Papers by Jiaqi Wang

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings (2025.findings-acl)

Challenge:	Existing methods rely on entity vector matching, but the purpose of the question is abstract and difficult to match with specific entities. Existing approaches rely only on entity-vector matching, and there is a problem with multi-hop reasoning.
Approach:	They propose a framework that constructs reasoning paths from purposes back to conditions using the KG ontology.
Outcome:	Experiments on the WebQSP and CWQ datasets show that ORT significantly improves the capability of large language models in knowledge graph question answering tasks (KGQA).

Copied to clipboard

Yubo Ma, Jinsong Li, Yuhang Zang, Xiaobao Wu, Xiaoyi Dong, Pan Zhang, Yuhang Cao, Haodong Duan, Jiaqi Wang, Yixin Cao, Aixin Sun

Representation Learning

Challenge:	Visualized Document Retrieval (VDR) uses large vision-language models to encode document pages into embeddings.
Approach:	They evaluate methods to reduce patch embeddings per page while minimizing performance degradation.
Outcome:	The proposed method maintains 98.2% of retrieval performance with only 11.8% of original memory usage and preserves 94.6% effectiveness at 2% memory footprint.

SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC (2024.findings-acl)

Copied to clipboard

Jinglong Luo, Yehong Zhang, Zhuo Zhang, Jiaqi Zhang, Xin Mu, Hui Wang, Yue Yu, Zenglin Xu

Unity in Diversity: Collaborative Pre-training Across Multimodal Medical Sources (2024.acl-long)

Challenge:	a growing number of cloud-based inference services are relying on SMPC to protect data privacy.
Approach:	They propose a framework for Privacy-Preserving Inference for Transformer models that eliminates exponential and maximum operations in PPI without sacrificing model performance.
Outcome:	The proposed framework outperforms MPCFormer in terms of performance and efficiency . it is 3.57 and 3.58 times faster than PUMA for BERTBASE and BERTLARGE .

Copied to clipboard

Xiaochen Wang, Junyu Luo, Jiaqi Wang, Yuan Zhong, Xiaokun Zhang, Yaqing Wang, Parminder Bhatia, Cao Xiao, Fenglong Ma

AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments (2026.acl-long)

Challenge:	Current pre-training techniques rely on a limited scope of medical data, limiting the range of downstream tasks.
Approach:	They propose a pre-training strategy that unifies patient data within individual sources and captures explicit and implicit correlations between patients across different sources.
Outcome:	The proposed strategy bridges the gap between multimodal medical sources by aggregating patient data within individual sources and capturing explicit and implicit correlations between patients across sources.

Copied to clipboard

Zhiheng Xi, Dingwen Yang, Jiaqi Liu, Jixuan Huang, Honglin Guo, Baodai Huang, Tinggang Chen, Qi Zhang, Zhonghang Lu, Chenyu Liu, Jiajun Sun, Jiazheng Zhang, Dingwei Zhu, Xin Guo, Junzhe Wang, Zhihao Zhang, Yuming Yang, Junjie Ye, Minghe Gao, Dongrui Liu, Jiaming Ji, Guohao Li, Tao Gui, Qi Zhang, Xuanjing Huang

CoRelation: Boosting Automatic ICD Coding through Contextualized Code Relation Learning (2024.lrec-main)

Challenge:	Existing benchmarks evaluate agents in simplified, idealized settings, relying on pre-packaged tool interfaces, overlooking critical steps, and assume inputs are clean and fully specified.
Approach:	They propose a framework that evaluates language agents in simplified, idealized settings . they show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 .
Outcome:	Experiments on 15 proprietary and open-source models show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 .

Copied to clipboard

Junyu Luo, Xiaochen Wang, Jiaqi Wang, Aofei Chang, Yaqing Wang, Fenglong Ma

Information Extraction & Text Mining

Challenge:	Existing methods for boosting ICD coding performance lack a model for complex code relations . current methods overlook the importance of context in clinical notes .
Approach:	They propose a contextualized and flexible framework to enhance learning of ICD code relations . they use clinical notes to model all possible code relations using a dependent learning paradigm .
Outcome:	The proposed approach improves on six public ICD coding datasets compared to state-of-the-art models.

Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models (2025.findings-acl)

Copied to clipboard

Xi Li, Ruofan Mao, Yusen Zhang, Renze Lou, Chen Wu, Jiaqi Wang

Towards Robustness of Text-to-SQL Models Against Natural and Realistic Adversarial Table Perturbation (2022.acl-long)

Challenge:	Large Language Models (LLMs) have demonstrated impressive capabilities across various domains, but are vulnerable to backdoor attacks.
Approach:	They propose a chain-of-scrutiny approach which leverages LLMs’ unique reasoning abilities to mitigate backdoor attacks.
Outcome:	The proposed model is well-suited for the popular API-only LLM deployments, enabling detection at minimal cost and with little data.

Copied to clipboard

Xinyu Pi, Bing Wang, Yan Gao, Jiaqi Guo, Zhoujun Li, Jian-Guang Lou

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

Challenge:	Existing Text-to-SQL parsers are vulnerable to perturbations in NL questions . we propose the Adversarial Table Perturbation (ATP) as a new attacking paradigm .
Approach:	They propose to use the Adversarial Table Perturbation to measure robustness of Text-to-SQL parsers against adversarial perturbations.
Outcome:	The proposed approach outperforms baseline methods in robustness evaluations on ADVETA and can be used in future projects.

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

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing (2026.acl-industry)

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

Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Zirui Tang, Boyu Niu, Yuanhong Zheng, Dongsheng Ma, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Fangdong Wang, Jingzhou Chen, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, RuiLiang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Dechen Lin, null Shenguanlin, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He

Green & Sustainable NLP

Challenge:	Document images are characterized by higher resolutions, denser content, and more complex structural layouts.
Approach:	They propose a 1.2B-parameter document parsing vision-language model that decouples layout analysis from local content recognition.
Outcome:	The proposed model surpasses general-purpose and domain-specific models on multiple benchmarks while maintaining significantly lower computational overhead.

Adaptive Preference Optimization with Uncertainty-aware Utility Anchor (2025.findings-emnlp)

Copied to clipboard

Xiaobo Wang, Zixia Jia, Jiaqi Li, Qi Liu, Zilong Zheng

Green & Sustainable NLP

Challenge:	Offline preference optimization methods are efficient for large language models (LLMs) alignment.
Approach:	They propose an offline preference optimization framework that estimates uncertainties from preference data . the method enables training even in scenarios where the data is unpaired .
Outcome:	The proposed method enables training even in scenarios where the data is unpaired .

SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition (2025.acl-long)

Copied to clipboard

Shuangrui Ding, Zihan Liu, Xiaoyi Dong, Pan Zhang, Rui Qian, Junhao Huang, Conghui He, Dahua Lin, Jiaqi Wang

Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures (2026.acl-long)

Challenge:	Creating lyrics and melodies in symbolic format requires expert knowledge of melody and an advanced understanding of lyrics.
Approach:	They introduce SongComposer, a music-specialized large language model that can create symbolic lyrics and melodies following instructions.
Outcome:	The proposed model outperforms existing models in symbolic song composition tasks.

Copied to clipboard

Yi Hu, Jiaqi Gu, Ruxin Wang, Zijun Yao, Hao Peng, Xiaobao Wu, Jianhui Chen, Muhan Zhang, Liangming Pan

Graph Reasoning Paradigm: Structured and Symbolic Reasoning with Topology-Aware Reinforcement Learning for Large Language Models (2026.acl-long)

Challenge:	Recent research has shown that reinforcement learning can elicit intriguing emergent reasoning behaviors.
Approach:	They propose a comprehensive survey of the mechanistic understanding of large reasoning models . they organize findings into three core dimensions: 1) training dynamics, 2) reasoning mechanisms, and 3) unintended behaviors.
Outcome:	This paper synthesizes the mechanistic understanding of large reasoning models into three dimensions . authors outline a roadmap for future studies including improved interpretability and methodologies .

Copied to clipboard

Runxuan Liu, Xianhao Ou, Xinyan Ma, Jiyuan Wang, Jiafeng Liang, Jiaqi Li, Tao He, Zheng Chu, Rongchuan Mu, Zekun Wang, Baoxin Wang, Dayong Wu, Ming Liu, Shijin Wang, Guoping Hu, Bing Qin

HelpSteer3: Human-Annotated Feedback and Edit Data to Empower Inference-Time Scaling in Open-Ended General-Domain Tasks (2025.acl-long)

Challenge:	Existing methods for long chain-of-thought (LCoT) are coarse-grained, reward hacking, and poor generalization.
Approach:	They propose a Long Chain-of-Thought (LCoT) model that integrates reinforcement learning with verifiable rewards with a process-aware verification approach.
Outcome:	The proposed model improves reasoning and code generation tasks while reducing the cost of training and performance bottlenecks.

Copied to clipboard

Zhilin Wang, Jiaqi Zeng, Olivier Delalleau, Daniel Egert, Ellie Evans, Hoo-Chang Shin, Felipe Soares, Yi Dong, Oleksii Kuchaiev

Challenge:	Inference-Time Scaling is critical to the success of recent models such as OpenAI o1 and DeepSeek R1 . however, many techniques require tasks to have answers that can be verified .
Approach:	They use data to train dedicated Feedback and Edit Models capable of inference-time scaling for open-ended tasks.
Outcome:	The proposed model can reach SoTA performance on Arena Hard at 92.7 as of 5 Mar 2025.

Reframe Your Life Story: Interactive Narrative Therapist and Innovative Moment Assessment with Large Language Models (2025.emnlp-main)

Copied to clipboard

Yi Feng, Jiaqi Wang, Wenxuan Zhang, Zhuang Chen, Shen Yutong, Xiyao Xiao, Minlie Huang, Liping Jing, Jian Yu

ChatHLS: Towards Systematic Design Automation and Optimization for High-Level Synthesis (2026.acl-long)

Challenge:	Existing approaches to mental health support lack realism and capture therapeutic progression over time.
Approach:	They propose a framework that simulates expert narrative therapists by planning therapeutic stages, guiding reflection levels, and generating contextually appropriate responses through retrieval-augmentation.
Outcome:	The proposed framework outperforms standard methods in quality and depth on 260 simulated clients and 230 human participants.

Copied to clipboard

Runkai Li, Jia Xiong, Xiuyuan He, Jieru Zhao, Jiaqi Lv, Haowen Fang, Lei Qi, Xi Wang

LRQuant: Learnable and Robust Post-Training Quantization for Large Language Models (2024.acl-long)

Challenge:	High-Level Synthesis (HLS) is a hardware design tool that can be used to design hardware from C-like languages, but its widespread adoption is limited by strict coding constraints and design-specific optimizations.
Approach:	They propose a multi-agent HLS design framework that leverages specialized LLMs for automated debugging and directive tuning.
Outcome:	The proposed framework outperforms Gemini-3-pro in debugging and speedups across various HLS kernels and neural network accelerators.

Copied to clipboard

Jiaqi Zhao, Miao Zhang, Chao Zeng, Ming Wang, Xuebo Liu, Liqiang Nie

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

Challenge:	Existing methods for post-training quantization (PTQ) are limited by the complexity of the quantization parameter and performance degradations when tested on unseen datasets.
Approach:	They propose a learnable smooth-based PTQ framework that allows for rapid adaptation during testing.
Outcome:	The proposed framework improves performance on unseen datasets and reduces memory constraints.

Copied to clipboard

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

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

Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding (2026.acl-long)

Copied to clipboard

Ke Ma, Jiaqi Tang, Bin Guo, Xueting Han, Ruonan Xu, Qingfeng He, Ziheng Wang, Xu Wang, Qifeng Chen, Zhiwen Yu, Yunhao Liu

ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection (2025.findings-acl)

Challenge:	Existing methods for streaming video understanding are query-agnostic and implicitly model video evidence.
Approach:	They propose a framework that establishes explicit, structured alignment between the accumulated video evidence and the query’s expected response conditions via scene graphs.
Outcome:	The proposed model achieves more interpretable and accurate response timing decisions on both proactive and reactive tasks.

Copied to clipboard

Jiaqi Li, Xinyi Dong, Yang Liu, Zhizhuo Yang, Quansen Wang, Xiaobo Wang, Song-Chun Zhu, Zixia Jia, Zilong Zheng

FEDKIM: Adaptive Federated Knowledge Injection into Medical Foundation Models (2024.emnlp-main)

Challenge:	ReflectEvo-460k is a large-scale, comprehensive, self-generated reflection dataset with broadened instructions and diverse multi-domain tasks.
Approach:	They propose a pipeline that iteratively generates self-reflection for self-training and a large-scale reflection dataset with broadened instructions and diverse multi-domain tasks.
Outcome:	The proposed pipeline improves Llama-3 reasoning ability by up to 71.2% and Mistral by upto 44.4%.

Copied to clipboard

Xiaochen Wang, Jiaqi Wang, Houping Xiao, Jinghui Chen, Fenglong Ma

Can Large Language Models Understand DL-Lite Ontologies? An Empirical Study (2024.findings-emnlp)

Challenge:	Existing foundation models are limited in access to diverse modalities and privacy regulations restrict the development of comprehensive foundation models.
Approach:	They propose a knowledge injection approach to extract and inject healthcare knowledge into medical foundation models to enhance their ability to handle multiple tasks and modalities.
Outcome:	The proposed method preserves privacy and enhances the model’s ability to handle complex medical tasks involving multiple modalities.

Copied to clipboard

Keyu Wang, Guilin Qi, Jiaqi Li, Songlin Zhai

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

Challenge:	Large language models (LLMs) have shown remarkable proficiency in understanding textual data and revolutionizing the field of natural language processing.
Approach:	They empirically analyze LLMs' capability of understanding Description Logic (DL) ontologies covering 6 representative tasks from syntactic and semantic aspects.
Outcome:	The proposed model can understand formal syntax and model-theoretic semantics of concepts and roles, but struggle with understanding TBox NI transitivity and handling ontologies with large ABoxes.

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

VideoPro: Adaptive Program Reasoning for Long Video Understanding (2026.acl-long)

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

Chenglin Li, Feng Han, Yikun Wang, Ruilin Li, Shuai Dong, Haowen Hou, Haitao Li, Qianglong Chen, Feng Tao, Jingqi Tong, Yin Zhang, Jiaqi Wang

InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model (2025.findings-acl)

Challenge:	Existing methods for understanding long videos are limited due to the sparsity of visual evidence relevant to a given query.
Approach:	They propose a framework that enables VideoLLMs to reason over long videos and refine their predictions through executable programs.
Outcome:	The proposed framework outperforms existing methods across long-video understanding benchmarks.

Copied to clipboard

Yuhang Zang, Xiaoyi Dong, Pan Zhang, Yuhang Cao, Ziyu Liu, Shengyuan Ding, Shenxi Wu, Yubo Ma, Haodong Duan, Wenwei Zhang, Kai Chen, Dahua Lin, Jiaqi Wang

Forget the Token and Pixel: Rethinking Gradient Ascent for Concept Unlearning in Multimodal Generative Models (2025.findings-acl)

Challenge:	Despite the promising performance of Large Vision Language Models, they sometimes generate incorrect outputs.
Approach:	They propose a multi-modal reward model that aligns LVLMs with human preferences.
Outcome:	The proposed model achieves excellent results on the latest multi-modal reward model benchmark and shows competitive performance on text-only reward model.

Copied to clipboard

Jiaqi Li, Chuanyi Zhang, Miaozeng Du, Hui Zhang, Yongrui Chen, Qianshan Wei, Junfeng Fang, Ruipeng Wang, Sheng Bi, Guilin Qi

Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better (2026.findings-acl)

Challenge:	Gradient Ascent (GA) has emerged as a promising approach for concept unlearning in Multimodal Generative Models (MGMs).
Approach:	They propose a novel approach that selectively applies GA to targeted Conceptual Knowledge while preserving Natural Knowledge through Gradient Descent (GD).
Outcome:	The proposed approach removes Conceptual Knowledge and inadvertently diminishes Natural Knowledge, resulting in utility degradation.

Copied to clipboard

Dianyi Wang, Wei Song, Yikun Wang, Siyuan Wang, Kaicheng Yu, Zhongyu Wei, Jiaqi Wang

BrainECHO: Semantic Brain Signal Decoding through Vector-Quantized Spectrogram Reconstruction for Whisper-Enhanced Text Generation (2025.findings-acl)

Challenge:	Typical large vision-language models emphasize vision-to-language alignment while overlooking fine-grained visual information.
Approach:	They introduce autoregressive semantic visual reconstruction (ASVR) that enables joint learning of visual and textual modalities within a unified autoregression framework.
Outcome:	The proposed model improves baselines and multimodal understanding benchmarks by 2-3%.

Copied to clipboard

Jilong Li, Zhenxi Song, Jiaqi Wang, Meishan Zhang, Honghai Liu, Min Zhang, Zhiguo Zhang

MIRTT: Learning Multimodal Interaction Representations from Trilinear Transformers for Visual Question Answering (2021.findings-emnlp)

Challenge:	Current EEG/MEG-to-text decoding systems rely on teacher-forcing methods . pre-trained large language models are over-dominant in decoding text from brain activity .
Approach:	They propose a framework that employs decoupled representation learning to achieve state-of-the-art performance on EEG and MEG datasets.
Outcome:	The proposed framework achieves state-of-the-art performance on EEG and MEG datasets.

Copied to clipboard

Junjie Wang, Yatai Ji, Jiaqi Sun, Yujiu Yang, Tetsuya Sakai

Training-Free Adaptive Speculative Decoding via Linguistic Priors (2026.findings-acl)

Challenge:	Existing bilinear methods focus on inter-modality information between images and questions . existing models focus on the interaction between images, questions, and images .
Approach:	They propose a trilinear interaction framework that incorporates attention mechanisms for capturing inter-modality and intra-modal relationships.
Outcome:	The proposed model outperforms bilinear models on the Visual7W Telling task and VQA-1.0 Multiple Choice task and outperformed baselines on the VQA, TDIUC and GQA datasets.

Copied to clipboard

Jingyi Wang, Jiaqi Huang, Zunnan Xu, Jun Zhou, Kehong Yuan, Xiang Qian

Syntactic Text Processing

Challenge:	Speculative decoding (SPD) is a promising technique to accelerate Large Language Models (LLMs). current approaches neglect the inherent heterogeneity of natural language and fail to distinguish between semantically-rich content and structurally-predictable syntax.
Approach:	They propose a training-free framework that leverages linguistic priors to enable adaptive drafting and verification.
Outcome:	The proposed framework significantly accelerates inference without additional training.

S2R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning (2025.acl-long)

Copied to clipboard

Ruotian Ma, Peisong Wang, Cheng Liu, Xingyan Liu, Jiaqi Chen, Bang Zhang, Xin Zhou, Nan Du, Jia Li

Resource-Friendly Dynamic Enhancement Chain for Multi-Hop Question Answering (2025.findings-acl)

Challenge:	Existing approaches to incentivize LLMs’ deep thinking abilities require large-scale data or significant training efforts.
Approach:	They introduce an efficient framework that enhances LLM reasoning by teaching models to self-verify and self-correct during inference.
Outcome:	The proposed framework outperforms models trained on long-CoT distilled data with 3.1k initialization samples and achieves an accuracy improvement of 51.0% to 81.6%.

Copied to clipboard

Binquan Ji, Haibo Luo, YifeiLu YifeiLu, Lei Hei, Jiaqi Wang, Tingjing Liao, Wang Lingyu, Shichao Wang, Feiliang Ren

Natural Language Interfaces

Challenge:	Existing approaches to solve multi-hop question answering challenges require multiple rounds of retrieval and iterative generation.
Approach:	They propose a framework that decomposes complex questions into coherent subquestions . it then iteratively refines these subquests through context-aware rewriting to generate effective query formulations.
Outcome:	The proposed framework performs on par with or surpasses state-of-the-art benchmarks while significantly reducing token consumption.

M2C: Towards Automatic Multimodal Manga Complement (2023.findings-emnlp)

Copied to clipboard

Hongcheng Guo, Boyang Wang, Jiaqi Bai, Jiaheng Liu, Jian Yang, Zhoujun Li

Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models (2026.findings-acl)

Challenge:	Multimodal manga analysis focuses on enhancing manga understanding with visual and textual features.
Approach:	They propose a task to enhance manga understanding with visual and textual features by providing a shared semantic space for vision and language understanding.
Outcome:	The proposed task provides a shared semantic space for vision and language understanding.

Copied to clipboard

Bang Zhang, Ruotian Ma, Qingxuan Jiang, Peisong Wang, Jiaqi Chen, Zheng Xie, Xingyu Chen, Yue Wang, Fanghua Ye, Jian Li, Yifan Yang, Zhaopeng Tu, Xiaolong Li

PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language Models (2025.acl-long)

Challenge:	Large language models (LLMs) have evolved from statistical sequence predictors to sophisticated autonomous agents capable of reasoning, planning, and sustaining multi-turn conversa-tions.
Approach:	They propose a system that instantiates a "Sentient Agent" that simulates human-like emotional changes and inner thoughts to provide a more realistic evaluation of the model in multi-turn conversations.
Outcome:	The proposed framework measures the agent's higher-order social cognition in multi-turn conversations.

Copied to clipboard

Jiaqi Zhao, Miao Zhang, Ming Wang, Yuzhang Shang, Kaihao Zhang, Weili Guan, Yaowei Wang, Min Zhang

SparkRA: A Retrieval-Augmented Knowledge Service System Based on Spark Large Language Model (2024.emnlp-demo)

Challenge:	Existing methods for sub 2-bit quantization introduce an extra 1-bit or more per weight.
Approach:	They propose a sub 2-bit post-training quantization method that enables weight quantization to 1.61-bit for the first time.
Outcome:	The proposed method reduces the upper bound of quantization error to 1.61-bit for the first time.

Copied to clipboard

Dayong Wu, Jiaqi Li, Baoxin Wang, Honghong Zhao, Siyuan Xue, Yanjie Yang, Zhijun Chang, Rui Zhang, Li Qian, Bo Wang, Shijin Wang, Zhixiong Zhang, Guoping Hu

GeometryZero: Advancing Geometry Solving via Group Contrastive Policy Optimization (2026.findings-acl)

Challenge:	Large language models (LLMs) have shown remarkable achievements across various language tasks.
Approach:	They propose a scientific literature LLM and a knowledge service system based on it . they collect scientific literature and then pre-train it using autoregressive training .
Outcome:	The proposed system provides literature investigation, paper reading, and academic writing functions.

Copied to clipboard

Yikun Wang, Yibin Wang, Dianyi Wang, Zimian Peng, Qipeng Guo, Dacheng Tao, Jiaqi Wang

Data Contamination Calibration for Black-box LLMs (2024.findings-acl)

Challenge:	Existing methods for auxiliary construction training are expensive and underperform . Existing Corresponding Author training methods lack self-correction capabilities in reasoning chains.
Approach:	They propose a reinforcement learning framework that rewards auxiliary construction with geometric reasoning by grouping construction rewards with a Length Reward.
Outcome:	Experiments on Geometry3K and MathVista show that GeometryZero outperforms baselines on auxiliary constructions.

Copied to clipboard

Wentao Ye, Jiaqi Hu, Liyao Li, Haobo Wang, Gang Chen, Junbo Zhao

Challenge:	Despite the rapid advancements of Large Language Models, the unchecked ultra-large-scale training sets introduce a series of potential risks like data contamination.
Approach:	They propose a method to detect contaminated training data and diminish the contamination effect by using a to-be-released dataset.
Outcome:	The proposed method outperforms existing methods by at least 4.5% on more 4 dataset formats, with more than 10 base LLMs.

MedDialog: Large-scale Medical Dialogue Datasets (2020.emnlp-main)

Copied to clipboard

Guangtao Zeng, Wenmian Yang, Zeqian Ju, Yue Yang, Sicheng Wang, Ruisi Zhang, Meng Zhou, Jiaqi Zeng, Xiangyu Dong, Ruoyu Zhang, Hongchao Fang, Penghui Zhu, Shu Chen, Pengtao Xie

Dialogue Systems & Conversational Agents

Challenge:	telemedicine is a medical practice that provides patient care remotely using video conferencing tools.
Approach:	They build large-scale medical dialogue datasets to facilitate research . they pretrain several models on the Chinese MedDialog dataset and compare their performance .
Outcome:	The proposed datasets show that models trained on MedDialog can generate doctor-like medical dialogues.

Shadow-Activated Backdoor Attacks on Multimodal Large Language Models (2025.findings-acl)

Copied to clipboard

Ziyi Yin, Muchao Ye, Yuanpu Cao, Jiaqi Wang, Aofei Chang, Han Liu, Jinghui Chen, Ting Wang, Fenglong Ma

HMoE: Heterogeneous Mixture of Experts for Language Modeling (2025.emnlp-main)

Challenge:	Existing backdoor attacks on Multimodal Large Language Models are less applicable to open-ended conversations with users.
Approach:	They propose a shadow-activated backdoor attack scenario where attackers inject malicious content into the responses of MLLMs when the responses explicitly relate to the shadowed object.
Outcome:	The proposed framework achieves the desired behaviors by constructing a poisoned dataset and implementing an attention-regularized tuning strategy.

Copied to clipboard

An Wang, Xingwu Sun, Ruobing Xie, Shuaipeng Li, Jiaqi Zhu, Zhen Yang, Pinxue Zhao, Weidong Han, Zhanhui Kang, Di Wang, Naoaki Okazaki, Cheng-zhong Xu

Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework (2026.findings-acl)

Challenge:	Mixture of Experts (MoE) models use homogeneous experts with diverse capacities, resulting in a lack of expert specialization and parameter utilization.
Approach:	They propose a framework where experts differ in size and possess diverse capacities . they propose HMoE to encourage frequent activation of smaller experts .
Outcome:	The proposed framework outperforms homogeneous homogenous MoE models on evaluation benchmarks and achieves lower loss rate with fewer activated parameters.

Copied to clipboard

Jiaqi Weng, Han Zheng, Hanyu Zhang, Ej Zhou, Qinqin He, Jialing Tao, Hui Xue, Zhixuan Chu, Xiting Wang

Explainability & Interpretability in NLP

Challenge:	Existing studies on how SAEs derive most fine-grained latent features for safety remain unexplored.
Approach:	They propose a framework for interpreting SAE features in safety-critical domains . they train a suite of SAEs with human-readable explanations and systematic evaluations based on pornography, politics, violence, and terror .
Outcome:	The proposed framework reduces interpretation cost by 55% and improves safety-critical features.

Debiasing In-Context Learning by Instructing LLMs How to Follow Demonstrations (2024.findings-acl)

Copied to clipboard

Lvxue Li, Jiaqi Chen, Xinyu Lu, Yaojie Lu, Hongyu Lin, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Zhongyi Liu, Xianpei Han, Le Sun

HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation (2022.acl-long)

Challenge:	In-context learning (ICL) has gained considerable attention due to its data efficiency and task adaptability.
Approach:	They propose to de-biase demonstration bias in in-context learning by focusing on semantic ambiguity induced by demonstrations and reducing the semantic hazard.
Outcome:	The proposed methods significantly improve performance on six datasets.

Copied to clipboard

Zhoujun Cheng, Haoyu Dong, Zhiruo Wang, Ran Jia, Jiaqi Guo, Yan Gao, Shi Han, Jian-Guang Lou, Dongmei Zhang

Natural Language Interfaces

Challenge:	Existing studies on table reasoning focus on flat tables and hierarchical tables . a new dataset, HiTab, aims to examine numerical reasoning over hierarchic tables based on hierarchically structured tables - a strong challenge for existing baselines and a valuable benchmark for future research.
Approach:	They propose a hierarchical question answering and natural language generation dataset to study hierarchic tables.
Outcome:	The proposed model shows that it is effective in QA and natural language generation over hierarchical tables.

PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning (2025.emnlp-industry)

Copied to clipboard

Mohammad Kachuee, Teja Gollapudi, Minseok Kim, Yin Huang, Kai Sun, Xiao Yang, Jiaqi Wang, Nirav Shah, Yue Liu, Aaron Colak, Anuj Kumar, Wen-tau Yih, Xin Luna Dong

Chase: A Large-Scale and Pragmatic Chinese Dataset for Cross-Database Context-Dependent Text-to-SQL (2021.acl-long)

Challenge:	Existing methods to improve factuality of large language models (LLMs) rely on human-engineered instructions.
Approach:	They propose a retrieval-augmented generation framework that trains the model with distractor-aware QA pairs mixing gold evidence with subtle distractor passages and instills reasoning-centric habits that make the LLM plan, rationalize, and synthesize without extensive human engineered instructions.
Outcome:	The proposed framework outperforms state-of-the-art solutions across 12 open-book RAG QA benchmarks and is being deployed in production.

Copied to clipboard

Jiaqi Guo, Ziliang Si, Yu Wang, Qian Liu, Ming Fan, Jian-Guang Lou, Zijiang Yang, Ting Liu

Programming Languages in NLP

Challenge:	XDTS is a cross-database context-dependent text-to-sql problem with wide range of applications.
Approach:	They present a large-scale Chinese dataset for cross-database context-dependent Text-to-SQL . they find that only 35% of questions are context-independent and 28% of SQL queries are easy .
Outcome:	The proposed approach achieves an exact match accuracy of 40% over all questions and 16% over all question sequences.

Molweni: A Challenge Multiparty Dialogues-based Machine Reading Comprehension Dataset with Discourse Structure (2020.coling-main)

Copied to clipboard

Jiaqi Li, Ming Liu, Min-Yen Kan, Zihao Zheng, Zekun Wang, Wenqiang Lei, Ting Liu, Bing Qin

Natural Language Interfaces

Challenge:	Multiparty dialog applications such as discourse parsing and meeting summarization are now mainstream research.
Approach:	They propose to annotate a machine reading comprehension dataset with discourse structure built over multiparty dialog using a modified Segmented Discourse Representation Theory (SDRT) style.
Outcome:	The proposed dataset contributes large-scale discourse dependency annotations in a modified Segmented Discourse Representation Theory (SDRT) style for all of its multiparty dialogs, and achieves only 67.7% F1 on Molweni’s questions, a 20+% significant drop as compared against its SQuAD 2.0 performance.

PEAP: Proactive Embodied Action Sequence Planning with Joint Understanding of Vision and Audio Perception (2026.acl-long)

Copied to clipboard

Tianwei Lan, Jiaqi Wu, Zeming Liu, Zhaoxin Fan, Haifeng Wang, Yuhang Guo

JurisBench: A Deep Benchmark for Assessing Large Language Models in Professional Legal Practice (2026.acl-long)

Challenge:	Embodied action sequence planning focuses on the capability of embodied agents to implement action planning via environmental perception without explicit human instructions.
Approach:	They propose to use a multimodal dataset to evaluate the performance of multiple large language models to evaluate their models' environmental perception capabilities.
Outcome:	The proposed model shows that it lacks accurate environmental perception capabilities and that it can improve on the PEAP dataset.

Copied to clipboard

Ziang Chen, Guannan Li, Fanlin Ji, Yipeng Kang, Jiaqi Li, Muhan Zhang, Yangtao Zhang, Li Tianjiao, Jiannan Wang, Xin Guo, Song-Chun Zhu, Bin Ling

m3P: Towards Multimodal Multilingual Translation with Multimodal Prompt (2024.lrec-main)

Challenge:	Existing legal benchmarks evaluate isolated tasks or exam-style questions, failing to capture the procedural interdependencies and adjudicative rigor inherent in professional practice.
Approach:	They propose a vertical, depth-oriented, domain-specific benchmark to evaluate Large Language Models (LLMs) in Chinese civil litigation.
Outcome:	The proposed benchmarks show that large language models exhibit an "illusion of competence" the results highlight a critical gap between fluent linguistic output and judicial reliability .

Copied to clipboard

Jian Yang, Hongcheng Guo, Yuwei Yin, Jiaqi Bai, Bing Wang, Jiaheng Liu, Xinnian Liang, LinZheng Chai, Liqun Yang, Zhoujun Li

Multilinguality

Challenge:	Existing multimodal neural machine translation models focus on bilingual translation, but experimental results show that they outperform the text-only baselines and multilingual multimodal methods by a large margin.
Approach:	They propose a framework to leverage the multimodal prompt to guide the Multimodal Multilingual Neural Machine Translation (m3P) this framework aligns the representations of different languages with the same meaning and generates the conditional vision-language memory for translation.
Outcome:	The proposed framework outperforms previous text-only baselines and multilingual multimodal methods by a large margin.

HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM (2024.naacl-long)

Copied to clipboard

Zhilin Wang, Yi Dong, Jiaqi Zeng, Virginia Adams, Makesh Narsimhan Sreedhar, Daniel Egert, Olivier Delalleau, Jane Scowcroft, Neel Kant, Aidan Swope, Oleksii Kuchaiev

Challenge:	Existing helpfulness preference datasets do not specify what makes some responses more helpful and others less helpful.
Approach:	They use a dataset that has annotated for correctness, coherence, complexity, and verbosity.
Outcome:	The dataset has annotations for correctness, coherence, complexity, and verbosity in addition to overall helpfulness of responses.

WebSynthesis: World Model-Guided Monte Carlo Tree Search for Efficient WebAgent Trajectory Synthesis (2026.acl-long)

Copied to clipboard

Yifei Gao, Junhong Ye, Yifan Yang, Jiaqi Wang, Yi Zhang, Zhang Ruichen, Jitao Sang

Green & Sustainable NLP

Challenge:	Recent advances in large language models have enabled increasingly capable web agents . however, training such agents at scale still relies on high-quality interaction trajectories that are difficult to obtain at scale.
Approach:	They propose a framework for scalable trajectory synthesis that simulates state transitions without network dependencies and integrates Monte Carlo Tree Search to enable reversible exploration over the simulated state space.
Outcome:	Experiments on WebArena, WebVoyager, and Mind2Web-Online show that agents trained exclusively on synthesized trajectories outperform those trained on real-world data.

Retrieval over Classification: Integrating Relation Semantics for Multimodal Relation Extraction (2025.emnlp-main)

Copied to clipboard

Lei Hei, Tingjing Liao, null Peiyingxin, Yiyang Qi, Jiaqi Wang, Ruiting Li, Feiliang Ren

Information Extraction & Text Mining

Challenge:	Existing approaches to multimodal relation extraction ignore structural constraints and lack semantic expressiveness for fine-grained relation understanding.
Approach:	They propose a framework that reformulates multimodal relation extraction as a retrieval task driven by relation semantics.
Outcome:	The proposed framework achieves state-of-the-art performance on the benchmark datasets MNRE and MORE and exhibits stronger robustness and interpretability.

From Inheritance to Saturation: Disentangling the Evolution of Visual Redundancy for Architecture-Aware MLLM Inference Acceleration (2026.acl-long)

Copied to clipboard

Jiaqi Shi, Xulong Zhang, Yuechan Li, Xiaoyang Qu, Jianzong Wang

Visual Data in NLP

Challenge:	Existing acceleration strategies suffer from severe "backbone dependency" Existing strategies such as token pruning or layer sparsity suffer from this .
Approach:	They propose a framework that decouples visual redundancy into IVR and architecture-dependent secondary saturation redundancies.
Outcome:	The proposed framework outperforms existing frameworks on Qwen25-VL and Qwa25-LL.

Towards Mitigating Modality Bias in Vision-Language Models for Temporal Action Localization (2026.acl-long)

Copied to clipboard

Jiaqi Li, Guangming Wang, Shuntian Zheng, Minzhe Ni, Xiaoman Lu, Guanghui Ye, Yu Guan

TrojFSP: Trojan Insertion in Few-shot Prompt Tuning (2024.naacl-long)

Challenge:	Existing vision-language models overemphasize linguistic priors, leading to modality bias.
Approach:	They propose a vision-language aggregation framework that mitigates modality bias in TAL by preserving vision as the dominant signal while adaptively exploiting language only when beneficial.
Outcome:	Experiments on THUMOS14 show that the proposed model outperforms state-of-the-art models by up to 3.2% mAP.

Copied to clipboard

Mengxin Zheng, Jiaqi Xue, Xun Chen, Yanshan Wang, Qian Lou, Lei Jiang

StyleDGPT: Stylized Response Generation with Pre-trained Language Models (2020.findings-emnlp)

Challenge:	Prompt tuning on a few data samples presents security issues, e.g., Trojan attacks.
Approach:	They propose a method to transfer established data poisoning attacks directly to few-shot prompt tuning, a technique to address the poisoned imbalance issue.
Outcome:	The proposed method achieves an ASR of over 99% while maintaining negligible decreases in CDA.

Copied to clipboard

Ze Yang, Wei Wu, Can Xu, Xinnian Liang, Jiaqi Bai, Liran Wang, Wei Wang, Zhoujun Li

Text Generation

Challenge:	Existing methods for generating responses following a desired style are lacking of parallel data for training.
Approach:	They propose a KL loss and a style classifier to fine-tune response generation . they show that their model can significantly outperform state-of-the-art methods .
Outcome:	The proposed model outperforms state-of-the-art models in style consistency and contextual coherence with two public datasets.

Hierarchical Pretraining on Multimodal Electronic Health Records (2023.emnlp-main)

Copied to clipboard

Xiaochen Wang, Junyu Luo, Jiaqi Wang, Ziyi Yin, Suhan Cui, Yuan Zhong, Yaqing Wang, Fenglong Ma

BIPEFT: Budget-Guided Iterative Search for Parameter Efficient Fine-Tuning of Large Pretrained Language Models (2024.findings-emnlp)

Challenge:	Existing pretraining models on EHR data are too specific, limiting their transferability.
Approach:	They propose a general, unified pretraining framework for hierarchically multimodal EHR data that can be used to train models on a large dataset before fine-tuning it on 'upstream' tasks.
Outcome:	The proposed model performs on eight downstream tasks spanning three levels and compares with baselines on 18 different tasks.

Copied to clipboard

Aofei Chang, Jiaqi Wang, Han Liu, Parminder Bhatia, Cao Xiao, Ting Wang, Fenglong Ma

LMDX: Language Model-based Document Information Extraction and Localization (2024.findings-acl)

Challenge:	Existing methods for parameter-efficient fine-tuning are limited by computational and storage requirements.
Approach:	They propose a budget-guided iterative search strategy to disentangle binary module and rank dimension search spaces and early selection strategies based on parameter budgets.
Outcome:	The proposed method significantly improves search efficiency on public benchmarks.

Copied to clipboard

Vincent Perot, Kai Kang, Florian Luisier, Guolong Su, Xiaoyu Sun, Ramya Sree Boppana, Zilong Wang, Zifeng Wang, Jiaqi Mu, Hao Zhang, Chen-Yu Lee, Nan Hua

ToolDNA: Autonomous Evolution of Tool Metadata for Robust Dialogue Agents (2026.findings-acl)

Challenge:	Large Language Models have revolutionized Natural Language Processing but their application in extracting information from visually rich documents has not been successful.
Approach:	They propose a language model-based document information extraction and localization methodology to reframe the document information extract task for a LLM.
Outcome:	The proposed method enables extraction of singular, repeated, and hierarchical entities with and without training data.

Copied to clipboard

Qiuyuan Ai, Cong Wang, Jiaqi Zhang, Zengxin Han, Jie Song

MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL (2025.coling-main)

Challenge:	Task-oriented dialogue systems face labor-intensive manual metadata tuning and sparse reinforcement learning (RL) rewards that fail to diagnose invocation errors.
Approach:	They propose a framework that enables auto-evolution of policy networks and tool metadata via RL . a tool metadata loop coordinates metadata through policy-generated candidates during rollouts .
Outcome:	The proposed framework achieves +11% problem resolution and +54% accuracy over commercial LLMs with prompt engineering and +25%/+35% over supervised fine-tuning.

Copied to clipboard

Bing Wang, Changyu Ren, Jian Yang, Xinnian Liang, Jiaqi Bai, LinZheng Chai, Zhao Yan, Qian-Wen Zhang, Di Yin, Xing Sun, Zhoujun Li

Programming Languages in NLP

Challenge:	Recent LLM-based Text-to-SQL methods suffer from performance degradation on “huge” databases and complex user questions that require multi-step reasoning.
Approach:	They propose a framework that integrates a decomposer agent and auxiliary agents to generate SQL queries from natural language text.
Outcome:	The proposed framework achieves comparable execution accuracy on SQL-Llama tasks compared to the baseline model.

OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference (2025.acl-long)

Copied to clipboard

Xiangyu Zhao, Shengyuan Ding, Zicheng Zhang, Haian Huang, Maosongcao Maosongcao, Jiaqi Wang, Weiyun Wang, Xinyu Fang, Wenhai Wang, Guangtao Zhai, Hua Yang, Haodong Duan, Kai Chen

Enhancing EEG-to-Text Decoding through Transferable Representations from Pre-trained Contrastive EEG-Text Masked Autoencoder (2024.acl-long)

Challenge:	Existing open-source multi-modal large language models (MLLMs) focus on enhancing foundational capabilities, leaving a significant gap in human preference alignment.
Approach:	They propose a dataset of 200K high-quality training samples featuring diverse images, complex questions, and varied response formats to improve MLLMs’ alignment with human preferences.
Outcome:	The proposed dataset of 200K high-quality training samples improves human preference alignment while maintaining or enhancing performance on standard VQA benchmarks.

Copied to clipboard

Jiaqi Wang, Zhenxi Song, Zhengyu Ma, Xipeng Qiu, Min Zhang, Zhiguo Zhang