Papers by Yang Shen

Pre-training Cross-Modal Retrieval by Expansive Lexicon-Patch Alignment (2024.lrec-main)

Challenge:	Existing works of knowledge infusion depend on multi-task learning frameworks, which are inefficient and require large-scale retraining when new knowledge is considered.
Approach:	They propose a method which integrates knowledge-generated attention maps into the self-attention mechanism and integrates it into the model.
Outcome:	The proposed model outperforms existing methods on academic datasets and industry-scale ad relevance applications.

Copied to clipboard

Yang Yiyuan, Guodong Long, Michael Blumenstein, Xiubo Geng, Chongyang Tao, Tao Shen, Daxin Jiang

Automated Progressive Red Teaming (2025.coling-main)

Challenge:	Recent large-scale vision-language pre-training relies on image-text global alignment by contrastive learning and is further boosted by fine-grained alignment in a weakly contrastive manner for cross-modal retrieval.
Approach:	They propose expansive lexicon-patch alignment (ELA) to align image patches with a vocabulary rather than only the words explicitly in the text for annotation-free alignment and information augmentation.
Outcome:	The proposed method outperforms state-of-the-art methods on cross-modal retrieval and can learn representative fine-grained information.

Copied to clipboard

Bojian Jiang, Yi Jing, Tong Wu, Tianhao Shen, Deyi Xiong, Qing Yang

The Death and Life of Great Prompts: Analyzing the Evolution of LLM Prompts from the Structural Perspective (2024.emnlp-main)

Challenge:	Automated red teaming (ART) is effective but time-consuming, costly and lacks scalability.
Approach:	They propose an automated red teaming framework that generates adversarial prompts to expose LLM vulnerabilities.
Outcome:	The proposed framework explores and exploits LLM vulnerabilities through multi-round interactions.

Copied to clipboard

Yihan Ma, Xinyue Shen, Yixin Wu, Boyang Zhang, Michael Backes, Yang Zhang

Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification (2025.emnlp-main)

Challenge:	Recent research has shown that high-quality prompts are essential for LLMs to produce accurate and relevant responses.
Approach:	They analyze 10,538 in-the-wild prompts collected from various platforms and develop a framework that decomposes the prompts into eight key components.
Outcome:	The proposed framework decomposes 10,538 in-the-wild prompts into eight components.

Copied to clipboard

Boyang Zhang, Yicong Tan, Yun Shen, Ahmed Salem, Michael Backes, Savvas Zannettou, Yang Zhang

WebClipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruning (2026.acl-long)

Challenge:	Recent advances in large language models (LLMs) have increased the vulnerability of LLMs, but they can cause more severe damage than standalone systems if compromised.
Approach:	They propose a new type of attack that induces malfunctions by misleading the agent into executing repetitive or irrelevant actions.
Outcome:	The proposed attacks induce failure rates exceeding 80% in multiple scenarios, highlighting the substantial risks associated with this vulnerability.

Copied to clipboard

Junjie Wang, Zequn Xie, Dan Yang, Jie Feng, Yue Shen, Duolin Sun, Meixiu Long, Yihan Jiao, Zhehao Tan, Jian Wang, Peng Wei, Jinjie Gu

Structured Data in NLP

Challenge:	Open-source web agents rely on long tool-call trajectories with cyclic reasoning loops and exploration of unproductive branches.
Approach:	They propose a framework that compresses web agent trajectories via graph-based pruning.
Outcome:	The proposed framework reduces tool-call rounds by 20% while improving accuracy and efficiency while maintaining the same level of performance as existing models.

Boosting Summarization with Normalizing Flows and Aggressive Training (2023.emnlp-main)

Copied to clipboard

Yu Yang, Xiaotong Shen

ReasonAny: Incorporating Reasoning Capability to Any Model via Simple and Effective Model Merging (2026.acl-long)

Challenge:	Experimental results show that FlowSUM improves the quality of generated summaries with minimal impact on inference time.
Approach:	They propose a normalizing flows-based variational encoder-decoder framework for Transformer-based summarization.
Outcome:	The proposed model improves the quality of generated summaries and reduces inference time.

Copied to clipboard

Junyao Yang, Chen Qian, Wen Shen, Yong Liu, Jing Shao, Dongrui Liu

GeAR: Graph-enhanced Agent for Retrieval-augmented Generation (2025.findings-acl)

Challenge:	Existing models with long chain-of-thought reasoning lack reasoning depth and domain-specific utility.
Approach:	They propose a model merging framework that integrates reasoning with domain-specific task models.
Outcome:	The proposed model merging framework outperforms state-of-the-art models while maintaining robust reasoning performance.

Copied to clipboard

Zhili Shen, Chenxin Diao, Pavlos Vougiouklis, Pascual Merita, Shriram Piramanayagam, Enting Chen, Damien Graux, Andre Melo, Ruofei Lai, Zeren Jiang, Zhongyang Li, Ye Qi, Yang Ren, Dandan Tu, Jeff Z. Pan

Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs (2024.findings-emnlp)

Challenge:	Retrieval-augmented Generation (RAG) relies on effective retrieval capabilities, yet traditional sparse and dense retrievers struggle with multi-hop retrieval scenarios.
Approach:	They propose a graph expansion mechanism that augments any conventional base retriever and an agent framework that incorporates the resulting graph-based retrieval into a multi-step retrieval framework.
Outcome:	The proposed system achieves state-of-the-art results on three multi-hop question answering datasets while consuming fewer tokens and requiring fewer iterations than existing multi-step retrieval systems.

Copied to clipboard

Junjie Wang, Mingyang Chen, Binbin Hu, Dan Yang, Ziqi Liu, Yue Shen, Peng Wei, Zhiqiang Zhang, Jinjie Gu, Jun Zhou, Jeff Pan, Wen Zhang, Huajun Chen

HiddenCut: Simple Data Augmentation for Natural Language Understanding with Better Generalizability (2021.acl-long)

Challenge:	Recent studies have attempted to enhance the performance of large language models (LLMs) in complex question-answering (QA) tasks by combining step-wise planning with external retrieval.
Approach:	They propose a framework for enhancing LLMs’ planning capabilities by using planning data derived from knowledge graphs (KGs).
Outcome:	The proposed framework improves LLMs’ planning capabilities by using knowledge graphs (KGs) the proposed framework is compared with existing frameworks on multiple datasets and shows that it is effective for large language models.

Copied to clipboard

Jiaao Chen, Dinghan Shen, Weizhu Chen, Diyi Yang

Perplexity-Aware Data Scaling Law: Perplexity Landscapes Predict Performance for Continual Pre-training (2026.acl-long)

Challenge:	Using data augmentation to fine-tune pre-trained models with task-specific data has been shown to be ineffective and redundant during fine-timing.
Approach:	They propose a data augmentation technique to regularize pre-trained models and encourage them to learn more generalizable features by dropping contiguous spans during training.
Outcome:	The proposed method outperforms state-of-the-art methods on the GLUE benchmark and consistently exhibits superior generalization performances on out-of distribution and challenging counterexamples.

Copied to clipboard

Lei Liu, Hao Zhu, Xiaoyan Yang, Yue Shen, Zhixuan Chu, Jian Wang, Jinjie Gu, Kui Ren

Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning (2026.acl-long)

Challenge:	Large language models (LLMs) have impressive capabilities across a wide range of domains, but their generalpurpose pre-training objectives often leave them illsuited for specialized applications such as healthcare.
Approach:	They propose a perplexity-aware data scaling law that establishes a predictive relationship between the perplexities of domain-specific data and the test loss.
Outcome:	Experiments on medical and general-domain benchmarks show that the proposed scaling law consistently identifies near-optimal training subsets with significantly reduced data consumption.

Copied to clipboard

Naixin Zhai, Pengyang Shao, Binbin Zheng, Yonghui Yang, Fei Shen, Long Bai, Xun Yang

Challenge:	Existing approaches to machine unlearning treat all tokens indiscriminately and enforce uncertainty over the entire vocabulary.
Approach:	They propose a framework that targets the prefix in a response and minimizes uncertainty in the critical subspace.
Outcome:	The proposed framework achieves superior forgetting efficacy and utility preservation compared to baselines.

The Mirage of Model Editing: Revisiting Evaluation in the Wild (2025.acl-long)

Copied to clipboard

Wanli Yang, Fei Sun, Jiajun Tan, Xinyu Ma, Qi Cao, Dawei Yin, Huawei Shen, Xueqi Cheng

Question Answering

Challenge:	despite near-perfect results, effectiveness of model editing in real-world applications remains unclear.
Approach:	They propose QAEdit and WILD to better reflect real-world use of model editing . they propose a benchmark aligned with widely used question answering datasets and a task-agnostic evaluation framework .
Outcome:	The proposed QAEdit benchmark and WILD evaluation framework show that current models perform worse than previously reported.

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.

E-ConvRec: A Large-Scale Conversational Recommendation Dataset for E-Commerce Customer Service (2022.lrec-1)

Copied to clipboard

Meihuizi Jia, Ruixue Liu, Peiying Wang, Yang Song, Zexi Xi, Haobin Li, Xin Shen, Meng Chen, Jinhui Pang, Xiaodong He

Natural Language Interfaces

Challenge:	Recent research has focused on developing conversational recommendation system (CRS), which provides valuable recommendations to users through conversations.
Approach:	They construct an authentic Chinese dialogue dataset consisting of over 25k dialogues and 770k utterances, which contains user profile, product knowledge base, and multiple sequential real conversations between users and recommenders.
Outcome:	The proposed dataset contains user profile, product knowledge base, and multiple sequential real conversations between users and recommenders.

Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement Learning (2026.acl-long)

Copied to clipboard

Xuanyu Lei, Chenliang Li, Yuning Wu, Kaiming Liu, Weizhou Shen, Peng Li, Ming Yan, Fei Huang, Ya-Qin Zhang, Yang Liu

Challenge:	Recent advances in Large Language Models (LLMs) have enabled strong performance in long-form writing, but current training paradigms remain limited.
Approach:	They propose an Adaptive Curriculum Reinforcement Learning framework to advance long-form writing capabilities beyond SFT.
Outcome:	Experiments on 7B-scale writer models show that Writing-RL improves long-form writing performance over strong SFT baselines.

Visual Evidence Prompting Mitigates Hallucinations in Large Vision-Language Models (2025.acl-long)

Copied to clipboard

Wei Li, Zhen Huang, Houqiang Li, Le Lu, Yang Lu, Xinmei Tian, Xu Shen, Jieping Ye

MReD: A Meta-Review Dataset for Structure-Controllable Text Generation (2022.findings-acl)

Challenge:	LVLMs have shown impressive progress by integrating visual perception with linguistic understanding to produce contextually grounded outputs.
Approach:	They propose a visual evidence prompting method to mitigate hallucinations in large vision-language models by using small visual models to complement them.
Outcome:	The proposed method reduces hallucinations by reducing false activation and enhancing correct ones.

Copied to clipboard

Chenhui Shen, Liying Cheng, Ran Zhou, Lidong Bing, Yang You, Luo Si

Mutual-Taught for Co-adapting Policy and Reward Models (2025.acl-long)

Challenge:	a new text generation dataset is needed to controllable text summarization, but it lacks the domain knowledge.
Approach:	They propose to use existing text generation datasets to leverage input and control signals . they propose to annotate each meta-review sentence manually with a control signal .
Outcome:	The proposed method can be used to control the structure of a text generation dataset . it can be applied to a variety of tasks, including a task with a large number of meta-review sentences .

Copied to clipboard

Tianyuan Shi, Canbin Huang, Fanqi Wan, Longguang Zhong, Ziyi Yang, Weizhou Shen, Xiaojun Quan, Ming Yan

Machine Translation

Challenge:	Experimental results show that this iterative approach leads to consistent improvements in both the policy model and reward model.
Approach:	They propose a method that iteratively improves both the policy model and reward model without requiring additional human annotation.
Outcome:	The proposed method improves both the policy model and reward model without human annotation.

MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct (2025.findings-acl)

Copied to clipboard

Run Luo, Haonan Zhang, Longze Chen, Ting-En Lin, Xiong Liu, Yuchuan Wu, Min Yang, Yongbin Li, Minzheng Wang, Pengpeng Zeng, Lianli Gao, Heng Tao Shen, Yunshui Li, Hamid Alinejad-Rokny, Xiaobo Xia, Jingkuan Song, Fei Huang

Large Language Models are Not Yet Human-Level Evaluators for Abstractive Summarization (2023.findings-emnlp)

Challenge:	a new framework for image-text instruction data evolution improves MLLM performance . lack of high-quality instruction data remains a major bottleneck in ML modeling .
Approach:	They propose a multimodal instruction data evolution framework that iteratively enhances data quality through fine-grained perception, cognitive reasoning, and interaction evolution.
Outcome:	The proposed approach improves MLLM performance in nine vision-language tasks while using significantly less data.

Copied to clipboard

Chenhui Shen, Liying Cheng, Xuan-Phi Nguyen, Yang You, Lidong Bing

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

Challenge:	ChatGPT and GPT-4 are popular as evaluation metric for complex generative tasks . however, they are not ready as human replacements due to significant limitations .
Approach:	They conduct extensive analysis to examine the stability and reliability of LLMs as automatic evaluators for abstractive summarization.
Outcome:	The proposed methods outperform the commonly used automatic metrics but are not ready for human evaluation due to significant limitations.

Copied to clipboard

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

PFDial: A Structured Dialogue Instruction Fine-tuning Method Based on UML Flowcharts (2025.findings-acl)

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 .

Copied to clipboard

Ming Zhang, Yuhui Wang, Yujiong Shen, Tingyi Yang, Changhao Jiang, Yilong Wu, Shihan Dou, Qinhao Chen, Zhiheng Xi, Zhihao Zhang, Yi Dong, Zhen Wang, Zhihui Fei, Mingyang Wan, Tao Liang, Guojun Ma, Qi Zhang, Tao Gui, Xuanjing Huang

JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs (2025.acl-long)

Challenge:	Large Language Models (LLMs) have shown remarkable progress in dialogue and reasoning, but they struggle to solve strictly constrained dialogue tasks.
Approach:	They construct a dataset that contains 12,705 high-quality Chinese dialogue instructions from 440 flowcharts containing 5,055 process nodes.
Outcome:	The proposed model outperforms GPT-4o models on backward transitions and outperformed GPT-42 models on the same dataset.

Copied to clipboard

Junjie Chu, Yugeng Liu, Ziqing Yang, Xinyue Shen, Michael Backes, Yang Zhang

Composite Backdoor Attacks Against Large Language Models (2024.findings-naacl)

Challenge:	Large language models (LLMs) have been used to mitigate misuse and to align with human values.
Approach:	They propose to use large-scale evaluations of various jailbreak attacks to identify key patterns and test them under eight advanced defenses.
Outcome:	The proposed attacks achieve high success rates but are easy to mitigate by defenses.

Copied to clipboard

Hai Huang, Zhengyu Zhao, Michael Backes, Yun Shen, Yang Zhang

Unveiling the Unknown: Open-Set Entity Typing via Two-Stage Generation (2026.acl-long)

Challenge:	Large language models (LLMs) have demonstrated superior performance on various tasks, but untrustworthy third-party LLMs may covertly introduce vulnerabilities for downstream tasks.
Approach:	They propose a composite backdoor attack that scatters multiple trigger keys in different prompt components.
Outcome:	The proposed attack achieves 100% Attack Success Rate (ASR) with a False Triggered Rate (FTR) below 2.06% and negligible model accuracy degradation.

Copied to clipboard

Hu Chen, Binhan Yang, Wei Shen

ParaCook: On Time-Efficient Planning for Multi-Agent Systems (2026.findings-acl)

Challenge:	Existing fine-grained entity typing models are susceptible to misclassify unknown-type instances . manual collection and annotation of large unknown-Type instances is time-consuming and labor-intensive in open environments.
Approach:	They propose a novel task that uses open-set entity typing to classify entities of unknown types . they propose 'two-stage generation model' that automatically produces large-scale pseudo unknown-type instances .
Outcome:	The proposed framework surpasses baselines on two newly established benchmark datasets.

Copied to clipboard

Shiqi Zhang, Xinbei Ma, Yunqing Xu, Zouying Cao, Pengrui Lu, Haobo Yuan, Tiancheng Shen, Zhuosheng Zhang, Hai Zhao, Ming-Hsuan Yang

Green & Sustainable NLP

Challenge:	Existing agent benchmarks focus on task completion while neglecting time efficiency in parallel and asynchronous operations.
Approach:	They propose a framework for large language models that allows agents to plan long-horizon tasks in a scalable way.
Outcome:	The proposed framework is based on the Overcooked game and can be used to evaluate time efficiency-aware multi-agent planning.

HIRAG: Hierarchical-Thought Instruction-Tuning Retrieval-Augmented Generation (2025.findings-emnlp)

Copied to clipboard

Yihan Jiao, Zhehao Tan, Dan Yang, Duolin Sun, Jie Feng, Yue Shen, Jian Wang, Peng Wei

Reasoning-Enhanced Domain-Adaptive Pretraining of Multimodal Large Language Models for Short Video Content Governance (2025.emnlp-industry)

Challenge:	In-depth research on the specific capabilities needed by the RAG generation model is lacking, leading to inconsistent document quality and retrieval system imperfections.
Approach:	They propose that RAG models should possess three progressively hierarchical abilities: (1) Filtering: the ability to select relevant information; (2) Combination: the capability to combine semantic information across paragraphs; (3) RAG-specific reasoning: the capacity to further process external knowledge using internal knowledge.
Outcome:	Experiments show that the proposed method significantly improves the model’s open-book examination capability on datasets such as RGB, PopQA, MuSiQue, HotpotQA, and PubmedQA.

Copied to clipboard

Zixuan Wang, Yu Sun, Hongwei Wang, Baoyu Jing, Xiang Shen, Xin Dong, Zhuolin Hao, Hongyu Xiong, Yang Song

SPARK: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning (2026.acl-long)

Challenge:	Existing approaches to identifying inappropriate content require extensive human-labeled data and lack cross-issue generalization.
Approach:	They propose a reasoning-enhanced multimodal large language model (MLLM) pretraining paradigm for unified inappropriate content detection.
Outcome:	The proposed model improves the MLLM's performance in both zero-shot and supervised fine-tuning settings and shows strong generalization capabilities to emergent, previously unseen issues.

Copied to clipboard

Jinyang Wu, Shuo Yang, Yuhao Shen, Shuai Zhang, Zhengqi Wen, Jianhua Tao

Challenge:	Existing methods for training large language models waste computation budget on trivial steps while failing to guarantee sample quality.
Approach:	They propose a framework that selectively branches at critical decision states for resource-efficient exploration.
Outcome:	The proposed framework activates adaptive branching exploration at critical decision states to probe promising trajectories, thereby achieving precise resource allocation that prioritizes sampling quality over blind coverage.

Evaluating Memory Capability in Continuous Lifelog Scenario (2026.findings-acl)

Copied to clipboard

Jianjie Zheng, Zhichen Liu, Zhanyu Shen, Jingxiang Qu, Guanhua Chen, Yile Wang, Yang Xu, Yang Liu, Sijie Cheng

Challenge:	Existing benchmarks focus on online one-on-one chatting or human-AI interactions, neglecting real-world scenarios.
Approach:	They propose a framework to curate a lifelog benchmark that combines two subsets of audio data to address temporal leakage in offline settings.
Outcome:	The proposed framework outperforms existing benchmarks on live chats and AI interactions.

Automatically Select Emotion for Response via Personality-affected Emotion Transition (2021.findings-acl)

Copied to clipboard

Zhiyuan Wen, Jiannong Cao, Ruosong Yang, Shuaiqi Liu, Jiaxing Shen

CrowdSelect: SyntheticInstruction Data Selection with Multi-LLM Wisdom (2026.findings-eacl)

Challenge:	Existing studies focus on rendering specified emotions in responses, yet the individual difference in emotion expression is overlooked.
Approach:	They propose to equip a dialog system with personality and enable it to select emotions in responses like humans.
Outcome:	The proposed system can select emotions in responses like humans by simulating the emotion transition of humans in conversation.

Copied to clipboard

Yisen Li, Lingfeng Yang, Wenxuan Shen, Pan Zhou, Yao Wan, Weiwei Lin, Dongping Chen

Machine Translation

Challenge:	Existing methods for capturing instruction-following complexity rely on single-dimensional signals, but they fail to capture complexity across diverse fields.
Approach:	They propose three foundational metrics that leverage Multi-LLMs wisdom to capture instruction-response pair characteristics and propose CrowdSelect, an integrated metric incorporating a clustering-based approach to maintain response diversity.
Outcome:	The proposed metrics outperform existing models on MT-bench and Arena-hard and show improvements of 4.81% on full and LoRA fine-tuning.

PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning (2026.findings-acl)

Copied to clipboard

Ruixiang Feng, Yuntao Wen, Silin Zhou, Ke Shi, Yifan Wang, Ran Le, Zhenwei An, Zongchao Chen, Chen Yang, Guangyue Peng, Yiming Jia, Dongsheng Wang, Tao Zhang, Lisi Chen, Yang Song, Shen Gao, Shuo Shang

Are We in the AI-Generated Text World Already? Quantifying and Monitoring AIGT on Social Media (2025.acl-long)

Challenge:	Existing LRMs often suffer from "overthinking" and excessively long reasoning traces . a dual-level framework for length compression of LRM is proposed .
Approach:	They propose a framework for prefix-protected and difficulty-aware compression under hierarchical supervision.
Outcome:	The proposed framework reduces token usage while improving accuracy on math benchmarks.

Copied to clipboard

Zhen Sun, Zongmin Zhang, Xinyue Shen, Ziyi Zhang, Yule Liu, Michael Backes, Yang Zhang, Xinlei He

Agentic Episodic Control (2026.findings-acl)

Challenge:	Social media platforms are experiencing a growing presence of AI-Generated Texts (AIGTs) however, the misuse of AIGTs could have profound implications for public opinion .
Approach:	They collect a dataset with 2.4M posts from 3 major social media platforms . they then construct a diverse dataset to train and evaluate AIGT detectors .
Outcome:	The proposed dataset analyzes 2.4M posts from 3 major social media platforms from 2022 to 2024 . it finds that Medium and Quora show marked increases in AAR .

Copied to clipboard

Xidong Yang, Wenhao Li, Junjie Sheng, Yun Hua, Haosheng Chen, Chuyun Shen, Xiangfeng Wang

Green & Sustainable NLP

Challenge:	Existing methods for reinforcement learning (RL) are limited by poor data efficiency and weak generalization.
Approach:	They propose a novel architecture that integrates large language models into episodic RL.
Outcome:	The proposed architecture achieves 2–6 higher data efficiency than baselines and is the only method to solve complex tasks like UnlockLocal with over 90% success.

LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning (2024.findings-acl)

Copied to clipboard

Mingyang Zhang, Hao Chen, Chunhua Shen, Zhen Yang, Linlin Ou, Xinyi Yu, Bohan Zhuang

Tackling Modality Heterogeneity with Multi-View Calibration Network for Multimodal Sentiment Detection (2023.acl-long)

Challenge:	Low-rank adaption (LoRA) is a low-level pruning method that can be expensive and slow to deploy.
Approach:	They propose a low-rank adaption pruning framework that provides an accurate structured pruned model in a memory-efficient manner.
Outcome:	The proposed pruning framework reduces perplexity and memory usage by 52.6% on LLaMA and T5 models while reducing memory usage.

Copied to clipboard

Yiwei Wei, Shaozu Yuan, Ruosong Yang, Lei Shen, Zhangmeizhi Li, Longbiao Wang, Meng Chen

Constituency Lattice Encoding for Aspect Term Extraction (2020.coling-main)

Challenge:	Existing studies focus on fusing different features but ignore the challenge of modality heterogeneity.
Approach:	They propose a text-guided fusion module with novel Sparse-Attention to reduce the negative impacts of redundant visual elements and a sentiment-based congruity constraint task to calibrate the feature shift in the representation space.
Outcome:	The proposed model is competitive against existing methods and achieves state-of-the-art results on two public benchmark datasets.

Copied to clipboard

Yunyi Yang, Kun Li, Xiaojun Quan, Weizhou Shen, Qinliang Su

Sentiment Analysis

Challenge:	a challenge for aspect term extraction is to extract phrase-level aspect terms . a constituency lattice structure is constructed using the span annotations of constituents of a sentence .
Approach:	They propose to incorporate the span annotations of constituents of a sentence to leverage syntactic information in neural network models.
Outcome:	The proposed model outperforms existing models on two benchmark datasets.

CSP:Code-Switching Pre-training for Neural Machine Translation (2020.emnlp-main)

Copied to clipboard

Zhen Yang, Bojie Hu, Ambyera Han, Shen Huang, Qi Ju

Multilinguality

Challenge:	Existing methods to train neural machine translation models are data-hungry and low-resource . et al., 2018; Radford e.t., 2019; Yang ee.,2019) proposes a new pre-training method for NMT .
Approach:	They propose a new pre-training method which randomly replaces some words in the input sentence with their translation words in target language.
Outcome:	The proposed method improves on unsupervised and supervised NMT models by making full use of monolingual corpora.

UNComp: Can Matrix Entropy Uncover Sparsity? — A Compressor Design from an Uncertainty-Aware Perspective (2025.emnlp-main)

Copied to clipboard

Jing Xiong, Jianghan Shen, Fanghua Ye, Chaofan Tao, Zhongwei Wan, Jianqiao Lu, Xun Wu, Chuanyang Zheng, Zhijiang Guo, Min Yang, Lingpeng Kong, Ngai Wong

MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning (2025.emnlp-main)

Challenge:	Deploying large language models (LLMs) for long-context inference remains challenging due to their substantial memory and computational demands.
Approach:	They propose an uncertainty-aware framework that leverages truncated matrix entropy to identify areas of low information content.
Outcome:	The proposed framework reduces the KV cache size to 4.74% of the original and achieves a 6% speedup.

Copied to clipboard

Jingyan Shen, Jiarui Yao, Rui Yang, Yifan Sun, Feng Luo, Rui Pan, Tong Zhang, Han Zhao

PLAWBENCH: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice (2026.acl-long)

Challenge:	Existing reward models assume a global reward function, limiting personalization and pluralistic alignment.
Approach:	They propose a framework that leverages binary preference datasets to enhance personalized preference learning.
Outcome:	The proposed framework captures diverse human preferences without fine-grained annotations and significantly improves personalized preference learning on downstream tasks.

Copied to clipboard

Yuzhen Shi, Huanghai Liu, Yiran HU, Song Gaojie, Xu Xinran, Yubo Ma, Tianyi Tang, Li Zhang, Qingjing Chen, Feng Di, Wenbo Lv, Weiheng Wu, Kexin Yang, Sen Yang, Wei Wang, Rongyao Shi, Qiu Yuanyang, Yuemeng Qi, Zhang Jingwen, Sui Xiaoyu, Yifan Chen, Zhang Yi, An Yang, Bowen Yu, Dayiheng Liu, Junyang Lin, Weixing Shen, Bing Zhao, Charles L. A. Clarke, HU Wei

Agent-GWO: Collaborative Agents for Dynamic Prompt Optimization in Large Language Models (2026.findings-acl)

Challenge:	Existing benchmarks for large language models (LLMs) are coarse, single-dimensional metrics and do not explicitly assess fine-grained legal reasoning.
Approach:	They propose a Practical Law Benchmark to evaluate large language models in real-world legal practice scenarios.
Outcome:	The proposed model is based on 850 questions and 13 scenarios with expert-designed evaluation rubrics.

Copied to clipboard

Xudong Wang, Chaoning Zhang, Chenghao Li, Shuxu Chen, Qigan Sun, Jiaquan Zhang, Fachrina Dewi Puspitasari, Tae-Ho Kim, Jiwei Wei, Malu Zhang, Guoqing Wang, Yang Yang, Heng Tao Shen

CDL: Curriculum Dual Learning for Emotion-Controllable Response Generation (2020.acl-main)

Challenge:	Existing automatic prompt optimization methods fail to optimize prompts and decoding hyperparameters within a unified framework to achieve stable global improvements.
Approach:	They propose a dynamic prompt optimization framework for complex reasoning that unifies prompt templates and decodes hyperparameters as inheritable agent configurations.
Outcome:	Experiments on multiple mathematical and hybrid reasoning benchmarks show that Agent-GWO improves accuracy and stability over existing prompt optimization methods.

Copied to clipboard

Lei Shen, Yang Feng

False Friends in the Shell: Unveiling the Emoticon Semantic Confusion in Large Language Models (2026.acl-long)

Challenge:	Existing methods for generating emotion-controllable response are inadequate due to content consistency and lack of coherence.
Approach:	They propose a framework that extends the emotion-controllable response generation to a dual task to generate emotional responses and emotional queries alternatively.
Outcome:	The proposed framework outperforms baseline models in coherence, diversity, and relation to emotion factors.

Copied to clipboard

Weipeng Jiang, Xiaoyu Zhang, Juan Zhai, Shiqing Ma, Chao Shen, Yang Liu

A Systematic Assessment of Language Models with Linguistic Minimal Pairs in Chinese (2026.tacl-1)

Challenge:	Emoticons are widely used in digital communication to convey affective intent, yet their safety implications for Large Language Models (LLMs) remain largely unexplored.
Approach:	They propose to use ASCII-based emoticons to perform unintended actions in large language models (LLMs) This vulnerability is pervasive, with an average confusion ratio exceeding 38%, and 90% of confused responses yield 'silent failures' authors call on the community to recognize this emerging vulnerability and develop effective mitigation methods to uphold the safety and reliability of human-LLM interactions.
Outcome:	The proposed framework exploits emoticon semantic confusion in six LLMs and demonstrates that existing prompt-based mitigations are ineffective.

Copied to clipboard

Yikang Liu, Yeting Shen, Hongao Zhu, Lilong Xu, Zhiheng Qian, Siyuan Song, Kejia Zhang, Jialong Tang, Pei Zhang, Baosong Yang, Rui Wang, Hai Hu

Tree-of-Code: A Self-Growing Tree Framework for End-to-End Code Generation and Execution in Complex Tasks (2025.findings-acl)

Challenge:	Using sub-linear length normalized log-probabilities (SLLN-LP), we find unequal lengths of sentences in minimal pairs difficult for LMs even up to 32B parameters.
Approach:	They propose to use ZhoBLiMP as a linguistic minimal pair benchmark for Chinese language models to mitigate biases.
Outcome:	The proposed metric mitigates biases in Chinese language models with over 100 paradigms . Anaphor, Quantifiers, and Ellipsis are difficult for LMs even up to 32B parameters .

Copied to clipboard

Ziyi Ni, Yifan Li, Ning Yang, Dou Shen, Pin Lyu, Daxiang Dong

Programming Languages in NLP

Challenge:	Effectively and efficiently handling complex realworld problems has become a key focus across industry and academia.
Approach:	They propose a tree-of-code framework that generates nodes through self-supervision and combines prompt and model exploration in a GT-free setting.
Outcome:	Experiments on two datasets with ten popular zero-shot LLMs show that Tree-of-Code boosts accuracy by nearly 20% over CodeAct with fewer than 1/4 turns.

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 .

From Observation to Understanding: Front-Door Adjustments with Uncertainty Calibration for Enhancing Egocentric Reasoning in LVLMs (2025.findings-acl)

Copied to clipboard

Shenshen Li, Wenxin Meng, Lei Wang, Hao Yang, Chong Peng, Peng Yan, Fumin Shen, Jingkuan Song, Heng Tao Shen, Xing Xu

Low-Resource NLP

Challenge:	Existing methods that adapt LVLMs to egocentric tasks overlook critical agent-environment interactions, limiting their ability to perform egoic reasoning.
Approach:	They propose a zero-shot paradigm to enhance egocentric reasoning by simulating human causal reasoning by formalizing ego-centric reasoning using a structural causal model.
Outcome:	The proposed method improves egocentric reasoning abilities on six tasks.

DeltaNet: Conditional Medical Report Generation for COVID-19 Diagnosis (2022.coling-1)

Copied to clipboard

Xian Wu, Shuxin Yang, Zhaopeng Qiu, Shen Ge, Yangtian Yan, Xingwang Wu, Yefeng Zheng, S. Kevin Zhou, Li Xiao

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

Challenge:	X-ray and CT are the gold standard for COVID-19 diagnosis and treatment . however, due to the excessive number of patients, writing reports becomes a heavy burden for radiologists.
Approach:	They propose to use X-ray and CT to generate medical reports automatically . they evaluate DeltaNet on a COVID-19 dataset, where it outperforms state-of-the-art approaches .
Outcome:	The proposed system outperforms state-of-the-art methods on a COVID-19 dataset.

Copied to clipboard

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

CODEMENV: Benchmarking Large Language Models on Code Migration (2025.findings-acl)

Challenge:	Existing multimodal Mixture-of-Experts models accurately perceive image content yet fail in subsequent reasoning . Seeing but not thinking phenomenon is a puzzling phenomenon .
Approach:	They propose a routing-guided intervention method that enhances domain expert activation.
Outcome:	The proposed method achieves consistent improvements on visual reasoning tasks.

Copied to clipboard

Keyuan Cheng, Xudong Shen, Yihao Yang, TengyueWang TengyueWang, Yang Cao, Muhammad Asif Ali, Hanbin Wang, Lijie Hu, Di Wang

Rethinking Token Reduction for State Space Models (2024.emnlp-main)

Challenge:	Large language models (LLMs) have demonstrated remarkable proficiency in handling a wide range of tasks within the software engineering domain, but their ability to perform code migration—adapting code to different environments—remains underexplored.
Approach:	They propose a benchmark to evaluate large language models’ performance in handling code migration tasks.
Outcome:	The proposed benchmark comprises 922 data points across 19 Python and Java packages and offers three tasks to systematically evaluate code migration: identifying version-incompatible functions, determining function changes, and adapting code to target environments.

Copied to clipboard

Zheng Zhan, Yushu Wu, Zhenglun Kong, Changdi Yang, Yifan Gong, Xuan Shen, Xue Lin, Pu Zhao, Yanzhi Wang

Challenge:	Existing methods for token reduction for SSMs lead to performance drops . a recent study shows that Mamba-2 improves the accuracy of the model by 5.7% to 13.1% .
Approach:	They propose a token reduction method that integrates token importance and similarity into SSMs and takes advantage of pruning and merging.
Outcome:	The proposed method improves accuracy by 5.7% to 13.1% on six benchmarks with Mamba-2 compared to existing methods while reducing computational demands and memory requirements.

Noisy Self-Knowledge Distillation for Text Summarization (2021.naacl-main)

Copied to clipboard

Yang Liu, Sheng Shen, Mirella Lapata

Summarization

Challenge:	Existing approaches to summarize text using a single reference and noisy datasets are ill-suited to summarising on single reference datasets.
Approach:	They propose to use self-knowledge distillation to improve text summarization by generating smoothed labels for students and teachers to reduce model uncertainty.
Outcome:	The proposed framework improves on pretrained and non-pretrained models on three benchmarks.

Self-Rewarding Large Vision-Language Models for Optimizing Prompts in Text-to-Image Generation (2025.findings-acl)

Copied to clipboard

Hongji Yang, Yucheng Zhou, Wencheng Han, Jianbing Shen

SentBS: Sentence-level Beam Search for Controllable Summarization (2022.emnlp-main)

Challenge:	Existing methods for rewriting text-to-image models require specialized vocabulary . a new approach uses large vision language models to optimize text-based models .
Approach:	They propose a prompt optimization framework that rephrases a user prompt into a text-to-image model by using large vision language models as solver and reward model.
Outcome:	The proposed model outperforms existing models on two popular datasets.

Copied to clipboard

Chenhui Shen, Liying Cheng, Lidong Bing, Yang You, Luo Si

Improving Latent Alignment in Text Summarization by Generalizing the Pointer Generator (D19-1)

Challenge:	Structure-controlled summarization is a useful and interesting research direction . current structure-controlling methods have limited effectiveness in enforcing the desired structure.
Approach:	They propose a sentence-level beam search generation method to select suitable sentences for subsequent generations.
Outcome:	The proposed method significantly reduces structural discrepancies by 68% on a structure-controlled dataset.

Copied to clipboard

Xiaoyu Shen, Yang Zhao, Hui Su, Dietrich Klakow

SWE-Swiss: A Multi-Task Fine-Tuning and RL Recipe for High-Performance Issue Resolution (2026.findings-acl)

Challenge:	Modern pointer generators only capture exact word matches, ignoring possible inflections or abstractions, which restricts its power of capturing richer latent alignment.
Approach:	They propose a pointer generator architecture that allows the model to "edit" pointed tokens instead of always copying them.
Outcome:	The proposed model captures more latent alignment relations than exact word matches and generates higher-quality summaries validated by both qualitative and quantitative evaluations.

Copied to clipboard

Zhenyu He, Qingping Yang, Wei Shen, Xiaojian Zhong, Kechi Zhang, Chenxin An, Wenlei Shi, Tianle Cai, Di He, Jiaze Chen, Jingjing Xu

SQL Generation via Machine Reading Comprehension (2020.coling-main)

Challenge:	SWE-Swiss-32B demonstrates strong generalization to other common LLM benchmarks.
Approach:	They propose a two-phase training recipe that decomposes issue resolution into three core skills: Localization, Repair, and Unit Test Generation.
Outcome:	The proposed model achieves a 60.2% score on the SWE-bench Verified benchmark and is in the top-tier performance bracket of much larger models.

Copied to clipboard

Zeyu Yan, Jianqiang Ma, Yang Zhang, Jianping Shen

Programming Languages in NLP

Challenge:	Text-to-SQL systems can generate SQL queries given natural language questions.
Approach:	They propose a method that formulates a question answering problem as a query answering problem where different slots are predicted by a unified machine reading comprehension (MRC) model.
Outcome:	The proposed method can achieve competitive results on WikiSQL, suggesting it being a promising direction for text-to-SQl.

Syntax-Infused Variational Autoencoder for Text Generation (P19-1)

Copied to clipboard

Xinyuan Zhang, Yi Yang, Siyang Yuan, Dinghan Shen, Lawrence Carin

Syntactic Text Processing

Challenge:	Experimental results demonstrate the generative superiority of SIVAE on both reconstruction and targeted syntactic evaluations.
Approach:	They propose a syntax-infused variational autoencoder that integrates sentences with their syntactic trees to improve the grammar of generated sentences.
Outcome:	The proposed model improves the grammar of generated sentences by integrating sentences with syntactic trees.

Bootstrapping Code Translation with Weighted Multilanguage Exploration (2026.acl-long)

Copied to clipboard

Yuhan Wu, Huan Zhang, Wei Cheng, Chen Shen, Jingyue Yang, Wei Hu

Multilinguality

Challenge:	Existing methods to improve code translation depend on abundant parallel code of high quality, which may not always be available.
Approach:	They propose a method that leverages functional invariance and cross-lingual portability of test suites to serve as universal verification oracles for multilingual reinforcement learning.
Outcome:	The proposed method leverages functional invariance and cross-lingual portability of test suites to serve as universal verification oracles for multilingual reinforcement learning (RL) training.

ModSCAN: Measuring Stereotypical Bias in Large Vision-Language Models from Vision and Language Modalities (2024.emnlp-main)

Copied to clipboard

Yukun Jiang, Zheng Li, Xinyue Shen, Yugeng Liu, Michael Backes, Yang Zhang

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

Challenge:	Large vision-language models have been widely used but stereotypical biases are unexplored.
Approach:	They propose a framework to SCAN stereotypical bias within large vision-language models . they examine stereotype biases with respect to gender and race in three scenarios .
Outcome:	The proposed framework can reduce stereotypical biases in large vision-language models . the currently popular models show significant stereotype biase .

Copied to clipboard

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

Scaling Under-Resourced TTS: A Data-Optimized Framework with Advanced Acoustic Modeling for Thai (2025.acl-industry)

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.

Copied to clipboard

Yizhong Geng, Jizhuo Xu, Zeyu Liang, Jinghan Yang, Xiaoyi Shi, Xiaoyu Shen

Low-Resource NLP

Challenge:	Text-to-speech (TTS) systems are limited by limited data and linguistic complexities.
Approach:	They propose a data-optimized framework with an advanced acoustic model to build high-quality TTS systems for low-resource scenarios.
Outcome:	The proposed framework enables zero-shot voice cloning and improved performance across diverse client applications, including finance, healthcare, education, and law.

DT-QDC: A Dataset for Question Comprehension in Online Test (2020.coling-main)

Copied to clipboard

Sijin Wu, Yujiu Yang, Nicholas Yung, Zhengchen Shen, Zeyang Lei

Non-Autoregressive Math Word Problem Solver with Unified Tree Structure (2023.emnlp-main)

Challenge:	Existing methods to measure difficulty of questions are not accurate enough to guide learning.
Approach:	They propose to use a Chinese DT-QDC dataset to measure difficulty of questions and provide a new model that can improve the judgment of difficulty from different perspectives.
Outcome:	The proposed methods outperform baselines by 7.79% on F1-score and 15.92% on MAE, 28.26% on MSE, and 28.2% on MSC on the new DT-QDC dataset.

Copied to clipboard

Yi Bin, Mengqun Han, Wenhao Shi, Lei Wang, Yang Yang, See-Kiong Ng, Heng Shen

Numerical Reasoning

Challenge:	Existing MWP solvers do not handle variants that can be derived via mathematical manipulation.
Approach:	They propose a non-autoregressive solver to present a solution expression and decode it from a given problem description.
Outcome:	The proposed solver is able to decode multiple expression variants and correct them . it is based on a unified tree structure and is available on Math23K and MAWPS.

IPS: In-Prompt Process Supervision for Short Video Content Moderation (2026.acl-industry)

Copied to clipboard

Mingchao Liu, Yu Sun, Ruixiao Sun, Xin Dong, Xiang Shen, Hongwei Wang, Hongyu Xiong, Yang Song

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

Challenge:	Multimodal large language models (MLLMs) capture semantics of short video content but fail to account for policy-specific details.
Approach:	They propose a framework that integrates In-prompt Process Supervision into MLLMs . they propose sequential reasoning over ancillary questions during fine-tuning .
Outcome:	IPS outperforms baseline MLLMs on public and proprietary benchmarks . replacing human-annotated ancillary labels with MLML-generated ones results in performance degradation.

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

Hierarchical Relation-Guided Type-Sentence Alignment for Long-Tail Relation Extraction with Distant Supervision (2022.findings-naacl)

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.

Copied to clipboard

Yang Li, Guodong Long, Tao Shen, Jing Jiang

The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training (2026.findings-acl)

Challenge:	Distant supervision uses triple facts to label corpus for relation extraction, leading to wrong labeling and long-tail problems.
Approach:	They propose a model to enrich distantly-supervised sentences with entity types by injecting context-free and -related backgrounds into sentences to alleviate sentence-level wrong labeling.
Outcome:	The proposed model achieves state-of-the-art on benchmarks and in overall and long-tail performance.

Copied to clipboard

Rui Zhang, Hongwei Li, Yun Shen, Xinyue Shen, Wenbo Jiang, Guowen Xu, Yang Liu, Michael Backes, Yang Zhang

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

Challenge:	Misaligned large language models can magnify harm by exploiting them to undermine safety . et al., 2022b; Bai e.t., 2023): misalignment, realignment and model-specific resistance are important .
Approach:	They evaluate four methods to identify a mechanism asymmetry between attack and defense . they find that ORPO is most effective for misalignment, but DPO excels in realignment .
Outcome:	The proposed methods show a mechanism asymmetry between attack and defense . the proposed methods excel in realignment, but at the expense of model utility .

Copied to clipboard

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

Improving Long-Tail Relation Extraction with Collaborating Relation-Augmented Attention (2020.coling-main)

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

Yang Li, Tao Shen, Guodong Long, Jing Jiang, Tianyi Zhou, Chengqi Zhang

STAIR: Learning Sparse Text and Image Representation in Grounded Tokens (2023.emnlp-main)

Challenge:	Existing approaches to handle wrong labeling and long-tail relations are labor-intensive and scarce training data.
Approach:	They propose a neural network to handle wrong labeling and long-tail relations by collaborating relation-augmented attention.
Outcome:	The proposed neural network improves the state-of-the-art on the NYT dataset .

Copied to clipboard

Chen Chen, Bowen Zhang, Liangliang Cao, Jiguang Shen, Tom Gunter, Albin Jose, Alexander Toshev, Yantao Zheng, Jonathon Shlens, Ruoming Pang, Yinfei Yang

Representation Learning

Challenge:	State-of-the-art contrastive learning models like CLIP and ALIGN are less interpretable and suffer from inferior accuracy than dense representations.
Approach:	They extend CLIP and ALIGN models to build a sparse semantic representation that is interpretable and easy to integrate with existing retrieval systems.
Outcome:	The proposed model outperforms CLIP and ALIGN models on image and text retrieval tasks with a 4.9% and +4.3% improvement on COCO-5k textimage and imagetext retrieval respectively.

BFS-Prover: Scalable Best-First Tree Search for LLM-based Automatic Theorem Proving (2025.acl-long)

Copied to clipboard

Ran Xin, Chenguang Xi, Jie Yang, Feng Chen, Hang Wu, Xia Xiao, Yifan Sun, Shen Zheng, Ming Ding

Information Retrieval

Challenge:	Existing approaches to theorem proving in large language models rely on value functions and/or Monte Carlo Tree Search (MCTS), but the potential of simpler methods like Best-First Tree Search remains underexplored.
Approach:	They propose a scalable expert iteration framework that implements strategic data filtering at each expert iteration round, excluding problems solvable via beam search node expansion to focus on harder cases.
Outcome:	The proposed framework achieves a state-of-the-art score of 72.95 on the MiniF2F test set and challenges the perceived necessity of complex tree search methods.

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.

MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding (2026.acl-long)

Copied to clipboard

Fuwen Luo, Shengfeng Lou, Chi Chen, Ziyue Wang, Chenliang Li, Weizhou Shen, Jiyue Guo, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Yang Liu

Visual Data in NLP

Challenge:	Existing methods for MLLMs struggle with fine-grained temporal reasoning . despite advances in video understanding, current methods struggle with time-sensitive tasks .
Approach:	They propose a time-stamp-aware multi-segment grounding method that enhances temporal understanding by introducing timestamps.
Outcome:	The proposed method outperforms existing methods on time-sensitive tasks and generalizes well across diverse temporal understanding scenarios.

CFBench: A Comprehensive Constraints-Following Benchmark for LLMs (2025.acl-long)

Copied to clipboard

Tao Zhang, ChengLIn Zhu, Yanjun Shen, Wenjing Luo, Yan Zhang, Hao Liang, Tao Zhang, Fan Yang, Mingan Lin, Yujing Qiao, Weipeng Chen, Bin Cui, Wentao Zhang, Zenan Zhou

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

Challenge:	Existing evaluations of Large Language Models (LLMs) focus on fragmented constraints or narrow scenarios, but they overlook the comprehensiveness and authenticity of constraints from the user’s perspective.
Approach:	They propose a Chinese Comprehensive Constraints Following Benchmark for LLMs that compiles constraints from real-world instructions and constructs a systematic framework for constraint types.
Outcome:	The proposed framework integrates multi-dimensional assessment criteria with requirement prioritization, covering various perspectives of constraints, instructions, and requirement fulfillment.

Copied to clipboard

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

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

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.

Copied to clipboard

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

GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs (2026.findings-acl)

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

Meixiu Long, Duolin Sun, Dan Yang, Yihan Jiao, Lei Liu, Jiahai Wang, Binbin Hu, Yue Shen, Jie Feng, Zhehao Tan, Junjie Wang, Lianzhen Zhong, Jian Wang, Peng Wei, Jinjie Gu

When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors (2026.acl-long)

Challenge:	Existing rankers excel in lexical-matching scenarios, while they struggle with complex queries requiring deep reasoning.
Approach:	They propose a new paradigm that balances flexibility and context awareness to unlock the full potential of groupwise reranking.
Outcome:	The proposed approach achieves a state-of-the-art 65.2 NDCG@10 on BRIGHT and surpasses baselines by 2.1 points on R2MED while delivering a 6.4 inference speedup.

Copied to clipboard

Yuqing Yang, Qi Zhu, Zhen Han, Boran Han, Zhengyuan Shen, Shuai Wang, Vassilis N. Ioannidis, Huzefa Rangwala

Unsupervised Rewriter for Multi-Sentence Compression (P19-1)

Challenge:	Large language models (LLMs) perform well on table tasks, but they still make data referencing errors (DREs) prior studies have only offered limited, small-scale analyses.
Approach:	They propose inference-time strategies and lightweight critics to mitigate data referencing errors.
Outcome:	The proposed model achieves an average F1 score of 78.2% in detecting both in-distribution and out-of-difference DREs and assists inference for larger models.

Copied to clipboard

Yang Zhao, Xiaoyu Shen, Wei Bi, Akiko Aizawa

Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data (2024.findings-acl)

Challenge:	Multi-sentence compression aims to generate a grammatical but reduced compression from multiple input sentences while retaining key information.
Approach:	They propose a neural rewriter for multi-sentence compression that does not need any parallel corpus.
Outcome:	Empirical studies show that the proposed approach achieves comparable results upon automatic evaluation and improves the grammaticality of compression based on human evaluation.

Copied to clipboard

Yanda Li, Chi Zhang, Gang Yu, Wanqi Yang, Zhibin Wang, Bin Fu, Guosheng Lin, Chunhua Shen, Ling Chen, Yunchao Wei

Open Schrödinger’s Closed Box: Identifying Retrieval Augmented Generation in API-Accessible Large Language Model Services (2026.acl-long)

Challenge:	OpenAI's GPT-4 has demonstrated remarkable multimodal capabilities, but specific mechanics of GPT4 remain unknown.
Approach:	They propose a data collection methodology that synchronously synthesizes images and dialogues for visual instruction tuning.
Outcome:	The proposed method improves on ten commonly assessed models and provides greater flexibility compared to existing methods.

Copied to clipboard

Yukun Jiang, Xinyue Shen, Michael Backes, Zheng Li, Yang Zhang

Directed Acyclic Graph Network for Conversational Emotion Recognition (2021.acl-long)

Challenge:	Large language models (LLMs) are powerful at question-answering but prone to hallucinations due to limited domain-specific or up-to-date knowledge.
Approach:	They propose a framework for IDentifying RAG properties in LLM services that integrates LLMs with retrieval systems and adds an external retriever and knowledge database to mitigate hallucinations.
Outcome:	The proposed framework detects RAG-enhanced LLMs with 99.97% accuracy with partial or no optional knowledge and nearly 100% when the LLM and database are known.

Copied to clipboard

Weizhou Shen, Siyue Wu, Yunyi Yang, Xiaojun Quan

ChainEdit: Propagating Ripple Effects in LLM Knowledge Editing through Logical Rule-Guided Chains (2025.acl-long)

Challenge:	Empirical evidence shows that a good representation of conversation context significantly contributes to the model performance.
Approach:	They propose to encode query utterances with a directed acyclic graph to better model the intrinsic structure within a conversation.
Outcome:	The proposed model outperforms existing models on four ERC benchmarks with state-of-the-art models employed as baselines.

Copied to clipboard

Zilu Dong, Xiangqing Shen, Zinong Yang, Rui Xia

FASTMATCH: Accelerating the Inference of BERT-based Text Matching (2020.coling-main)

Challenge:	Existing knowledge editing methods for large language models struggle to maintain logical consistency when propagating ripple effects to associated facts.
Approach:	They propose a framework that synergizes knowledge graph-derived logical rules with LLM logical reasoning capabilities to enable systematic chain updates.
Outcome:	The proposed framework improves logical generalization and specificity while maintaining reliability and specificness.

Copied to clipboard

Shuai Pang, Jianqiang Ma, Zeyu Yan, Yang Zhang, Jianping Shen

Detecting AI-Generated Content on Social Media with Multi-modal Language Models (2026.acl-industry)

Challenge:	Recent pre-trained language models have shown state-of-the-art accuracies in text matching.
Approach:	They propose a BERT-based text matching model where representations and interactions are decoupled . they propose generating final matching scores using a lightweight attention network .
Outcome:	Experiments show that the proposed model can achieve up to 100X speed-up to BERT and RoBERTa while keeping more up to 98.7% of the performance.

Copied to clipboard

Chenyang Yang, Shen Yan, Yibo Yang, Litao Hu, Yuchen Liu, Yuan Zeng, Hanchao Yu, Yinan Zhu, Sumedha Singla, Brian Vanover, Huijun Qian, Zihao Wang, Fujun Liu, Aashu Singh, Jianyu Wang, Xuewen Zhang

CURE: Critique-Driven Unified Reinforcement Learning for Test-Time Self-Improvement (2026.acl-long)

Challenge:	Existing methods for AI-generated content detection face poor generalization to newer models, reliance on single modalities, and lack of interpretable explanations.
Approach:	They propose a model that curates diverse social media data and trains a vision-language model for detection and explanation.
Outcome:	The proposed model achieves state-of-the-art detection performance on public benchmarks and observes positive downstream impacts on user engagement.

Copied to clipboard

Guirong Chen, Shuqi Ye, Wenkai Yang, Shiqi Shen, Guangyao Shen, Yankai Lin

Challenge:	Existing critique-guided methods fail to equip models with the autonomous improvement capabilities required for test-time scaling.
Approach:	They propose a framework that jointly optimizes a single policy for standard solving, critiquing, and guided re-exploration.
Outcome:	The proposed framework maintains competitive single-turn performance and unlocks effective inference-time scaling.

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

Copied to clipboard

Haohao Luo, Ying Shen, Yang Deng

GTM: A Generative Triple-wise Model for Conversational Question Generation (2021.acl-long)

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

Lei Shen, Fandong Meng, Jinchao Zhang, Yang Feng, Jie Zhou

Natural Language Interfaces

Challenge:	Experimental results show that opendomain conversational question generation improves the quality of questions in terms of fluency, coherence and diversity over competitive baselines.
Approach:	They propose a triple-wise model with hierarchical variations for open-domain conversational question generation using a post-question-answer triple and one-to-many semantic mappings.
Outcome:	The proposed model significantly improves the quality of questions in terms of fluency, coherence and diversity over baselines.

SeaLLMs - Large Language Models for Southeast Asia (2024.acl-demos)

Copied to clipboard

Xuan-Phi Nguyen, Wenxuan Zhang, Xin Li, Mahani Aljunied, Zhiqiang Hu, Chenhui Shen, Yew Ken Chia, Xingxuan Li, Jianyu Wang, Qingyu Tan, Liying Cheng, Guanzheng Chen, Yue Deng, Sen Yang, Chaoqun Liu, Hang Zhang, Lidong Bing

EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction (2025.naacl-long)

Challenge:	Existing large language models favor high-resource languages, such as English, at the expense of low-resourced and regional languages.
Approach:	They propose a series of language models that specifically focuses on Southeast Asian languages.
Outcome:	SeaLLM models outperform ChatGPT-3.5 in non-Latin languages by large margins . linguistic disparity impedes access to state-of-the-art AI technologies for non-English-speaking populations .

Copied to clipboard

Siyu Yuan, Kaitao Song, Jiangjie Chen, Xu Tan, Yongliang Shen, Kan Ren, Dongsheng Li, Deqing Yang

Gold-Medal-Level Olympiad Geometry Solving with Efficient Heuristic Auxiliary Constructions (2026.acl-long)

Challenge:	EASYTOOL combines tools from diverse tool documentation into a single tool instruction.
Approach:	They propose a framework that transforms tool documentation into a unified tool instruction.
Outcome:	EASYTOOL combines extensive tool documentation into a concise tool instruction . it reduces token consumption and improves performance of LLM-based agents .

Copied to clipboard

Boyan Duan, Xiao Liang, Shuai Lu, Yaoxiang Wang, Yelong Shen, Kai-Wei Chang, Ying Nian Wu, Mao Yang, Weizhu Chen, Yeyun Gong

Green & Sustainable NLP

Challenge:	Existing methods for geometry theorem proving in Euclidean geometry are challenging and require a neural network to perform.
Approach:	They propose a method for adding auxiliary points in geometry that runs on CPUs without relying on neural network-based inference.
Outcome:	The proposed method achieves silver-medal-level human performance on IMO-30 benchmark.

Speeding Up Neural Machine Translation Decoding by Cube Pruning (D18-1)

Copied to clipboard

Wen Zhang, Liang Huang, Yang Feng, Lei Shen, Qun Liu

Machine Translation

Challenge:	Neural machine translation suffers from slow translation speed due to the large search space . a trade-off has to be made between translation quality and speed, argues a new study .
Approach:	They apply cube pruning technique to speed up dynamic programming into neural machine translation to speed it up.
Outcome:	The proposed method can translate faster on GPUs and CPUs with better translation quality than naive beam search.

LoRASC: Expressive and Generalizable Low-rank Adaptation for Large Models via Slow Cascaded Learning (2024.findings-emnlp)

Copied to clipboard

Siwei Li, Yifan Yang, Yifei Shen, Fangyun Wei, Zongqing Lu, Lili Qiu, Yuqing Yang

Aligning Large Multimodal Models with Factually Augmented RLHF (2024.findings-acl)

Challenge:	Existing low-rank adaptations have limited expressiveness, a tendency to overfit, and sensitivity to hyperparameter settings.
Approach:	They propose a technique to enhance LoRA’s expressiveness and generalization capabilities while preserving its training efficiency.
Outcome:	The proposed method outperforms baselines, mitigates overfitting, enhances model stability, and improves OOD robustness.

Copied to clipboard

Zhiqing Sun, Sheng Shen, Shengcao Cao, Haotian Liu, Chunyuan Li, Yikang Shen, Chuang Gan, Liangyan Gui, Yu-Xiong Wang, Yiming Yang, Kurt Keutzer, Trevor Darrell

SportQA: A Benchmark for Sports Understanding in Large Language Models (2024.naacl-long)

Challenge:	Large Multimodal Models (LMMs) are built across modalities and the misalignment between two modality can result in "hallucination" . developing LMMs faces challenges such as a lack of data and a limited number of data sets.
Approach:	They propose a new algorithm that augments the reward model with additional factual information such as image captions and ground-truth multi-choice options.
Outcome:	The proposed approach improves on the LLaVA-Bench dataset with the 96% performance level of the text-only GPT-4 and an improvement of 60% on MMHAL-BENCH over other baselines.

Copied to clipboard

Haotian Xia, Zhengbang Yang, Yuqing Wang, Rhys Tracy, Yun Zhao, Dongdong Huang, Zezhi Chen, Yan Zhu, Yuan-fang Wang, Weining Shen

Multi-Grained Knowledge Retrieval for End-to-End Task-Oriented Dialog (2023.acl-long)

Challenge:	SportQA is a benchmark specifically designed for evaluating Large Language Models (LLMs) sports knowledge is characterized by its fast pace, variety of types, abundance of strategies, and rich player narratives .
Approach:	They propose a benchmark specifically designed for evaluating Large Language Models in the context of sports understanding.
Outcome:	The proposed benchmark aims to bridge the gap between existing and specialized benchmarks in sports understanding.

Copied to clipboard

Fanqi Wan, Weizhou Shen, Ke Yang, Xiaojun Quan, Wei Bi

CCPrefix: Counterfactual Contrastive Prefix-Tuning for Many-Class Classification (2024.eacl-long)

Challenge:	Existing systems blend knowledge retrieval with response generation and optimize them with direct supervision from reference responses.
Approach:	They propose a multi-grained knowledge retrieval system that decouples knowledge retrievals from response generation and introduces an entity selector and an attribute selector to acquire multigrained information from the knowledge base.
Outcome:	The proposed system performs better on small and large knowledge bases.

Copied to clipboard

Yang Li, Canran Xu, Guodong Long, Tao Shen, Chongyang Tao, Jing Jiang

Noise Robust Named Entity Understanding for Voice Assistants (2021.naacl-industry)

Challenge:	Existing methods to improve pre-trained language models for many-class classification suffer from verbalizer ambiguity . a significant disparity exists between the pre-training and fine-tuning stages of the model .
Approach:	They propose a method to tune pre-trained language models to a broad spectrum of tasks . they use an instance-dependent soft prefix to complement language verbalizers in many-class classification .
Outcome:	The proposed method outperforms baselines on many-class datasets.

Copied to clipboard

Deepak Muralidharan, Joel Ruben Antony Moniz, Sida Gao, Xiao Yang, Justine Kao, Stephen Pulman, Atish Kothari, Ray Shen, Yinying Pan, Vivek Kaul, Mubarak Seyed Ibrahim, Gang Xiang, Nan Dun, Yidan Zhou, Andy O, Yuan Zhang, Pooja Chitkara, Xuan Wang, Alkesh Patel, Kushal Tayal, Roger Zheng, Peter Grasch, Jason D Williams, Lin Li

Hero-Gang Neural Model For Named Entity Recognition (2022.naacl-main)

Challenge:	Named Entity Recognition and Entity Linking are challenging for voice assistants . utterances are relatively short, so there is not much context to help disambiguate .
Approach:	They propose a Named Entity Understanding system that combines NER and EL in a joint reranking module.
Outcome:	The proposed framework improves NER accuracy by up to 3.13% and EL accuracy by 3.6% in F1 score . it also leads to better accuracies in other natural language understanding tasks .

Copied to clipboard

Jinpeng Hu, Yaling Shen, Yang Liu, Xiang Wan, Tsung-Hui Chang

From Knowing to Teaching: Scaffolding Pedagogical Decisions for LLM Agent (2026.acl-long)

Challenge:	Named entity recognition (NER) is a fundamental and important task in natural language processing.
Approach:	They propose a novel Hero-Gang Neural structure to leverage both global and local information to promote NER by using a Transformer-based encoder and a Gang module.
Outcome:	The proposed model can extract local features and position information from the Hero and Gang modules, and it performs on multiple datasets.

Copied to clipboard

Yucheng Wang, Shen Yang, Jifan Yu, Haoxuan Li, Joy Jia Yin Lim, Daniel Zhang-Li, Huiqin Liu, Lei Hou, Juanzi Li, Bin Xu

Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment (2025.emnlp-main)

Challenge:	Large language models produce content lacking pedagogical depth when asked to generate lessons .
Approach:	They propose a framework that allows teachers to select content according to pedagogical intent and sequence topics so foundations precede applications.
Outcome:	The framework achieves 67.8% win rate in human evaluation and 79.6% in LLM-based evaluation against eight baselines.

Copied to clipboard

Jingcheng Deng, Zhongtao Jiang, Liang Pang, Zihao Wei, Liwei Chen, Kun Xu, Yang Song, Huawei Shen, Xueqi Cheng

A Hierarchical Encoding-Decoding Scheme for Abstractive Multi-document Summarization (2023.findings-emnlp)

Challenge:	Experimental results demonstrate that our method significantly outperforms traditional contrastive learning approaches when using the same amount of data.
Approach:	They propose a new contrastive learning method built on embedding conditional probability distributions that integrates two tasks: information compression and conditional distribution alignment.
Outcome:	The proposed method outperforms traditional contrastive learning approaches and achieves comparable performance to state-of-the-art models when using the same amount of data.

Copied to clipboard

Chenhui Shen, Liying Cheng, Xuan-Phi Nguyen, Yang You, Lidong Bing

O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning (2021.findings-acl)

Challenge:	Pre-trained language models have been used for abstractive single-document summarization (SDS) but they may not be suitable for multi-document summary (MDS)
Approach:	They propose to enforce hierarchy on both encoder and decoder to facilitate multi-document interactions for MDS.
Outcome:	Xiao et al. (2019) outperforms or is competitive with the previous best models.

Copied to clipboard

Fenglin Liu, Xuancheng Ren, Xian Wu, Bang Yang, Shen Ge, Xu Sun

Lock on Target! Precision Unlearning via Directional Control (2025.findings-emnlp)

Challenge:	Existing methods for video captioning consider a sequence of frames and biases towards focused objects.
Approach:	They propose an Object-Oriented Non-Autoregressive approach to video captioning . it performs three steps: 1) identify the focused objects and predict their locations . 2) generate related attribute words and relation words of these focused objects to form a draft caption .
Outcome:	The proposed method achieves competitive results with the state-of-the-art methods but with higher diversity and faster inference speed.

Copied to clipboard

Yuntao Wen, Ruixiang Feng, Feng Guo, Yifan Wang, Ran Le, Yang Song, Shen Gao, Shuo Shang

Challenge:	Existing methods for unlearning harmful, sensitive, or outdated knowledge suffer from two critical limitations: (1) collateral forgetting, where erasing target data inadvertently removes related but desirable knowledge, and (2) generality forgetting degrades the model’s general capabilities.
Approach:	They propose a method that identifies and leverages a targeted "unlearning direction" in the model's parameter space and selectively updates along this direction.
Outcome:	Experiments show that the proposed method achieves state-of-the-art unlearning precision while preserving both related knowledge and general capabilities.

Learning Compressed Sentence Representations for On-Device Text Processing (P19-1)

Copied to clipboard

Dinghan Shen, Pengyu Cheng, Dhanasekar Sundararaman, Xinyuan Zhang, Qian Yang, Meng Tang, Asli Celikyilmaz, Lawrence Carin

Representation Learning

Challenge:	Existing methods for learning sentence embeddings assume they are continuous and real-valued.
Approach:	They propose four different strategies to transform continuous and generic sentence embeddings into a binarized form while preserving their rich semantic information.
Outcome:	The proposed methods reduce storage requirements by over 98% and improve performance on downstream tasks.

Improving Text Generation with Student-Forcing Optimal Transport (2020.emnlp-main)

Copied to clipboard

Jianqiao Li, Chunyuan Li, Guoyin Wang, Hao Fu, Yuhchen Lin, Liqun Chen, Yizhe Zhang, Chenyang Tao, Ruiyi Zhang, Wenlin Wang, Dinghan Shen, Qian Yang, Lawrence Carin

FinEval: A Chinese Financial Domain Knowledge Evaluation Benchmark for Large Language Models (2025.naacl-long)

Challenge:	Maximum likelihood estimation (MLE) is used to train models, but during testing, the model is conditioned on previously generated tokens, resulting in exposure bias.
Approach:	They propose to use optimal transport to match the sequences generated in MLE and test modes to reduce exposure bias.
Outcome:	The proposed method is validated on machine translation, text summarization, and text generation tasks.

Copied to clipboard

Xin Guo, Haotian Xia, Zhaowei Liu, Hanyang Cao, Zhi Yang, Zhiqiang Liu, Sizhe Wang, Jinyi Niu, Chuqi Wang, Yanhui Wang, Xiaolong Liang, Xiaoming Huang, Bing Zhu, Zhongyu Wei, Yun Chen, Weining Shen, Liwen Zhang

SRAP-Agent: Simulating and Optimizing Scarce Resource Allocation Policy with LLM-based Agent (2024.findings-emnlp)

Challenge:	Large language models have demonstrated outstanding performance in various natural language processing tasks, but their security capabilities in the financial domain have not been explored.
Approach:	They propose to use a benchmark to evaluate large language models' financial domain knowledge and practical abilities.
Outcome:	The proposed benchmark evaluates large language models' financial domain knowledge and practical abilities.

Copied to clipboard

Jiarui Ji, Yang Li, Hongtao Liu, Zhicheng Du, Zhewei Wei, Qi Qi, Weiran Shen, Yankai Lin

Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations (2025.findings-emnlp)

Challenge:	Existing research on the allocation of public scarce resources has limitations due to data scarcity and data scariness.
Approach:	They propose a framework that integrates Large Language Models into economic simulations . they conduct extensive policy simulation experiments to verify the framework's effectiveness .
Outcome:	The proposed framework bridges the gap between theoretical models and real-world dynamics by integrating large language models into economic simulations.

Copied to clipboard

Shuo Li, Jiajun Sun, Guodong Zheng, Xiaoran Fan, Yujiong Shen, Yi Lu, Zhiheng Xi, Yuming Yang, Wenming Tan, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang

Seq2Path: Generating Sentiment Tuples as Paths of a Tree (2022.findings-acl)

Challenge:	Multimodal large language models have demonstrated remarkable performance in visual-language tasks, but their authenticity is often compromised by object hallucinations.
Approach:	They propose a multi-frequency perturbation method that leverages both low-frequency and high-frequency features of images to perturb visual feature representations and explicitly suppress redundant frequency-domain features during inference.
Outcome:	The proposed method significantly mitigates object hallucinations across various model architectures.

Copied to clipboard

Yue Mao, Yi Shen, Jingchao Yang, Xiaoying Zhu, Longjun Cai

Sentiment Analysis

Challenge:	Existing generative methods for extracting sentiment tuples do not have orders between the t-uples . a novel parallel generative framework for ABSA is proposed .
Approach:	They propose a parallel generative framework to generate sentiment tuples as paths of a tree . they train the model with an independent target and introduce a discriminative token .
Outcome:	The proposed method achieves state-of-the-art on AOPE, ASTE, TASD, UABSA, ACOS . it trains with the loss of ordinary Seq2Seq averaged over paths, and inferences automatically select valid paths.

CodeV: Issue Resolving with Visual Data (2025.findings-acl)

Copied to clipboard

Linhao Zhang, Daoguang Zan, Quanshun Yang, Zhirong Huang, Dong Chen, Bo Shen, Tianyu Liu, Yongshun Gong, Huang Pengjie, Xudong Lu, Guangtai Liang, Lizhen Cui, Qianxiang Wang

Whether LLMs Know If They Know: Identifying Knowledge Boundaries via Debiased Historical In-Context Learning (2025.findings-acl)

Challenge:	Large Language Models (LLMs) have expanded to more complex repository-level tasks.
Approach:	They propose a first approach to leveraging visual data to enhance the issue-resolving capabilities of Large Language Models (LLMs) they demonstrate the effectiveness of CodeV and provide valuable insights into leveraging visualization to resolve GitHub issues.
Outcome:	The proposed approach improves the issue-resolving capabilities of Large Language Models (LLMs) by using visual data.

Copied to clipboard

Bo Lv, Nayu Liu, Yang Shen, Xin Liu, Ping Luo, Yue Yu

The Fall of ROME: Understanding the Collapse of LLMs in Model Editing (2024.findings-emnlp)

Challenge:	Existing methods for active retrieval (AR) rely on training classification models or using the confidence of the model’s answer to determine knowledge boundaries.
Approach:	They propose a method to identify knowledge boundaries in active retrieval by retrieving historical queries as high-confidence in-context examples.
Outcome:	Experiments on four QA benchmarks show that DH-ICL achieves performance comparable to full retrieval on LLaMA with only half the number of retrievals, without any additional training.

Copied to clipboard

Wanli Yang, Fei Sun, Jiajun Tan, Xinyu Ma, Du Su, Dawei Yin, Huawei Shen

Unified Hallucination Detection for Multimodal Large Language Models (2024.acl-long)

Challenge:	Recent studies have found that model editing methods can cause large language models to collapse with just a single edit.
Approach:	They propose a method that uses prefixed keys and adds prefixes during testing to prevent model collapse.
Outcome:	The proposed method prevents model collapse while maintaining effectiveness, the authors show . Rank-One Model Editing (ROME) has been found to cause model collapse with just a single edit .

Copied to clipboard

Xiang Chen, Chenxi Wang, Yida Xue, Ningyu Zhang, Xiaoyan Yang, Qiang Li, Yue Shen, Lei Liang, Jinjie Gu, Huajun Chen

Relational Graph Attention Network for Aspect-based Sentiment Analysis (2020.acl-main)

Challenge:	despite significant strides in multimodal tasks, MLLMs are plagued by the critical issue of hallucination.
Approach:	They propose a meta-evaluation benchmark to facilitate evaluation of advancements in hallucination detection methods.
Outcome:	The proposed framework validates hallucinations robustly and provides strategic insights . MHaluBench is a meta-evaluation benchmark designed to facilitate evaluation .

Copied to clipboard

Kai Wang, Weizhou Shen, Yunyi Yang, Xiaojun Quan, Rui Wang

Sentiment Analysis

Challenge:	Aspect-based sentiment analysis aims to determine the sentiment polarity towards a specific aspect in online reviews.
Approach:	They propose a relational graph attention network to encode a tree structure for sentiment prediction.
Outcome:	The proposed approach improves the performance of the graph attention network (GAT) on the SemEval 2014 and Twitter datasets.

The Invisible Hand: Unveiling Provider Bias in Large Language Models for Code Generation (2025.acl-long)

Copied to clipboard

Xiaoyu Zhang, Juan Zhai, Shiqing Ma, Qingshuang Bao, Weipeng Jiang, Qian Wang, Chao Shen, Yang Liu

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering (2026.findings-eacl)

Challenge:	Large Language Models (LLMs) have emerged as the new recommendation engines, surpassing traditional methods in both capability and scope, particularly in code generation.
Approach:	They propose to use a dataset to investigate a new type of bias in Large Language Models for code generation, provider bias, to determine whether the model favors specific providers.
Outcome:	The proposed model favors services from Google and Amazon, but without explicit directives, and can modify input code to incorporate their preferred providers without user requests.

Copied to clipboard

Haiyan Zhao, Xuansheng Wu, Fan Yang, Bo Shen, Ninghao Liu, Mengnan Du

A Triple-View Framework for Fine-Grained Emotion Classification with Clustering-Guided Contrastive Learning (2025.acl-long)

Challenge:	Existing methods for steering concept vectors suffer from noisy features in diverse datasets that undermine steering robustness.
Approach:	They propose a Sparse Autoencoder-Denoised Concept Vector (SDCV) which selectively keeps the most discriminative SAE latents while reconstructing hidden representations.
Outcome:	The proposed method improves steering success rates by 4-16% across six challenging concepts while maintaining topic relevance.

Copied to clipboard

Junqing Gong, Binhan Yang, Wei Shen

When GPT Spills the Tea: Comprehensive Assessment of Knowledge File Leakage in GPTs (2025.acl-long)

Challenge:	Existing studies have focused on dealing with only one of the two difficulties of coarse-grained emotion classification.
Approach:	They propose a triple-view framework that treats FEC as an instance-label joint embedding learning problem to tackle both difficulties concurrently by considering three complementary views.
Outcome:	The proposed framework achieves significant and consistent improvements on two widely-used benchmark datasets.

Copied to clipboard

Xinyue Shen, Yun Shen, Michael Backes, Yang Zhang

Modeling Semantic Relationship in Multi-turn Conversations with Hierarchical Latent Variables (P19-1)

Challenge:	Existing studies show that adversarial prompts can induce GPTs to leak knowledge file content.
Approach:	They propose a workflow inspired by Data Security Posture Management to identify five leakage vectors for knowledge file leakage using 651,022 GPT metadata and 11,820 flows.
Outcome:	The proposed workflow analyzes 651,022 GPT metadata, 11,820 flows, and 1,466 responses to identify five leakage vectors: metadata, GPT initialization, retrieval, sandboxed execution environments, and prompts.

Copied to clipboard

Lei Shen, Yang Feng, Haolan Zhan

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

Challenge:	Existing work on multi-turn conversations has focused on the relationship between the response and context, but it is lacking a model to model the relationship.
Approach:	They propose a conversational semantic relationship RNN model to construct hierarchical dependency between utterances and their context.
Outcome:	The proposed model significantly improves the quality of responses in terms of fluency, coherence, and diversity compared to baseline methods.

Copied to clipboard

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

TOREE: Evaluating Topic Relevance of Student Essays for Chinese Primary and Middle School Education (2024.findings-acl)

Challenge:	Existing web agents lack visual perception, planning, and memory abilities, but their reasoning process is deviate from human cognition.
Approach:	They propose a multimodal web agent framework that emulates human planning process to decompose complex user instructions.
Outcome:	The proposed framework emulates human planning process to decompose complex user instructions.

Copied to clipboard

Xinlin Zhuang, Hongyi Wu, Xinshu Shen, Peimin Yu, Gaowei Yi, Xinhao Chen, Tu Hu, Yang Chen, Yupei Ren, Yadong Zhang, Youqi Song, Binxuan Liu, Man Lan

An End-to-End Generative Architecture for Paraphrase Generation (D19-1)

Challenge:	Existing research on Automatic Essay Scoring (AES) for Chinese essays has overlooked topic relevance and lacks detailed feedback.
Approach:	They propose to use TOREE to assess topic relevance in Chinese primary and middle school students’ essays to improve automatic and human evaluations.
Outcome:	The proposed method significantly improves both automatic and human evaluations across four diverse LLMs.

Copied to clipboard

Qian Yang, Zhouyuan Huo, Dinghan Shen, Yong Cheng, Wenlin Wang, Guoyin Wang, Lawrence Carin