for multi-agent collaboration use a fixed communication graph and manage collaboration structure and shared memory in separate modules.
Approach:	They propose a framework that uses an evolving hypergraph topology for multi-agent collaboration.
Outcome:	The proposed framework achieves 3.2% to 7.8% accuracy gains over state-of-the-art methods and efficient, reducing token consumption by up to 23.5%.

LongMP-Bench: A Benchmark for Multimodal Persona Understanding in Long-Term Dialogues (2026.findings-acl)

Copied to clipboard

Zhuoqun Li, Zhaopei Huang, Wenxuan Wang, Qin Jin

CLAMBER: A Benchmark of Identifying and Clarifying Ambiguous Information Needs in Large Language Models (2024.acl-long)

Challenge:	Existing datasets suffer from limited persona diversity and static, overly simplified settings, making them insufficient for capturing the complexity of real-world interactions.
Approach:	They propose a benchmark to evaluate models' ability to understand evolving user personas within long-term multimodal dialogues by using a dataset that contains long conversations from 150 users.
Outcome:	The proposed benchmark aims to assess models' ability to track persona evolution, integrate visual and textual inputs, and apply persona understanding in realistic dialogue scenarios.

Copied to clipboard

Tong Zhang, Peixin Qin, Yang Deng, Chen Huang, Wenqiang Lei, Junhong Liu, Dingnan Jin, Hongru Liang, Tat-Seng Chua

T2A-Feedback: Improving Basic Capabilities of Text-to-Audio Generation via Fine-grained AI Feedback (2025.acl-long)

Challenge:	Large language models are used to meet user information needs, but their effectiveness in dealing with user queries that contain various types of ambiguity remains unknown.
Approach:	They propose a benchmark for evaluating large language models using a well-organized taxonomy.
Outcome:	The proposed model is based on a well-organized taxonomy and compares it with other models.

Copied to clipboard

Zehan Wang, Ke Lei, Chen Zhu, Jiawei Huang, Sashuai Zhou, Luping Liu, Xize Cheng, Shengpeng Ji, Zhenhui Ye, Tao Jin, Zhou Zhao

Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers? (2025.coling-main)

Challenge:	Text-to-audio (T2A) models still struggle to satisfy human preferences for prompt-following and acoustic quality when generating complex multi-event audio.
Approach:	They propose to use AI feedback learning to enhance basic capabilities of text-to-audio models . they use a large audio preference dataset to evaluate the model's capabilities .
Outcome:	The proposed model improves in simple and complex scenarios with AI feedback learning.

Copied to clipboard

Mingyu Jin, Qinkai Yu, Jingyuan Huang, Qingcheng Zeng, Zhenting Wang, Wenyue Hua, Haiyan Zhao, Kai Mei, Yanda Meng, Kaize Ding, Fan Yang, Mengnan Du, Yongfeng Zhang

Model-Based Imaginative Planning for Embodied Agents (2026.acl-long)

Challenge:	Large language models have shown remarkable performances across a wide range of tasks, but mechanisms by which they encode tasks of varying complexity remain poorly understood.
Approach:	They propose to explore the possibility that LLMs process concepts in different layers . they propose to categorize concepts based on their level of abstraction .
Outcome:	The proposed model can process complex concepts in shallow layers, the authors show . the proposed model could be used to prob complex tasks in shallow ones .

Copied to clipboard

Junru Song, Hengzhe Jin, Yucong Huang, Tingsong Jiang, Weien Zhou, Feifei Wang, Yang Yang, Ying Wen, Wen Yao

TinyChart: Efficient Chart Understanding with Program-of-Thoughts Learning and Visual Token Merging (2024.emnlp-main)

Challenge:	a lightweight world model converts raw pixels into object-centric symbolic states amenable to language-based reasoning . IMPLEMENT is a framework for grounding language agents in visual embodied environments .
Approach:	They propose a model-based reasoning framework that enables frozen large language models to perform imaginative planning.
Outcome:	The proposed framework can be used to ground language agents in visual embodied environments.

Copied to clipboard

Liang Zhang, Anwen Hu, Haiyang Xu, Ming Yan, Yichen Xu, Qin Jin, Ji Zhang, Fei Huang

Revisiting Entropy in Reinforcement Learning for Large Reasoning Models (2026.findings-acl)

Challenge:	Recent studies have shown that multimodal large language models can be useful for chart understanding, but their size limits their use in resource-constrained environments.
Approach:	They propose an efficient multimodal large language model with only 3B parameters for chart understanding.
Outcome:	The proposed model outperforms several chart-understanding MLLMs with up to 13B parameters on ChartQA, Chart-to-Text, Chart to Table, OpenCQA, and ChartX.

Copied to clipboard

Renren Jin, Pengzhi Gao, Yuqi Ren, Zhuowen Han, Tongxuan Zhang, Wuwei Huang, Wei Liu, Jian Luan, Deyi Xiong

From Prediction to Intervention: Personalized Meal-Level Glucose Regulation via an LLM Agent (2026.findings-acl)

Challenge:	Reinforcement learning with verifiable rewards (RLVR) has emerged as a paradigm for enhancing the reasoning capabilities of large language models.
Approach:	They propose a positive-advantage reweighting approach that regulates model entropy by adjusting the loss weights assigned to tokens with positive advantages during RLVR training.
Outcome:	The proposed approach regulates model entropy by adjusting loss weights assigned to tokens with positive advantages during RLVR training while maintaining competitive performance.

Copied to clipboard

Mingyu Huang, Weiqing Min, Ying Jin, Yilin Wang, Shuqiang Jiang

Challenge:	Existing approaches to individualized glucose regulation are generic and do not account for individual-specific glucose dynamics.
Approach:	They propose a physio-feedback agentic loop that integrates individualized absorption modeling with dietary intervention to regulate glucose response.
Outcome:	The proposed system improves prediction accuracy and reduces glucose excursions.

Harder Task Needs More Experts: Dynamic Routing in MoE Models (2024.acl-long)

Copied to clipboard

Quzhe Huang, Zhenwei An, Nan Zhuang, Mingxu Tao, Chen Zhang, Yang Jin, Kun Xu, Kun Xu, Liwei Chen, Songfang Huang, Yansong Feng

The Art of SOCRATIC QUESTIONING: Recursive Thinking with Large Language Models (2023.emnlp-main)

Challenge:	Unlike existing MoE approaches that rely on fixed TopK Routing, our dynamic expert selection framework dynamically allocates experts based on the confidence level in expert selection for each input.
Approach:	They propose a dynamic expert selection framework that dynamically allocates experts based on the confidence level in expert selection for each input.
Outcome:	The proposed method achieves an average improvement of 0.7% with less than 90% activated parameters and outperforms dense models in QA and machine translation tasks.

Copied to clipboard

Jingyuan Qi, Zhiyang Xu, Ying Shen, Minqian Liu, Di Jin, Qifan Wang, Lifu Huang

Detection, Diagnosis, and Explanation: A Benchmark for Chinese Medial Hallucination Evaluation (2024.lrec-main)

Challenge:	Chain-of-Thought (CoT) prompting relies on the initial decisions, causing errors in early steps to accumulate and impact the final answers.
Approach:	They propose a divide-and-conquer style algorithm that leverages large language models to raise and answer sub-questions until collecting enough information to tackle the original one.
Outcome:	The proposed algorithm is more robust to errors and errors than CoT prompting and Tree-of-Thought prompting methods.

Copied to clipboard

Chengfeng Dou, Ying Zhang, Yanyuan Chen, Zhi Jin, Wenpin Jiao, Haiyan Zhao, Yu Huang

Semantically Consistent Data Augmentation for Neural Machine Translation via Conditional Masked Language Model (2022.coling-1)

Challenge:	Large Language Models (LLMs) have made significant progress in recent years, but their practical use is hindered by their tendency to generate hallucinations.
Approach:	They propose to use ICD-10 and MeSH to evaluate LLMs' ability to detect medical hallucinations and make accurate diagnoses in noisy environments.
Outcome:	The proposed benchmark can be used to evaluate LLMs’ ability to detect medical hallucinations, make accurate diagnoses in noisy conditions, and provide plausible explanations.

Copied to clipboard

Qiao Cheng, Jin Huang, Yitao Duan

Machine Translation

Challenge:	Neural network models have a large number of parameters to train, but data augmentation is relatively under-explored in natural language processing.
Approach:	They propose a bi-directional conditional Masked Language Model (CMLM) that can be conditional on both left and right contexts and the label.
Outcome:	The proposed method achieves the best performance on four translation datasets and yields up to 1.90 BLEU points over the baseline.

Internal Value Alignment in Large Language Models through Controlled Value Vector Activation (2025.acl-long)

Copied to clipboard

Haoran Jin, Meng Li, Xiting Wang, Zhihao Xu, Minlie Huang, Yantao Jia, Defu Lian

Characterizing the Impacts of Instances on Robustness (2023.findings-acl)

Challenge:	Existing LLMs do not possess consistent values, but many have been developed to align them at the behavioral level, including supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF).
Approach:	They propose a Controlled Value Vector Activation method that directly aligns the internal values of Large Language Models by interpreting how a value is encoded in their latent representations.
Outcome:	The proposed method achieves highest success rate across 10 basic values without hurting model performance and fluency, and ensures target values even with opposite and potentially malicious input prompts.

Copied to clipboard

Rui Zheng, Zhiheng Xi, Qin Liu, Wenbin Lai, Tao Gui, Qi Zhang, Xuanjing Huang, Jin Ma, Ying Shan, Weifeng Ge

Robustness in NLP

Challenge:	Existing defense approaches focus on developing new model structures or training algorithms, but they do little to tap the potential of training instances.
Approach:	They propose a method that can distinguish between robust and non-robust instances according to the model’s sensitivity to perturbations on individual instances during training.
Outcome:	The proposed method can distinguish between robust and non-robust instances according to the model’s sensitivity to perturbations on individual instances during training.

ReStyle-TTS: Relative and Continuous Style Control for Zero-Shot Speech Synthesis (2026.findings-acl)

Copied to clipboard

Haitao Li, Chunxiang Jin, Chenglin Li, Wenhao Guan, Zhengxing Huang, Xie Chen

From Capabilities to Performance: Evaluating Key Functional Properties of LLM Architectures in Penetration Testing (2025.emnlp-main)

Challenge:	Recent controllable zero-shot text-to-speech systems can synthesize speech for unseen speakers from a short reference audio clip, but they also inherit the speaking style present in the reference.
Approach:	They propose a framework that enables continuous and reference-relative style control in zero-shot text-to-speech systems by combining style-specific LoRAs with Orthogonal LoRA Fusion.
Outcome:	The proposed framework reduces the model's dependence on reference style while preserving text fidelity while maintaining intelligibility and speaker timbre.

Copied to clipboard

Lanxiao Huang, Daksh Dave, Tyler Cody, Peter A. Beling, Ming Jin

NL2Lean: Translating Natural Language into Lean 4 through Multi-Aspect Reinforcement Learning (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) have been explored for automating or enhancing penetration testing tasks, but their effectiveness and reliability remain open questions.
Approach:	They evaluate multiple LLM-based agents across realistic penetration testing scenarios . they also examine impact of core functional capabilities on agent success .
Outcome:	The proposed models improve agent performance in multi-step and real-time penetration testing scenarios.

Copied to clipboard

Yue Fang, Shaohan Huang, Xin Yu, Haizhen Huang, Zihan Zhang, Weiwei Deng, Furu Wei, Feng Sun, Qi Zhang, Zhi Jin

Machine Translation

Challenge:	Existing formal proof assistants rely on instruction tuning and lack fine-grained structural and semantic alignment.
Approach:	They propose a reinforcement learning framework that enables LLMs to translate natural language into formal language such as Lean 4 . they use a model with basic translation ability to refine the model's reinforcement learning .
Outcome:	The proposed method outperforms baseline models on NL-to-Lean 4 tasks.

Contrastive Token-Wise Meta-Learning for Unseen Performer Visual Temporal-Aligned Translation (2023.findings-acl)

Copied to clipboard

Linjun Li, Tao Jin, Xize Cheng, Ye Wang, Wang Lin, Rongjie Huang, Zhou Zhao

Machine Translation

Challenge:	a novel generalization framework for visual temporal-aligned translation is proposed to transfer recognition skills to unseen performers . ambiguity in the visual sequence can hinder current methods for visual language translation .
Approach:	They propose a generalizable framework to transfer recognition skills to unseen performers . they use visual temporal-aligned translation to generate multiple words autoregressively .
Outcome:	The proposed framework is generalized to transfer recognition skills to unseen performers . it is compared with existing methods on lipreading and fingerspelling datasets .

MLeVLM: Improve Multi-level Progressive Capabilities based on Multimodal Large Language Model for Medical Visual Question Answering (2024.findings-acl)

Copied to clipboard

Dexuan Xu, Yanyuan Chen, Jieyi Wang, Yue Huang, Hanpin Wang, Zhi Jin, Hongxing Wang, Weihua Yue, Jing He, Hang Li, Yu Huang

S2-MAD: Breaking the Token Barrier to Enhance Multi-Agent Debate Efficiency (2025.naacl-long)

Challenge:	Existing MVQA models ignore multi-level progressive capabilities due to unspecific data and plain architecture.
Approach:	They propose a multi-level visual language model for medical visual question answering (MVQA) which covers multi- level questions and answers as well as reasoning processes from visual clues to semantic cognition.
Outcome:	The proposed model outperforms existing medical multimodal large language models on a multi-level instruction dataset and a feature alignment module.

Copied to clipboard

Yuting Zeng, Weizhe Huang, Lei Jiang, Tongxuan Liu, XiTai Jin, Chen Tianying Tiana, Jing Li, Xiaohua Xu

Can You Tell Me How to Get Past Sesame Street? Sentence-Level Pretraining Beyond Language Modeling (P19-1)

Challenge:	Large language models exhibit limitations when handling complex mathematical reasoning and logical inference tasks.
Approach:	They propose a sparsification strategy to reduce token costs within Multi-agent Debate (MAD) this strategy minimizes ineffective exchanges of information and unproductive discussions among agents .
Outcome:	The proposed approach reduces token costs by up to 94.5% while maintaining performance degradation below 2.0%.

Copied to clipboard

Alex Wang, Jan Hula, Patrick Xia, Raghavendra Pappagari, R. Thomas McCoy, Roma Patel, Najoung Kim, Ian Tenney, Yinghui Huang, Katherin Yu, Shuning Jin, Berlin Chen, Benjamin Van Durme, Edouard Grave, Ellie Pavlick, Samuel R. Bowman

TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation (2024.findings-acl)

Challenge:	State-of-the-art models in natural language processing (NLP) often incorporate sentence encoder functions which generate a sequence of vectors intended to represent the in-context meaning of each word in an input text.
Approach:	They conduct the first large-scale systematic study of candidate pretraining tasks, comparing 19 different tasks as alternatives and complements to language modeling.
Outcome:	The proposed model can be used to train sentences on language modeling tasks.

Copied to clipboard

Xize Cheng, Rongjie Huang, Linjun Li, Zehan Wang, Tao Jin, Aoxiong Yin, Chen Feiyang, Xinyu Duan, Baoxing Huai, Zhou Zhao

MASSW: A New Dataset and Benchmark Tasks for AI-Assisted Scientific Workflows (2025.findings-naacl)

Challenge:	Existing methods for talking head translation rely on cascading, resulting in delays and cascadic errors.
Approach:	They propose a model for talking head translation, TransFace, which can translate audio-visual speech into audio-visual speech in other languages.
Outcome:	The proposed model can translate audio-visual speech into audio-visual speech in other languages.

Copied to clipboard

Xingjian Zhang, Yutong Xie, Jin Huang, Jinge Ma, Zhaoying Pan, Qijia Liu, Ziyang Xiong, Tolga Ergen, Dongsub Shim, Honglak Lee, Qiaozhu Mei

Challenge:	Scientific innovation is driven by detailed workflows, which include critical steps such as contextualizing literature, generating ideas, validating ideas, and planning new research.
Approach:	They propose to use large language models to extract five key aspects from scientific publications to optimize scientific workflows.
Outcome:	The proposed dataset includes more than 152,000 peer-reviewed publications from 17 leading computer science conferences spanning the past 50 years.

Automatic Reconstruction of Ancient Chinese Pronunciations (2024.findings-emnlp)

Copied to clipboard

Zhige Huang, Haoan Jin, Mengyue Wu, Kenny Zhu

Syntactic Text Processing

Challenge:	A human language is comprised of a pronunciation system and a writing system, both evolving and changing over time.
Approach:	They reformulate existing phonetic rules into a dataset of 70,943 entries for 17,001 Chinese characters and use it to perform a temporal prediction task.
Outcome:	The transformer-based model significantly advances the digitization and computational reconstruction of ancient Chinese phonology, providing a more complete and temporally contextualized resource for computational linguistics and historical research.

Rapid Diffusion: Building Domain-Specific Text-to-Image Synthesizers with Fast Inference Speed (2023.acl-industry)

Copied to clipboard

Bingyan Liu, Weifeng Lin, Zhongjie Duan, Chengyu Wang, Wu Ziheng, Zhang Zipeng, Kui Jia, Lianwen Jin, Cen Chen, Jun Huang

InternalInspector I2: Robust Confidence Estimation in LLMs through Internal States (2024.findings-emnlp)

Challenge:	Text-to-Image Synthesis (TIS) aims to generate images based on textual inputs . but, current diffusion-based models lack entity knowledge and low inference speed .
Approach:	They propose a framework for training and deploying latent diffusion models with rich entity knowledge injected and optimized networks.
Outcome:	The proposed framework improves image quality and inference speed and can be used in industrial applications.

Copied to clipboard

Mohammad Beigi, Ying Shen, Runing Yang, Zihao Lin, Qifan Wang, Ankith Mohan, Jianfeng He, Ming Jin, Chang-Tien Lu, Lifu Huang

DiPT: Enhancing LLM Reasoning through Diversified Perspective-Taking (2025.findings-naacl)

Challenge:	Large Language Models (LLMs) often struggle with generating reliable outputs, often producing high-confidence inaccuracies known as hallucinations.
Approach:	They propose a framework that leverages contrastive learning on internal states including attention states, feed-forward states, and activation states of all layers to enhance confidence estimation in LLMs.
Outcome:	The framework outperforms existing methods in the hallucination detection benchmark HaluEval and the previous methods at the same time.

Copied to clipboard

Hoang Anh Just, Mahavir Dabas, Lifu Huang, Ming Jin, Ruoxi Jia

Traces in the Brain: Neural Evidence for Syntactic Movement in English and Chinese (2026.findings-acl)

Challenge:	Existing work on improving language model reasoning typically explores a single solution path, which can be prone to errors.
Approach:	They propose a novel approach that incorporates diversified viewpoints into existing reasoning methods to improve their reasoning performance.
Outcome:	The proposed approach can be flexibly integrated into existing models that focus on a single reasoning approach, enhancing their reasoning performance and stability when presented with paraphrased problems.

Copied to clipboard

Yuhan Huang, Zhengwu Ma, Yuqi Jin, Beth Chan, Zheng Shen, Jackie Yan-Ki Lai, John T. Hale, Jixing Li

Syntactic Text Processing

Challenge:	Syntactic movement is a core concept in generative linguistics to account for word-order variation and long-distance dependencies.
Approach:	They annotated every sentence in the audiobook The Little Prince using X-bar style tree annotations.
Outcome:	The proposed model shows that deep structure significantly predicts neural responses in English but not in Chinese.

DiffChat: Learning to Chat with Text-to-Image Synthesis Models for Interactive Image Creation (2024.findings-acl)

Copied to clipboard

Jiapeng Wang, Chengyu Wang, Tingfeng Cao, Jun Huang, Lianwen Jin

LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference (2024.findings-emnlp)

Challenge:	a novel method to align Large Language Models to "chat" with prompt-as-input Text-to-Image Synthesis models is proposed . a user-specified instruction can be used to create a high quality image .
Approach:	They propose a method to align Large Language Models to "chat" with prompt-as-input Text-to-Image Synthesis models for interactive image creation.
Outcome:	The proposed method can exhibit superior performance than baseline models and strong competitors based on automatic and human evaluations.

Copied to clipboard

Zhongwei Wan, Ziang Wu, Che Liu, Jinfa Huang, Zhihong Zhu, Peng Jin, Longyue Wang, Li Yuan

Visual Data in NLP

Challenge:	Long-context Multimodal Large Language Models (MLLMs) require substantial computational resources for inference . the growth of their multimodal Key-Value (KV) cache challenges memory and time efficiency.
Approach:	They propose a fine-tuning-free approach that efficiently reduces the multimodal KV cache size while maintaining performance comparable to a full cache.
Outcome:	The proposed method reduces the multimodal KV cache size while maintaining performance comparable to a full cache.

Can GRPO Boost Complex Multimodal Table Understanding? (2025.emnlp-main)

Copied to clipboard

Xiaoqiang Kang, Shengen Wu, Zimu Wang, Yilin Liu, Xiaobo Jin, Kaizhu Huang, Wei Wang, Yutao Yue, Xiaowei Huang, Qiufeng Wang

Can AI Revise Research Papers with Human Review Feedback? An Empirical Study and Benchmark (2026.findings-acl)

Challenge:	Existing table understanding methods struggle with low initialization accuracy and coarse rewards in tabular contexts.
Approach:	They propose a three-stage RL framework that enhances multimodal table understanding through: (1) Warm-up that prompts initial perception and reasoning capabilities; (2) Perception Alignment GRPO (PA-GRPO); (3) Hint-Completion GR PO (HC-GRP);
Outcome:	The proposed framework outperforms existing models on held-in and held-out datasets, outperforming SFT and GRPO largely.

Copied to clipboard

Zihan Luo, Hong Huang, Jianxun Lian, Yu Chang, Xing Xie, Hai Jin

Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation (2025.findings-acl)

Challenge:	Large Language Models (LLMs) are fundamentally reshaping the scientific landscape, transitioning the role of AI from passive tools to active partners within a new paradigm of Human-AI collaboration.
Approach:	They propose a benchmark to evaluate the ability of Large Language Models to improve papers with human feedback.
Outcome:	The proposed benchmark tests the skills of Large Language Models (LLMs) on paper interpretation, experimental implementation, and paper formulation, using authors’ camera-ready versions as natural human baselines.

Copied to clipboard

Qiyue Gao, Xinyu Pi, Kevin Liu, Junrong Chen, Ruolan Yang, Xinqi Huang, Xinyu Fang, Lu Sun, Gautham Kishore, Bo Ai, Stone Tao, Mengyang Liu, Jiaxi Yang, Chao-Jung Lai, Chuanyang Jin, Jiannan Xiang, Benhao Huang, Zeming Chen, David Danks, Hao Su, Tianmin Shu, Ziqiao Ma, Lianhui Qin, Zhiting Hu

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

Challenge:	Recent studies have evaluated and shown limitations in specific capabilities such as visual understanding, but a systematic evaluation of VLMs’ fundamental WM abilities remains absent.
Approach:	They propose a framework that assesses perception and prediction to provide an atomic evaluation of VLMs as WMs.
Outcome:	The proposed framework assesses perception and prediction abilities on 15 latest VLMs and compares them to human-level models.

Copied to clipboard

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

Parrot: A Training Pipeline Enhances Both Program CoT and Natural Language CoT for Reasoning (2025.emnlp-main)

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

Senjie Jin, Lu Chen, Zhiheng Xi, Yuhui Wang, Sirui Song, Yuhao Zhou, Xinbo Zhang, Peng Sun, Hong Lu, Tao Gui, Qi Zhang, Xuanjing Huang

Reusing Transferable Weight Increments for Low-resource Style Generation (2024.emnlp-main)

Challenge:	Existing work focuses on enabling models to generate natural language chain-of-thought rationales or leverage executable and verifiable code, such as Python.
Approach:	They propose a novel training pipeline that integrates sequential P-CoT and N-Co T generation and a subtask hybrid training strategy to facilitate natural language transferability.
Outcome:	The proposed training pipeline improves both N-CoT and P-Co T performance over the RL baseline.

Copied to clipboard

Chunzhen Jin, Eliot Huang, Heng Chang, Yaqi Wang, Peng Cao, Osmar Zaiane

Low-Resource NLP

Challenge:	Text style transfer (TST) is crucial in natural language processing, aiming to endow text with a new style without altering its meaning.
Approach:	They propose a framework to use style features in weight increments to transfer low-resource styles effectively.
Outcome:	The proposed framework achieves remarkable performance across different backbones, achieving particularly effective results in low-resource scenarios.

Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning (2024.findings-acl)

Copied to clipboard

Zhiyang Xu, Chao Feng, Rulin Shao, Trevor Ashby, Ying Shen, Di Jin, Yu Cheng, Qifan Wang, Lifu Huang

On the Universal Adversarial Perturbations for Efficient Data-free Adversarial Detection (2023.findings-acl)

Challenge:	Recent vision-language models (VLMs) have shown impressive capabilities as general visual assistants, but there are two challenges to their performance: (1) lacking task diversity in pretraining and visual instruction tuning; (2) annotation error and bias in GPT-4 synthesized instruction tuning data.
Approach:	They propose a two-stage instruction tuning framework that fine tunes VLMs firstly and further tuned on GPT-4 synthesized data.
Outcome:	The proposed framework outperforms the traditional single-stage visual instruction tuning framework and achieves state-of-the-art performance across a wide range of multi-modal evaluation benchmarks.

Copied to clipboard

SongYang Gao, Shihan Dou, Qi Zhang, Xuanjing Huang, Jin Ma, Ying Shan

FashionKLIP: Enhancing E-Commerce Image-Text Retrieval with Fashion Multi-Modal Conceptual Knowledge Graph (2023.acl-industry)

Challenge:	Existing adversarial detection methods require access to training data, which brings noteworthy concerns regarding privacy leakage and generalizability.
Approach:	They propose a data-agnostic adversarial detection framework which induces different responses between normal and adversarials to UAPs.
Outcome:	The proposed framework achieves competitive detection performance on various text classification tasks, and maintains equivalent time consumption to normal inference.

Copied to clipboard

Xiaodan Wang, Chengyu Wang, Lei Li, Zhixu Li, Ben Chen, Linbo Jin, Jun Huang, Yanghua Xiao, Ming Gao

Uncovering Hidden Correctness in LLM Causal Reasoning via Symbolic Verification (2026.eacl-long)

Challenge:	Recent advances in visual-language pre-trained (VLP) models have greatly improved cross-modal retrieval performance . however, the fine-grained interactions between objects from different modalities are far from well-established . e-commerce domain lacks sufficient training data and fine-granular cross-modulal knowledge .
Approach:	They propose a visual-language pre-trained (VLP) image-text retrieval model that integrates cross-modal knowledge into the model to improve performance.
Outcome:	The proposed model improves performance on e-commerce image-text retrieval task by a large margin.

Copied to clipboard

Paul He, Yinya Huang, Mrinmaya Sachan, Zhijing Jin

CocaCLIP: Exploring Distillation of Fully-Connected Knowledge Interaction Graph for Lightweight Text-Image Retrieval (2023.acl-industry)

Challenge:	Large language models (LLMs) are increasingly being applied to causal reasoning tasks.
Approach:	They propose a symbolic verification framework that checks whether LLM-generated causal expressions are derivable from a given causal graph using do-calculus and probability theory.
Outcome:	The proposed framework can recover correct answers that would otherwise be marked incorrect due to superficial differences.

Copied to clipboard

Jiapeng Wang, Chengyu Wang, Xiaodan Wang, Jun Huang, Lianwen Jin

Dual Low-Rank Multimodal Fusion (2020.findings-emnlp)

Challenge:	Existing methods for text-image retrieval are limited to edge devices and real-time situations due to the substantial indexing and inference time.
Approach:	They propose a fully-Connected knowledge interaction graph technique for cross-modal pre-training distillation.
Outcome:	The proposed method achieves SOTA performances on the widely-used Flickr30K and MSCOCO benchmarks under the lightweight setting.

Copied to clipboard

Tao Jin, Siyu Huang, Yingming Li, Zhongfei Zhang

Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories (2025.emnlp-main)

Challenge:	Existing tensor-based fusion methods make poor use of fine-grained temporal dynamics of multimodal sequential features.
Approach:	They propose a novel multimodal fusion method called Fine-Grained Temporal Low-Rank Multimodal Fusion that uses low-rank tensor approximation along dual dimensions of input features.
Outcome:	The proposed method outperforms the state-of-the-art tensor-based methods with a similar computational complexity.

Copied to clipboard

Mohammad Beigi, Ying Shen, Parshin Shojaee, Qifan Wang, Zichao Wang, Chandan K. Reddy, Ming Jin, Lifu Huang

ReInceptionE: Relation-Aware Inception Network with Joint Local-Global Structural Information for Knowledge Graph Embedding (2020.acl-main)

Challenge:	Existing studies show that large language models inadvertently foster sycophancy . scophancies are a tendency of models to blindly conform to user preferences without critical reasoning or self-reflection.
Approach:	They propose a method to reduce sycophancy by combining uncertainty-aware Monte Carlo tree search and progress-based reinforcement learning.
Outcome:	The proposed model outperforms baseline models in effectively reducing sycophancy while maintaining performance on out-of-distribution inputs.

Copied to clipboard

Zhiwen Xie, Guangyou Zhou, Jin Liu, Jimmy Xiangji Huang

Towards Explainable Diagnosis: A Self-learned Explanatory Knowledge Base Approach (2026.acl-long)

Challenge:	Existing knowledge graph embedding methods are limited in their expressiveness and lack structural information in the embeddable space.
Approach:	They propose to use a relation-aware network to learn query embedding . they first explore the Inception network to further increase interactions between head and relation embedders .
Outcome:	The proposed network improves performance on WN18RR and FB15k-237 datasets.

Copied to clipboard

Dongqi Huang, Tong Zhou, Zhuoran Jin, Shenghui Shi, null Maoyujiao, Kang Liu, Jun Zhao, Yubo Chen

Explainability & Interpretability in NLP

Challenge:	Large language models (LLMs) have great potential to facilitate explainable diagnosis, but their effectiveness is often constrained by insufficient diagnostic expertise.
Approach:	They propose a unified LLM-based framework for faithful and explainable diagnosis that builds a high-quality diagnostic knowledge base through a record-driven explanation learning paradigm.
Outcome:	The proposed framework outperforms baselines on the DiReCT and JAMA benchmarks and improves the explanation completeness metric from 64.5% to 76.9% over the best existing methods.

LogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation (2026.acl-long)

Copied to clipboard

Yilin Xiao, Jin Chen, Qinggang Zhang, Yujing Zhang, Chuang Zhou, Longhao Yang, Lingfei Ren, Xin Yang, Xiao Huang

Learning Query Adaptive Anchor Representation for Inductive Relation Prediction (2023.findings-acl)

Challenge:	Graph-based Retrieval-Augmented Generation (GraphRAG) enhances the reasoning capabilities of Large Language Models (LLMs) however, traditional RAG attacks are difficult to pose an effective threat to GraphRAg systems.
Approach:	They propose a novel attack framework that targets logical reasoning rather than injecting false contents into GraphRAG systems by grounding their responses in structured knowledge graphs.
Outcome:	The proposed framework outperforms state-of-the-art attacks on GraphRAG systems in both effectiveness and stealth.

Copied to clipboard

Zhiwen Xie, Yi Zhang, Jin Liu, Guangyou Zhou, Jimmy Huang

Structured Data in NLP

Challenge:	Existing methods to infer the missing links between entities are limited to the transductive setting . Query Adaptive Anchor Representation (QAAR) model is based on entity-independent features .
Approach:	They propose a query adaptive anchor representation model which extracts one opening subgraph and performs reasoning by one time for all candidate triples.
Outcome:	The proposed model outperforms state-of-the-art models in relation prediction task.

Entropy-Based Vocabulary Substitution for Incremental Learning in Multilingual Neural Machine Translation (2022.emnlp-main)

Copied to clipboard

Kaiyu Huang, Peng Li, Jin Ma, Yang Liu

Multilinguality

Challenge:	Existing methods to update a multilingual model with new language pairs are expensive and time-consuming.
Approach:	They propose an entropy-based vocabulary substitution method that walks through new language pairs for incremental learning while remaining the size of the original vocabulary.
Outcome:	The proposed method achieves better performance and saves excess overhead in a multilingual machine translation task.

VRPO: Rethinking Value Modeling for Robust RL under Noisy Supervision in LLM Post-Training (2026.acl-long)

Copied to clipboard

Dingwei Zhu, Shihan Dou, Zhiheng Xi, Senjie Jin, Guoqiang Zhang, Jiazheng Zhang, Junjie Ye, Mingxu Chai, Enyu Zhou, Ming Zhang, Yuhui Wang, Caishuang Huang, Chenhao Huang, Yunke Zhang, Yuran Wang, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang

Robustness in NLP

Challenge:	Reinforcement Learning (RL) in real-world environments often suffers from ambiguous or incomplete supervision.
Approach:	They propose a framework that enhances value modeling for robust RL in LLM post-training by integrating auxiliary losses guided by entropy and perplexity from a frozen language model and variational information bottleneck.
Outcome:	The proposed framework outperforms baselines on multi-turn dialogue, math reasoning, and science QA with rule-based and model-based rewards.

COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning (2025.findings-naacl)

Copied to clipboard

Yuelin Bai, Xeron Du, Yiming Liang, Leo Jin, Junting Zhou, Ziqiang Liu, Feiteng Fang, Mingshan Chang, Tianyu Zheng, Xincheng Zhang, Nuo Ma, Zekun Moore Wang, Ruibin Yuan, Haihong Wu, Hongquan Lin, Wenhao Huang, Jiajun Zhang, Chenghua Lin, Jie Fu, Min Yang, Shiwen Ni, Ge Zhang

On Construction of the ASR-oriented Indian English Pronunciation Dictionary (2020.lrec-1)

Challenge:	Existing datasets for Chinese instruction tuning are not well-aligned with Chinese users’ interaction patterns.
Approach:	They propose to use Chinese instruction tuning datasets to improve instruction fine-tuning for Chinese users.
Outcome:	The proposed dataset shows that Chinese models achieve competitive performance in diverse benchmarks.

Copied to clipboard

Xian Huang, Xin Jin, Qike Li, Keliang Zhang

Speech & Audio in NLP

Challenge:	Indian English (IE) has distinctive characteristics, especially phonologically, from other varieties of English.
Approach:	They build a small IE spontaneous speech corpus and use a linguistically-guided IE pronunciation dictionary to apply it to IE.
Outcome:	The proposed system performs better on IE spontaneous speech data than the one trained with CMUdict.

Your Inference Request Will Become a Black Box: Confidential Inference for Cloud-based Large Language Models (2026.acl-long)

Copied to clipboard

Chung-ju Huang, Huiqiang Zhao, Yuanpeng He, Lijian Li, Wenpin Jiao, Zhi Jin, Peixuan Chen, Leye Wang

A Contextual Alignment Enhanced Cross Graph Attention Network for Cross-lingual Entity Alignment (2020.coling-main)

Challenge:	Existing approaches fail to ensure privacy, maintain model performance, and preserve computational efficiency simultaneously.
Approach:	They propose a confidential inference framework that partitions the LLM pipeline between a client-verified Confidential Virtual Machine (CVM) and the public cloud to protect client data without compromising the cloud’s model intellectual property or inference quality.
Outcome:	The proposed framework can defend against state-of-the-art token inference attacks while preserving model privacy, performance, and efficiency.

Copied to clipboard

Zhiwen Xie, Runjie Zhu, Kunsong Zhao, Jin Liu, Guangyou Zhou, Jimmy Xiangji Huang

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

Challenge:	Existing methods for cross-lingual entity alignment ignore useful pre-aligned links between two KGs.
Approach:	They propose a novel method that jointly learns embeddings in different KGs by propagating cross-KG information through pre-aligned seed alignments.
Outcome:	The proposed method achieves remarkable performance gains on three benchmark cross-lingual entity alignment datasets.

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.

Data-Efficiently Learn Large Language Model for Universal 3D Scene Perception (2025.findings-naacl)

Copied to clipboard

Zehan Wang, Haifeng Huang, Yang Zhao, Ziang Zhang, Tao Jin, Zhou Zhao

RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization (2026.acl-long)

Challenge:	Existing methods for 3D scene understanding are limited to specific downstream tasks, hindering their practicality in real-world applications.
Approach:	They propose a 3D visual perceptual ability and advanced reasoning capabilities for 3D scenes by aligning 3D representations into the feature space of advanced LLMs.
Outcome:	The proposed system achieves a 82.2% relative score compared with state-of-the-art methods with limited data.

Copied to clipboard

Yihong Dong, Xue Jiang, Yongding Tao, Huanyu Liu, Kechi Zhang, Lili Mou, Rongyu Cao, Yingwei MA, Jue Chen, Binhua Li, Zhi Jin, Fei Huang, Yongbin Li, Ge Li

Knowledge Transfer in Incremental Learning for Multilingual Neural Machine Translation (2023.acl-long)

Challenge:	Reinforcement Learning with Verifiable Reward (RLVR) has significantly advanced the complex reasoning abilities of Large Language Models (LLMs).
Approach:	They propose a hybrid-policy optimization approach that synergizes internal exploitation with external data to achieve stronger reasoning capabilities.
Outcome:	The proposed approach achieves state-of-the-art performance on six math reasoning benchmarks and superior performance on out-of distribution reasoning tasks.

Copied to clipboard

Kaiyu Huang, Peng Li, Jin Ma, Ting Yao, Yang Liu

Multilinguality

Challenge:	Existing studies focus on overcoming catastrophic forgetting on original language pairs while lacking encouragement to learn new knowledge from incremental learning.
Approach:	They propose a knowledge transfer method that can adapt original MNMT models to diverse incremental language pairs by flexibly introducing knowledge from external models into original models, which encourages the models to learn new language pairs.
Outcome:	The proposed method outperforms baselines on multiple languages while maintaining performance on original language pairs.

RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter (2024.findings-acl)

Copied to clipboard

Meng Cao, Haoran Tang, Jinfa Huang, Peng Jin, Can Zhang, Ruyang Liu, Long Chen, Xiaodan Liang, Li Yuan, Ge Li

Green & Sustainable NLP

Challenge:	Text-Video Retrieval (TVR) aims to align relevant video content with natural language queries.
Approach:	They propose to conduct efficient text-video Retrieval with a salient-and-correlated AdaPter . they propose a low-rank modulation module to refine per-image features from frozen CLIP backbone .
Outcome:	Experiments on four TVR datasets show that the proposed method performs better than other methods.

Tasty Burgers, Soggy Fries: Probing Aspect Robustness in Aspect-Based Sentiment Analysis (2020.emnlp-main)

Copied to clipboard

Xiaoyu Xing, Zhijing Jin, Di Jin, Bingning Wang, Qi Zhang, Xuanjing Huang

Sentiment Analysis

Challenge:	Existing ABSA test sets cannot be used to distinguish the sentiment of the target aspect from the non-target aspect.
Approach:	They propose a simple but effective approach to enrich ABSA test sets by disentangle the confounding sentiments of non-target aspects from the target aspect’s sentiment.
Outcome:	The proposed model can distinguish the sentiment of the non-target aspects from the target aspect’s sentiment by using the Aspect Robustness Test Set (ARTS).

LLEOT: A Privacy-Enhancing Offsite Tuning Framework via Loss Landscape Elevation (2026.findings-acl)

Copied to clipboard

Jin Zhong, Jinglin Liang, Tongtong Yang, Zijian Xie, Shuangping Huang, Hanlin Gu