Papers by Ying Shen

INREACT: An Inspire-Then-Reinforce Training Framework For Multimodal GUI Agent (2025.findings-emnlp)

Challenge:	Existing LLMs struggle to identify errors in financial documents, a study shows . 18% of financial practitioners make errors daily, one-third make errors several times weekly, and 59% make errors multiple times monthly.
Approach:	They introduce FinED-Bench, a publicly available Benchmark for financial error detection . it covers nine real-world financial scenarios and includes over 900 documents in 2025 . supervised fine-tuning can significantly improve the performance of weaker LLMs, they show .
Outcome:	The proposed benchmark covers nine real-world financial scenarios and includes over 900 documents reported in 2025 that are unseen by existing language models.

Copied to clipboard

Yuanlei Wang, Liuzhou Zhang, Haohao Luo, Ying Shen

Efficient Low-rank Multimodal Fusion With Modality-Specific Factors (P18-1)

Challenge:	Existing multimodal large language models struggle with precise localization of small elements.
Approach:	They propose a multimodal GUI agent framework that unifies observing, thinking, and acting for precise and interpretable decision-making.
Outcome:	The proposed framework unifies observing, thinking, and acting for precise and interpretable decision-making.

Copied to clipboard

Zhun Liu, Ying Shen, Varun Bharadhwaj Lakshminarasimhan, Paul Pu Liang, AmirAli Bagher Zadeh, Louis-Philippe Morency

LLM Braces: Straightening Out LLM Predictions with Relevant Sub-Updates (2025.acl-long)

Challenge:	Multimodal research is a growing field of artificial intelligence, and fusion is one of the main research problems.
Approach:	They propose a low-rank multimodal fusion method which integrates multiple unimodal representations into one compact multimodal representation.
Outcome:	The proposed method achieves competitive results on multimodal sentiment analysis, speaker trait analysis, and emotion recognition tasks while reducing computational complexity.

Copied to clipboard

Ying Shen, Lifu Huang

CLEME: Debiasing Multi-reference Evaluation for Grammatical Error Correction (2023.emnlp-main)

Challenge:	Recent studies reveal that much of the knowledge in a Transformer-based Large Language Model (LLM) is encoded in its feed-forward (FFN) layers, where each FNN layer can be interpreted as the summation of sub-updates, each corresponding to a weighted column vector from the FFN’s value parameter matrix.
Approach:	They propose a method that computes relevance scores associated with value vectors in FFN layers and leverages these scores to dynamically adjust the contribution of sub-updates.
Outcome:	The proposed framework outperforms baseline approaches in fine-tuning and zero-shot settings while requiring significantly fewer tunable parameters.

Copied to clipboard

Jingheng Ye, Yinghui Li, Qingyu Zhou, Yangning Li, Shirong Ma, Hai-Tao Zheng, Ying Shen

Robustness in NLP

Challenge:	Evaluating the performance of Grammatical Error Correction systems is a challenging task due to its subjectivity.
Approach:	They propose a method to evaluate GEC systems in multi-reference evaluation setting . they use consistent edit boundaries to eliminate bias caused by inconsistent edit boundaries .
Outcome:	The proposed evaluation metric eliminates bias caused by inconsistent edit boundaries on six English reference sets.

DALK: Dynamic Co-Augmentation of LLMs and KG to answer Alzheimer’s Disease Questions with Scientific Literature (2024.findings-emnlp)

Copied to clipboard

Dawei Li, Shu Yang, Zhen Tan, Jae Baik, Sukwon Yun, Joseph Lee, Aaron Chacko, Bojian Hou, Duy Duong-Tran, Ying Ding, Huan Liu, Li Shen, Tianlong Chen

Structured Data in NLP

Challenge:	Recent advances in large language models have achieved promising performances across various applications, but the challenge of integrating long-tail knowledge continues to impede the seamless adoption of LLMs in specialized domains.
Approach:	They propose a dynamic co-augmentation framework for the refinement of large language models and knowledge graphs in the context of Alzheimer's Disease.
Outcome:	The proposed framework can be used to study Alzheimer's Disease (AD) using LLMs and KGs.

DiffLM: Controllable Synthetic Data Generation via Diffusion Language Models (2025.findings-acl)

Copied to clipboard

Ying Zhou, Xinyao Wang, Yulei Niu, Yaojie Shen, Lexin Tang, Fan Chen, Ben He, Le Sun, Longyin Wen

P-FOLIO: Evaluating and Improving Logical Reasoning with Abundant Human-Written Reasoning Chains (2024.findings-emnlp)

Challenge:	Recent advances in large language models (LLMs) have significantly enhanced their knowledge and generative capabilities, leading to a surge of interest in leveraging LLMs for high-quality data synthesis.
Approach:	They propose a controllable data synthesis framework based on variational autoencoder which leverages diffusion models to reserve more information of original distribution and format structure in the learned latent distribution.
Outcome:	The proposed framework generates high-quality data with performance exceeding that of real data by 2%–7% on seven real-world datasets.

Copied to clipboard

Simeng Han, Aaron Yu, Rui Shen, Zhenting Qi, Martin Riddell, Wenfei Zhou, Yujie Qiao, Yilun Zhao, Semih Yavuz, Ye Liu, Shafiq Joty, Yingbo Zhou, Caiming Xiong, Dragomir Radev, Rex Ying, Arman Cohan

Amalgamating Knowledge from Two Teachers for Task-oriented Dialogue System with Adversarial Training (2020.emnlp-main)

Challenge:	Existing methods on understanding the capabilities of LLMs in logical reasoning rely on binary entailment classification or synthetically derived rationales.
Approach:	They propose to annotate a human-annotated dataset consisting of diverse and complex reasoning chains for a set of realistic logical reasoning stories also written by humans.
Outcome:	The proposed model outperforms existing methods on understanding the capabilities of LLMs in logical reasoning by 10% or more.

Copied to clipboard

Wanwei He, Min Yang, Rui Yan, Chengming Li, Ying Shen, Ruifeng Xu

Robustness in NLP

Challenge:	Existing approaches to task-oriented dialogue systems require a large number of handcrafted features and labels.
Approach:	They propose a "Two-Teacher One-Student" learning framework for task-oriented dialogue . the framework amalgamates knowledge from two teacher networks and provides guidance .
Outcome:	The proposed framework outperforms baseline methods on two benchmark datasets . it can retrieve accurate KB entities and generate human-like responses simultaneously .

Tunable Soft Prompts are Messengers in Federated Learning (2023.findings-emnlp)

Copied to clipboard

Chenhe Dong, Yuexiang Xie, Bolin Ding, Ying Shen, Yaliang Li

LiGen: Active Lipid Generation via a Molecular Language Model (2026.acl-long)

Challenge:	Existing methods to protect model privacy in federated learning (FL) are limited.
Approach:	They propose a federated learning approach that provides model privacy protection via tunable soft prompts.
Outcome:	The proposed approach provides protection for the global model while reducing communication and computation costs.

Copied to clipboard

Ying Zhan, Xiuqi Tang, Yan Zhang, Xiao Tan, Dian Shen, Zhou Yu, Beilun Wang

Wasserstein Selective Transfer Learning for Cross-domain Text Mining (2021.emnlp-main)

Challenge:	Lipid nanoparticles (LNPs) can deliver cargos to tumor and immune cells . traditional approaches rely on experimental screening and expert judgment .
Approach:	They propose a method to generate lipid molecules efficiently and actively using deep learning.
Outcome:	The proposed method outperforms baseline methods on multiple cell lines and achieves a 30% improvement over the current methods.

Copied to clipboard

Lingyun Feng, Minghui Qiu, Yaliang Li, Haitao Zheng, Ying Shen

Benchmarking and Learning Real-World Customer Service Dialogue (2026.acl-long)

Challenge:	Existing methods to improve the learning of data-scarce target domains have negative transfer due to the data distributions between source and target domain.
Approach:	They propose a method that uses a reinforced selector to select helpful data for transfer learning and a Wasserstein-based discriminator to maximize the distance between the selected data and target data.
Outcome:	The proposed method performs better on three real-world text mining tasks.

Copied to clipboard

Tianhong Gao, Jundong Shen, Jiapeng Wang, Bei Shi, Ying Ju, Junfeng Yao, Huiyu Yu

Dialogue Systems & Conversational Agents

Challenge:	Existing benchmarks and training pipelines for industrial intelligent customer service (ICS) focus on task completion and tool correctness.
Approach:	They propose a benchmark-to-optimization loop that bridges offline gains to deployment . they propose OlaMind, which distills reusable reasoning patterns from expert dialogues .
Outcome:	The proposed benchmark surpasses GPT-5.2 and Gemini 3 Pro on OlaBench . it delivers an average +23.67% issue resolution and -6.6% human transfer rate versus baseline .

Unifying Language Agent Algorithms with Graph-based Orchestration Engine for Reproducible Agent Research (2025.acl-demo)

Copied to clipboard

Qianqian Zhang, Jiajia Liao, Heting Ying, Yibo Ma, Haozhan Shen, Jingcheng Li, Peng Liu, Lu Zhang, Chunxin Fang, Kyusong Lee, Ruochen Xu, Tiancheng Zhao

REAP: Towards Effective Training-Free Chemical Reasoning with Explicit Atomic Priors (2026.findings-acl)

Challenge:	Language agents powered by large language models (LLMs) have demonstrated remarkable capabilities in understanding, reasoning, and executing complex tasks.
Approach:	They propose a flexible framework that addresses engineering overhead and insufficient evaluation frameworks for fair comparison.
Outcome:	The proposed framework simplifies language agent development and establishes a foundation for reproducible agent research.

Copied to clipboard

Mingxu Zhang, Dazhong Shen, Qi Zhang, Ying Sun

MKT: A Multi-Stage Knowledge Transfer Framework to Mitigate Catastrophic Forgetting in Multi-Domain Chinese Spelling Correction (2025.emnlp-industry)

Challenge:	Current approaches to instill explicit priors into LLMs often suffer from an information bottleneck .
Approach:	They propose a training-free framework that equips LLMs with an external knowledge base, enabling them to reason over retrieved chemical priors dynamically.
Outcome:	Experiments show that REAP outperforms current reasoning methods and rivals state-of-the-art training-based models.

Copied to clipboard

Peng Xing, Yinghui Li, Shirong Ma, Xinnian Liang, Haojing Huang, Yangning Li, Shu-Yu Guo, Hai-Tao Zheng, Wenhao Jiang, Ying Shen

Green & Sustainable NLP

Challenge:	Chinese Spelling Correction (CSC) is a model that detects and corrects spelling errors in given sentences.
Approach:	They propose a model-agnostic model with an evolving teacher model and dynamic distillation weights for knowledge transfer in each domain rather than focusing solely on new domain knowledge.
Outcome:	The proposed model-agnostic framework is based on an evolving teacher model and dynamic distillation weights for knowledge transfer in each domain, rather than focusing solely on new domain knowledge.

Too Good to be Bad: On the Failure of LLMs to Role-Play Villains (2026.findings-acl)

Copied to clipboard

Zihao Yi, Qingxuan Jiang, Ruotian Ma, Xingyu Chen, Qu Yang, Mengru Wang, Fanghua Ye, Ying Shen, Zhaopeng Tu, Xiaolong Li, Liefeng Bo

Challenge:	Large Language Models (LLMs) are increasingly tasked with creative generation, but their ability to portray non-prosocial, antagonistic personas remains largely unexamined.
Approach:	They propose a moral alignment benchmark to test the safety of large language models . they find that models struggle with traits directly antithetical to safety principles .
Outcome:	The proposed model fails to accurately portray morally ambiguous or villainous characters . the model fails most with traits directly antithetical to safety principles .

Answer-driven Deep Question Generation based on Reinforcement Learning (2020.coling-main)

Copied to clipboard

Liuyin Wang, Zihan Xu, Zibo Lin, Haitao Zheng, Ying Shen

Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation (2026.acl-long)

Challenge:	Existing methods for deep question generation focus on enhancing document representations, but little attention is paid to the answer information.
Approach:	They propose a deep question generation model that makes better use of the target answer as a guidance to facilitate question generation.
Outcome:	The proposed model outperforms state-of-the-art models in automatic and human evaluations on the hotpotQA dataset.

Copied to clipboard

Hanwen Shen, Ting Ying, Jiajie Lu, Shanshan Wang

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

Challenge:	Debiased large language models excel at handling known or low-bias prompts, but fail on unfamiliar and high-biased prompts.
Approach:	They propose a debiasing framework that detects high-bias prompts and triggers context-aware LoRA updates only when a bias-risk score exceeds a threshold.
Outcome:	The proposed framework reduces toxicity/bias score with significantly lower latency than standard optimization methods.

Copied to clipboard

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

Experience Retrieval-Augmentation with Electronic Health Records Enables Accurate Discharge QA (2026.acl-long)

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

Copied to clipboard

Justice Ou, Tinglin Huang, Yilun Zhao, Ziyang Yu, Peiqing Lu, Yifei Shen, Rex Ying

Information Retrieval

Challenge:	Existing methods to improve the reliability of Large Language Models (LLMs) in clinical applications require factual knowledge from open-ended datasets and clinical case-based knowledge to provide context grounded in real-world patient experiences.
Approach:	They propose a retrieval-augmented generation framework based on the electronic health record to offer contextual information from other patients’ discharge reports.
Outcome:	The proposed framework outperforms a text-based ranker in a clinical QA dataset with 1,280 discharge-related questions .

HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model Compression (2021.emnlp-main)

Copied to clipboard

Chenhe Dong, Yaliang Li, Ying Shen, Minghui Qiu

Source-free Domain Adaptation for Aspect-based Sentiment Analysis (2024.lrec-main)

Challenge:	Large pre-trained language models (PLMs) have shown overwhelming performances on many tasks, but their large size and slow inference speed have hindered practical deployments.
Approach:	They propose a hierarchical relational knowledge distillation method to capture hierarchic and domain relational information.
Outcome:	The proposed method outperforms existing methods on multi-domain datasets and is highly reproducible.

Copied to clipboard

Zishuo Zhao, Ziyang Ma, Zhenzhou Lin, Jingyou Xie, Yinghui Li, Ying Shen

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

Challenge:	Unsupervised Domain Adaptation (UDA) of the Aspect-based Sentiment Analysis task is a data mining technique that involves aspect extraction and aspect sentiment classification subtasks.
Approach:	They propose a framework that allows model parameter transfer, not data transfer, between different domains.
Outcome:	The proposed framework performs competitively with traditional unsupervised domain adaptation methods under privacy conditions.

Copied to clipboard

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

Summarize before Aggregate: A Global-to-local Heterogeneous Graph Inference Network for Conversational Emotion Recognition (2020.coling-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

Dongming Sheng, Dong Wang, Ying Shen, Haitao Zheng, Haozhuang Liu

Structured Data in NLP

Challenge:	Existing studies focus on modeling emotion influences with utterance-level features, with little attention paid on phrase-level semantic connection between utterrances.
Approach:	They propose a two-stage Summarization and Aggregation Graph Inference Network which integrates inference for topic-related emotional phrases and local dependency reasoning over neighbouring utterances in a global-to-local fashion.
Outcome:	The proposed model outperforms the state-of-the-art models on three CER benchmark datasets.

Continual Learning for Task-oriented Dialogue System with Iterative Network Pruning, Expanding and Masking (2021.acl-short)

Copied to clipboard

Binzong Geng, Fajie Yuan, Qiancheng Xu, Ying Shen, Ruifeng Xu, Min Yang

Dialogue Systems & Conversational Agents

Challenge:	Existing methods to learn consecutive tasks without forgetting how to perform previously trained problems are lacking.
Approach:	They propose a continual learning method which preserves performance on previously encountered tasks while accelerating learning progress on subsequent tasks.
Outcome:	The proposed method preserves performance on previously encountered tasks while accelerating learning progress on subsequent tasks.

GEMv2: Multilingual NLG Benchmarking in a Single Line of Code (2022.emnlp-demos)

Copied to clipboard

Sebastian Gehrmann, Abhik Bhattacharjee, Abinaya Mahendiran, Alex Wang, Alexandros Papangelis, Aman Madaan, Angelina Mcmillan-major, Anna Shvets, Ashish Upadhyay, Bernd Bohnet, Bingsheng Yao, Bryan Wilie, Chandra Bhagavatula, Chaobin You, Craig Thomson, Cristina Garbacea, Dakuo Wang, Daniel Deutsch, Deyi Xiong, Di Jin, Dimitra Gkatzia, Dragomir Radev, Elizabeth Clark, Esin Durmus, Faisal Ladhak, Filip Ginter, Genta Indra Winata, Hendrik Strobelt, Hiroaki Hayashi, Jekaterina Novikova, Jenna Kanerva, Jenny Chim, Jiawei Zhou, Jordan Clive, Joshua Maynez, João Sedoc, Juraj Juraska, Kaustubh Dhole, Khyathi Raghavi Chandu, Laura Perez Beltrachini, Leonardo F . R. Ribeiro, Lewis Tunstall, Li Zhang, Mahim Pushkarna, Mathias Creutz, Michael White, Mihir Sanjay Kale, Moussa Kamal Eddine, Nico Daheim, Nishant Subramani, Ondrej Dusek, Paul Pu Liang, Pawan Sasanka Ammanamanchi, Qi Zhu, Ratish Puduppully, Reno Kriz, Rifat Shahriyar, Ronald Cardenas, Saad Mahamood, Salomey Osei, Samuel Cahyawijaya, Sanja Štajner, Sebastien Montella, Shailza Jolly, Simon Mille, Tahmid Hasan, Tianhao Shen, Tosin Adewumi, Vikas Raunak, Vipul Raheja, Vitaly Nikolaev, Vivian Tsai, Yacine Jernite, Ying Xu, Yisi Sang, Yixin Liu, Yufang Hou

Text Generation

Challenge:	Evaluations in machine learning rarely use the latest metrics, datasets, or human evaluation in favor of remaining compatible with prior work.
Approach:	They propose to use the Generation, Evaluation, and Metrics Benchmark to integrate new evaluation methods into existing evaluations.
Outcome:	The proposed evaluation infrastructure bridges the gap between the advantages of leaderboards and in-depth and evolving evaluations by allowing model developers to benefit from each other's work.

Invocation Refiner: A Plug-and-Play Module for Rectifying LLM Tool Invocations (2026.findings-acl)

Copied to clipboard

Qirui Jiao, Dian Jiao, Nan Du, Ying Shen, Liang Lin

Reasoning

Challenge:	Large Language Models (LLMs) have shown remarkable capabilities in Tool-Integrated Reasoning (TIR) however, the practical application is often hindered by frequent errors in tool invocations, such as incorrect tool names, invalid parameters, wrong tool-call order, or malformed invocation formats.
Approach:	They propose a specialized post-processing module that performs independent reasoning on the input of a frozen upstream LLM and an advanced RL algorithm to improve the tool-use reliability of base LLMs.
Outcome:	The proposed module improves task completion rates and invocation accuracy over the raw outputs of various upstream LLMs on a diverse set of tool-use and reasoning benchmarks.

Knowledge as A Bridge: Improving Cross-domain Answer Selection with External Knowledge (C18-1)

Copied to clipboard

Yang Deng, Ying Shen, Min Yang, Yaliang Li, Nan Du, Wei Fan, Kai Lei

Question Answering

Challenge:	Existing approaches to answer selection are limited in domains with limited labeled data.
Approach:	They propose a Knowledge-aware Attentive Network framework for cross-domain answer selection that uses the knowledge base as a bridge to enable knowledge transfer from the source domain to the target domain.
Outcome:	The proposed model outperforms strong competitors by a noticeable margin in cross-domain answer selection.

Learning from the Irrecoverable: Error-Localized Policy Optimization for Tool-Integrated LLM Reasoning (2026.acl-long)

Copied to clipboard

Qiao Liang, Yuke Zhu, Chao Ge, Lei Yang, Ying Shen, Bo Zheng, Sheng Guo

Reasoning

Challenge:	Tool-integrated reasoning (TIR) enables LLM agents to solve tasks through planning, tool use, and iterative revision, but outcome-only reinforcement learning suffers from sparse, delayed rewards and weak step-level credit assignment.
Approach:	They propose a tool-integrated reasoning approach that localizes the first irrecoverable step and leverages it for fine-grained credit assignment.
Outcome:	The proposed algorithm outperforms strong Agentic RL benchmarks in math, science QA, and code execution with additional gains in Pass@K and Major@K scaling, rollout ranking quality, and tool-call efficiency.

X-Eval: Generalizable Multi-aspect Text Evaluation via Augmented Instruction Tuning with Auxiliary Evaluation Aspects (2024.naacl-long)

Copied to clipboard

Minqian Liu, Ying Shen, Zhiyang Xu, Yixin Cao, Eunah Cho, Vaibhav Kumar, Reza Ghanadan, Lifu Huang

Text Generation

Challenge:	X-Eval is a two-stage instruction tuning framework to evaluate text in both seen and unseen aspects customized by end users.
Approach:	They introduce a two-stage instruction tuning framework to evaluate text in both seen and unseen aspects customized by end users.
Outcome:	The proposed framework improves the model’s ability to follow evaluation instructions and enhances the learning stage to better assess text quality.

Why Do Emotions Change? Appraisal-Guided Reasoning for Emotion–Cause Triplet Extraction in Conversations (2026.acl-long)

Copied to clipboard

Qiao Liang, Ying Shen, Yao Liu, Tiantian Chen, Lin Zhang

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

Challenge:	Existing methods for multi-turn, multi-speaker multimodal affect understanding are difficult to maintain conversation-level consistency under within-speaks' emotion shifts.
Approach:	They propose a framework that combines appraisal-guided structured generation with graph-structured reinforcement learning to extract triplets from multi-turn multimodal conversations.
Outcome:	The proposed framework outperforms baselines on public MECTEC benchmarks and improves structure-aware metrics on emotion shift coherence and core events.

Copied to clipboard

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

Enhancing Multimodal Retrieval via Complementary Information Extraction and Alignment (2025.acl-long)

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

Delong Zeng, Yuexiang Xie, Yaliang Li, Ying Shen

Chinese Relation Extraction with Multi-Grained Information and External Linguistic Knowledge (P19-1)

Challenge:	Existing studies focus on capturing information in multimodal data that is similar to their paired texts, but often ignores the complementary information contained in multimodule data.
Approach:	They propose a multimodal retrieval approach that employs Complementary Information Extraction and Alignment to capture complementary information in multimodal data.
Outcome:	The proposed approach achieves significant improvements over divide-and-conquer models and universal dense retrieval models.

Copied to clipboard

Ziran Li, Ning Ding, Zhiyuan Liu, Haitao Zheng, Ying Shen

Knowledge Representation

Challenge:	Existing methods for Chinese relation extraction suffer from segmentation errors and ambiguity of polysemy.
Approach:	They propose a multi-grained lattice framework for Chinese relation extraction . they incorporate word-level information into character sequence inputs to avoid segmentation errors .
Outcome:	The proposed model outperforms existing models on three real-world datasets in distinct domains.

Aspect and Sentiment Aware Abstractive Review Summarization (C18-1)

Copied to clipboard

Min Yang, Qiang Qu, Ying Shen, Qiao Liu, Wei Zhao, Jia Zhu

Summarization

Challenge:	Abstractive summarization is a task that generates short and concise summaries of user generated reviews.
Approach:	They propose an interactive attention mechanism to learn the representations of context and aspect words within reviews, acted as an encoder.
Outcome:	The proposed model achieves impressive results compared to other strong competitors on a real-life dataset.

Chain-of-Exemplar: Enhancing Distractor Generation for Multimodal Educational Question Generation (2024.acl-long)

Copied to clipboard

Haohao Luo, Yang Deng, Ying Shen, See-Kiong Ng, Tat-Seng Chua

Text Generation

Challenge:	Existing methods for multiple choice questions focus on text inputs and lack visual information.
Approach:	They propose a framework to generate subject-specific educational questions with plausible distractors based on multimodal content.
Outcome:	The proposed framework improves question generation and distractor generation over existing methods across subjects and educational levels.

Cooperative Denoising for Distantly Supervised Relation Extraction (C18-1)

Copied to clipboard

Kai Lei, Daoyuan Chen, Yaliang Li, Nan Du, Min Yang, Wei Fan, Ying Shen

Linguistic Rules-Based Corpus Generation for Native Chinese Grammatical Error Correction (2022.findings-emnlp)

Challenge:	Existing methods for distantly supervised relation extraction suffer from noisy labeling problem, which can severely degrade its performance.
Approach:	They propose a framework for distantly supervised relation extraction that leverages text corpus and knowledge graph and a cooperative module involving their mutual learning.
Outcome:	The proposed method reduces the noisy labels and achieves substantial improvement over the state-of-the-art methods.

Copied to clipboard

Shirong Ma, Yinghui Li, Rongyi Sun, Qingyu Zhou, Shulin Huang, Ding Zhang, Li Yangning, Ruiyang Liu, Zhongli Li, Yunbo Cao, Haitao Zheng, Ying Shen

Syntactic Text Processing

Challenge:	Chinese Grammatical Error Correction (CGEC) is a challenging NLP task and a common application in human daily life.
Approach:	They propose a linguistic rules-based approach to construct large-scale CGEC training corpora with automatically generated grammatical errors.
Outcome:	The proposed method improves performance of existing CGEC models and the benchmark is excellent resource for further development.

Multimodal Instruction Tuning with Conditional Mixture of LoRA (2024.acl-long)

Copied to clipboard

Ying Shen, Zhiyang Xu, Qifan Wang, Yu Cheng, Wenpeng Yin, Lifu Huang

Relabel the Noise: Joint Extraction of Entities and Relations via Cooperative Multiagents (2020.acl-main)

Challenge:	Multimodal Large Language Models (MLLMs) have demonstrated proficiency in diverse tasks across different domains.
Approach:	They propose a method that integrates multimodal instruction tuning with Conditional Mixture-of-LoRA.
Outcome:	Experimental results show that MixLoRA outperforms LoRA with the same or higher ranks . MLLMs have demonstrated remarkable proficiency in diverse tasks across domains .

Copied to clipboard

Daoyuan Chen, Yaliang Li, Kai Lei, Ying Shen

Express What You See: Can Multimodal LLMs Decode Visual Ciphers with Intuitive Semiosis Comprehension? (2025.findings-acl)

Challenge:	Existing methods for entity and relation extraction require light human annotation efforts.
Approach:	They propose a method to re-label noisy instances with a cooperative group . they use a confidence consensus module to gather the wisdom of all agents .
Outcome:	The proposed model outperforms state-of-the-art methods on two real-world datasets.

Copied to clipboard

Jiayi Kuang, Yinghui Li, Chen Wang, Haohao Luo, Ying Shen, Wenhao Jiang

Attention Basin: Why Contextual Position Matters in Large Language Models (2026.acl-long)

Challenge:	Traditional VQA benchmarks encounter a modality gap and over-reliance on language priors, whereas human cognition excels at intuitive semiosis, associating abstract visual symbols to linguistic semantics.
Approach:	They propose a task of generating abstract linguistics from emoji sequence images, where such reasoning underpins critical applications in cryptography.
Outcome:	The proposed model can generate abstract linguistics from emoji sequence images, challenging MLLMs’ reasoning of decoding complex semantics of visual ciphers.

Copied to clipboard

Zihao Yi, Zhenqing Ling, Delong Zeng, Haohao Luo, Zhe Xu, Wei Liu, Jian Luan, Wanxia Cao, Ying Shen

ChartThinker: A Contextual Chain-of-Thought Approach to Optimized Chart Summarization (2024.lrec-main)

Challenge:	Large Language Models (LLMs) are sensitive to the contextual position of information in input.
Approach:	They introduce Attention-Driven Reranking (AttnRank) which estimates a model’s intrinsic positional attention preferences using a small calibration set and reorders retrieved documents or few-shot examples to align the most salient content with these high-attention positions.
Outcome:	Experiments on multi-hop QA and few-shot in-context learning tasks show that AttnRank achieves substantial improvements across 10 large language models of varying architectures and scales, without modifying model parameters or training procedures.

Copied to clipboard

Mengsha Liu, Daoyuan Chen, Yaliang Li, Guian Fang, Ying Shen

Visual Data in NLP

Challenge:	Existing methods for chart summarization lack visual-language matching and reasoning ability.
Approach:	They propose a method which synthesizes deep analysis based on chains of thought and strategies of context retrieval to improve the logical coherence and accuracy of the generated summaries.
Outcome:	The proposed method outperforms 8 state-of-the-art models over 7 evaluation metrics and can significantly reduce time and cognitive resources required.

MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning (2023.acl-long)

Copied to clipboard

Zhiyang Xu, Ying Shen, Lifu Huang

Unifying Text, Tables, and Images for Multimodal Question Answering (2023.findings-emnlp)

Challenge:	Experimental results show zero-shot performance on unseen multimodal tasks . instruction tuning has yet to be explored for vision and multimodal task.
Approach:	They propose a multimodal instruction tuning benchmark dataset that consists of 62 diverse multimodal tasks in a unified seq-to-seq format covering 10 broad categories.
Outcome:	The proposed model performs well on unseen multimodal tasks and is highly scalable.

Copied to clipboard

Haohao Luo, Ying Shen, Yang Deng

Beyond A Single AI Cluster: A Survey of Decentralized LLM Training (2025.emnlp-main)

Challenge:	Existing approaches to multimodal question answering rely on single-modal or bi-modal models, which limit their ability to integrate information across all modalities.
Approach:	They propose a framework that unifies three different input modalities into a text-to-text format by employing position-enhanced table linearization and diversified image captioning techniques.
Outcome:	The proposed framework unifies three input modalities into a text-to-text format using position-enhanced table linearization and diversified image captioning techniques.

Copied to clipboard

Haotian Dong, Jingyan Jiang, Rongwei Lu, Jiajun Luo, Jiajun Song, Bowen Li, Ying Shen, Zhi Wang

Text Clustering

Challenge:	Decentralized LLM training leverages dispersed resources at varying scales.
Approach:	They propose a resource-driven paradigm that leverages dispersed resources across clusters, datacenters and even regions.
Outcome:	The proposed model scales are 175 billion to 660 billion parameters, and the exponential growth in computational requirements poses significant challenges.

R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generation (2025.emnlp-main)

Copied to clipboard

Kaijie Chen, Zihao Lin, Zhiyang Xu, Ying Shen, Yuguang Yao, Joy Rimchala, Jiaxin Zhang, Lifu Huang

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

Challenge:	Reasoning is a fundamental capability underpinning text-to-image (T2I) generation.
Approach:	They propose a benchmark to rigorously assess reasoning-driven T2I generation.
Outcome:	Experiments with 16 representative T2I models show limited reasoning performance . a strong pipeline-based framework decouples reasoning and generation .

Copied to clipboard

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

M3HG: Multimodal, Multi-scale, and Multi-type Node Heterogeneous Graph for Emotion Cause Triplet Extraction in Conversations (2025.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

Qiao Liang, Ying Shen, Tiantian Chen, Lin Zhang

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

Challenge:	Existing methods for ECAC focus on textual contexts, overlooking other modalities.
Approach:	They propose a multimodal, multi-scenario MECTEC dataset that captures emotional and causal contexts and effectively fuses contextual information at different levels.
Outcome:	The proposed model captures emotional and causal contexts and effectively fuses contextual information at both inter- and intra-utterance levels.

Copied to clipboard

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

Reasoning

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.

PIPER: Benchmarking and Prompting Event Reasoning Boundary of LLMs via Debiasing-Distillation Enhanced Tuning (2025.acl-long)

Copied to clipboard

Zhicong Lu, Changyuan Tian, PeiguangLi PeiguangLi, Li Jin, Sirui Wang, Wei Jia, Ying Shen, Guangluan Xu

Browsing Like Human: A Multimodal Web Agent with Experiential Fast-and-Slow Thinking (2025.acl-long)

Challenge:	Existing studies on Large Language Models (LLMs) have failed to evaluate their performance in event reasoning with a single event relational type or reasoning format.
Approach:	They propose a benchmark to evaluate LLMs' event reasoning capability using a single event relational type or reasoning format.
Outcome:	The proposed model improves on 10K diverse instruction-tuning demonstrations to alleviate event reasoning-oriented data scarcity.

Copied to clipboard

Haohao Luo, Jiayi Kuang, Wei Liu, Ying Shen, Jian Luan, Yang Deng