Papers by Lin Gui
NarrativePlay: Interactive Narrative Understanding (2024.eacl-demo)
Copied to clipboard
| Challenge: | Existing systems for interactive agents focus on specific capabilities in predetermined scenarios. |
| Approach: | They propose a novel system that allows users to role-play a fictional character and interact with other characters in narratives in an immersive environment. |
| Outcome: | The proposed system generates human-like responses guided by personality traits extracted from narratives. |
PECAN: LLM-Guided Dynamic Progress Control with Attention-Guided Hierarchical Weighted Graph for Long-Document QA (2025.findings-acl)
Copied to clipboard
| Challenge: | Long-document Question Answering (QA) challenges with large-scale text and long-distance dependencies. |
| Approach: | They propose a method that leverages large language models to control retrieval process . they propose 'attention-based' retrieval methods that construct hierarchical graphs . |
| Outcome: | The proposed method achieves LLM-level performance while maintaining computational complexity comparable to RAG methods. |
Two Heads Are Better Than One: Dual-Model Verbal Reflection at Inference-Time (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing LLMs struggle to reliably detect subtle reasoning errors in ASAS tasks. |
| Approach: | They propose a dual-model framework with a dedicated Critic model trained for effective reflection that generates precise verbal feedback. |
| Outcome: | The proposed framework outperforms existing ASAS benchmarks and provides valuable insights into the performance of the proposed framework. |
Distilling ChatGPT for Explainable Automated Student Answer Assessment (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing automated student answer assessment models lack explainable and faithful feedback. |
| Approach: | They propose a framework that leverages ChatGPT for student answer scoring and rationale generation. |
| Outcome: | The proposed method improves the overall QWK score by 11% compared to ChatGPT. |
JointCL: A Joint Contrastive Learning Framework for Zero-Shot Stance Detection (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods achieve promising performance in in-target stance detection when trained and tested on the same datasets. |
| Approach: | They propose a joint contrastive learning framework to generalize stance features for unseen targets. |
| Outcome: | The proposed framework achieves state-of-the-art on three benchmark datasets. |
IEPile: Unearthing Large Scale Schema-Conditioned Information Extraction Corpus (2024.acl-short)
Copied to clipboard
| Challenge: | Large Language Models exhibit a significant performance gap in Information Extraction (IE) high-quality instruction data is the vital key for enhancing LLMs' specific capabilities . |
| Approach: | They propose a bilingual (English and Chinese) IE instruction corpus that contains 0.32B tokens. |
| Outcome: | The proposed model improves the performance of LLMs for IE with zero-shot generalization. |
Multi-modal Stance Detection: New Datasets and Model (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for stance detection for pure texts have limited results to multi-modal content. |
| Approach: | They propose a multi-modal stance detection framework that leverages target information to learn multi-modal stance features from textual and visual modalities. |
| Outcome: | The proposed framework achieves state-of-the-art in multi-modal stance detection on five datasets based on Twitter . |
Beta Distribution Guided Aspect-aware Graph for Aspect Category Sentiment Analysis with Affective Knowledge (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for aspect category sentiment analysis do not necessarily occur in a sentence. |
| Approach: | They propose a Beta Distribution-guided aspect-aware graph construction based on external knowledge . they use aspect-related words as the pivots to derive aspect-relevant weights . |
| Outcome: | The proposed approach outperforms the state-of-the-art methods on 6 benchmark datasets. |
Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection (2021.acl-long)
Copied to clipboard
| Challenge: | Emotion detection in dialogues requires the identification of thematic topics underlying a conversation, commonsense knowledge, and the intricate transition patterns between affective states. |
| Approach: | They propose a Topic-Driven Knowledge-Aware Transformer model that integrates topic representation and commonsense knowledge from ATOMIC for dialogue emotion detection. |
| Outcome: | The proposed model outperforms state-of-the-art models on four dialogue datasets . it can detect topics which help distinguish emotion categories, the authors show . |
Linguistic Neuron Overlap Patterns to Facilitate Cross-lingual Transfer on Low-resource Languages (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have focused on data-efficient methods, particularly Cross-lingual In-Context Learning (X-ICL) |
| Approach: | They propose a method to improve cross-lingual in-context learning for low-resource languages by using language-specific neurons. |
| Outcome: | The proposed method improves cross-lingual performance on low-resource languages by ensuring full activation of language overlap neurons. |
The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and Analysis (2024.emnlp-main)
Copied to clipboard
| Challenge: | In-context learning (ICL) is a capability that enables large language models to excel in proficiency through demonstration examples. |
| Approach: | They present a survey on the interpretation and analysis of in-context learning . they focus on theoretical and empirical perspectives on the concept . |
| Outcome: | The proposed model can perform tasks with minimal examples without re-training and has demonstrated proficiency across various tasks with a minimal set of task-oriented examples. |
Sparse Activation Editing for Reliable Instruction Following in Narratives (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing benchmarks fail to capture the challenges of instruction following in complex narrative contexts. |
| Approach: | They propose a training-free framework that identifies and edits instruction-relevant neurons using only natural language instructions without requiring labelled data. |
| Outcome: | The proposed framework improves instruction following by identifying and editing instruction-relevant neurons using only natural language instructions, without requiring labelled data. |
Adversarial Learning of Poisson Factorisation Model for Gauging Brand Sentiment in User Reviews (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing models for sentiment-topic extraction assume topics are grouped under discrete sentiment categories such as ‘positive’, ‘negative’ and ‘neural’. |
| Approach: | They propose a Brand-Topic Model which aims to detect brand-associated polarity-bearing topics from product reviews. |
| Outcome: | The proposed model outperforms existing models on Amazon reviews and shows that it is more coherent and unique than existing models. |
Transition-based Directed Graph Construction for Emotion-Cause Pair Extraction (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods to extract emotions and causes from unannotated text are pipelined, causing error propagation. |
| Approach: | They propose to transform a task into a procedure of parsing-like directed graph construction . they propose to generate a directed graph with labeled edges based on a sequence of actions . |
| Outcome: | The proposed method outperforms the state-of-the-art methods by 6.71% (p0.01) in F1 measure. |
Large Language Models Fall Short: Understanding Complex Relationships in Detective Narratives (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing datasets for narrative understanding fail to represent complexity and uncertainty of relationships in real-life social scenarios. |
| Approach: | They propose a benchmark for extracting and analysing intricate character relation graphs from detective narratives using large-scale large-language models. |
| Outcome: | The proposed dataset extracts and analyses character relation graphs from detective narratives using advanced Large Language Models like GPT-3.5, GPT-4, and Llama2 . |
OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding (2026.acl-long)
Copied to clipboard
Deming Ding, Shichun Liu, Enhui Yang, Jiahang Lin, Ziying Chen, Shihan Dou, Honglin Guo, Weiyu Cheng, Pengyu Zhao, Chengjun Xiao, Qunhong Zeng, Qi Zhang, Xuanjing Huang, Qidi Xu, Tao Gui
| Challenge: | coding scaffolds that follow heterogeneous instructions remain under-examined in software engineering . coding models are capable software agents, but their ability to follow constraints remains under-explored . |
| Approach: | They introduce OctoBench, which benchmarks scaffold-aware instruction following in agentic coding. |
| Outcome: | The proposed benchmark aims to accelerate the development of more scaffold-aware agents. |
Jointly Learning Aspect-Focused and Inter-Aspect Relations with Graph Convolutional Networks for Aspect Sentiment Analysis (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for aspect sentiment analysis do not include explicit sentiment expressions. |
| Approach: | They propose to construct a heterogeneous graph by leveraging aspect-focused and inter-aspect contextual dependencies for the specific aspect. |
| Outcome: | The proposed model outperforms state-of-the-art methods on four benchmark datasets and significantly boosts performance in comparison with BERT. |
Multi-Programming Language Sandbox for LLMs (2025.acl-demo)
Copied to clipboard
Shihan Dou, Jiazheng Zhang, Jianxiang Zang, Yunbo Tao, Weikang Zhou, Haoxiang Jia, Shichun Liu, Yuming Yang, Shenxi Wu, Zhiheng Xi, Muling Wu, Rui Zheng, Changze Lv, Limao Xiong, Shaoqing Zhang, Lin Zhang, Wenyu Zhan, Rongxiang Weng, Jingang Wang, Xunliang Cai, Yueming Wu, Ming Wen, Yixin Cao, Tao Gui, Xipeng Qiu, Qi Zhang, Xuanjing Huang
| Challenge: | MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for Large Language Models (LLMs). |
| Approach: | They propose a multi-programming language sandbox that provides unified feedback from compilers and analysis tools for Large Language Models. |
| Outcome: | The proposed multi-language sandbox can provide comprehensive feedback from compilers and analysis tools for large language models (LLMs). |
Coarse-to-fine Few-shot Learning for Named Entity Recognition (2023.findings-acl)
Copied to clipboard
Ruotian Ma, Zhang Lin, Xuanting Chen, Xin Zhou, Junzhe Wang, Tao Gui, Qi Zhang, Xiang Gao, Yun Wen Chen
| Challenge: | Existing few-shot NER solutions do not consider sub-class discrimination and various granularity of new classes during coarse training. |
| Approach: | They propose a method that uses a cluster-based prototype loss to learn group-wise discriminative representations of coarse-grained classes and a mixture prototype loss for learning the representations. |
| Outcome: | The proposed method shows superior performance over baseline methods on in-domain and cross-domain settings with various target granularity. |
Tracking Brand-Associated Polarity-Bearing Topics in User Reviews (2023.tacl-1)
Copied to clipboard
| Challenge: | Existing models that infer brand polarity scores from reviews are not able to infer polarities directly. |
| Approach: | They propose a dynamic Brand-Topic Model which detects and tracks brand-associated sentiment scores and polarity-bearing topics from product reviews organized in temporally ordered time intervals. |
| Outcome: | The proposed model outperforms competitive models on a MakeupAlley and hotel review datasets. |
RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing role-playing datasets mostly contribute to controlling role style and knowledge boundaries, but overlook role-following in instruction-follower scenarios. |
| Approach: | They propose a fine-grained role-playing and instruction-following composite benchmark, named RoleMRC, which includes multi-turn dialogues between ideal roles and humans, including free chats or discussions upon given passages . |
| Outcome: | The proposed model improves instruction-following without compromising general role-playing and reasoning capabilities. |
Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models (2026.acl-long)
Copied to clipboard
Binghai Wang, Yantao Liu, Yuxuan Liu, Tianyi Tang, Shenzhi Wang, Chang Gao, Chujie Zheng, Yichang Zhang, Le Yu, Shixuan Liu, Tao Gui, Qi Zhang, Xuanjing Huang, Bowen Yu, Fei Huang, Junyang Lin
| Challenge: | Recent studies observe a phenomenon where reward models achieve high accuracy on static datasets but fail to generalize effectively during RLHF. |
| Approach: | They propose a method that combines rationale consistency with outcome accuracy to improve performance on RM-Bench and JudgeBench. |
| Outcome: | The proposed method surpasses baselines on RM-Bench and JudgeBench by an average of 5% and improves creative writing tasks by 7%. |
AutoPKG: An Automated Framework for Dynamic E-commerce Product-Attribute Knowledge Graph Construction (2026.findings-acl)
Copied to clipboard
Pollawat Hongwimol, Haoning Shang, Chutong Wang, Zhichao Wan, Yi Gao, Yuanming Li, Lin Gui, Wenhao Sun, Cheng Yu
| Challenge: | Product attribute extraction in e-commerce is bottlenecked by ontologies that are inconsistent, incomplete, and costly to maintain. |
| Approach: | They propose a multi-agent Large Language Model framework that constructs a Product-attribute Knowledge Graph from multimodal product content. |
| Outcome: | The proposed framework achieves 0.953 WKE for product types, 0.724 WKEs for attribute keys, and 0.531 edge-level accuracy for value assertions after canonicalization on a large real-world marketplace catalog dataset from Lazada (Alibaba). |
Position Bias Mitigation: A Knowledge-Aware Graph Model for Emotion Cause Extraction (2021.acl-long)
Copied to clipboard
| Challenge: | Existing models for ECE tend to explore relative position information and suffer from the dataset bias. |
| Approach: | They propose to generate adversarial examples where relative position is no longer indicative feature of cause clauses to address the dataset bias. |
| Outcome: | The proposed method performs on par with existing state-of-the-art methods on the original ECE dataset and is more robust against adversarial attacks compared to existing models. |
COPR: Continual Human Preference Learning via Optimal Policy Regularization (2025.findings-acl)
Copied to clipboard
Han Zhang, Lin Gui, Yu Lei, Yuanzhao Zhai, Yehong Zhang, Zhuo Zhang, Yulan He, Hui Wang, Yue Yu, Kam-Fai Wong, Bin Liang, Ruifeng Xu
| Challenge: | Reinforcement Learning from Human Feedback (RLHF) is effective for aligning Large Language Models with human preferences, but its complex process limits its ability to continually learn human feedback. |
| Approach: | They propose a non-RL offline method to convert historical optimal policies into optimization constraints when continually learning new preferences. |
| Outcome: | The proposed method outperforms strong CL baselines in terms of reward-based evaluations and human assessment. |
Beyond Prompting: An Efficient Embedding Framework for Open-Domain Question Answering (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have recently pushed open-domain question answering (ODQA) to new heights. |
| Approach: | They propose an embedding-level framework that enhances both the retriever and the reader by reordering query representations via lightweight linear layers under an unsupervised contrastive learning objective. |
| Outcome: | The proposed framework outperforms baselines in accuracy and efficiency across three open-source LLMs, three retrieval methods, and four ODQA benchmarks. |
A Scalable Framework for Table of Contents Extraction from Complex ESG Annual Reports (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for document classification focus on local layout, sidelining holistic comprehension of content and organisation. |
| Approach: | They propose a framework for Table of Contents extraction that uses hierarchical structure to extract text from ESG annual reports. |
| Outcome: | The proposed framework outperforms the state-of-the-art with a fraction of running time. |
Document-Level Multi-Event Extraction with Event Proxy Nodes and Hausdorff Distance Minimization (2023.acl-long)
Copied to clipboard
| Challenge: | Document-level multi-event extraction aims to extract the structural information from a given document automatically. |
| Approach: | They propose an alternative approach for document-level multi-event extraction with event proxy nodes and Hausdorff distance minimization. |
| Outcome: | The proposed method outperforms state-of-the-art methods on two datasets with only a fraction of training time. |
Encourage or Inhibit Monosemanticity? Revisit Monosemanticity from a Feature Decorrelation Perspective (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies focus on monosemanticity on its basic units. |
| Approach: | They propose to revisit monosemanticity from the feature decorrelation perspective and advocate for its encouragement. |
| Outcome: | The proposed method improves representation diversity and activation sparsity and improves preference alignment performance. |
Addressing Overthinking in Large Vision-Language Models via Gated Perception-Reasoning Optimization (2026.findings-acl)
Copied to clipboard
Xingjian Diao, Zheyuan Liu, Chunhui Zhang, Weiyi Wu, Keyi Kong, Lin Shi, Kaize Ding, Soroush Vosoughi, Jiang Gui
| Challenge: | Prior work has attempted to mitigate this issue by using adaptive reasoning strategies, but these methods overlook a fundamental bottleneck: visual perception failures. |
| Approach: | They propose a meta-reasoning controller that dynamically routes computation among three decision paths at each generation step. |
| Outcome: | The proposed method outperforms slow-thinking methods while producing shorter responses. |
GraphMind: Interactive Novelty Assessment System for Accelerating Scientific Discovery (2025.emnlp-demos)
Copied to clipboard
| Challenge: | Existing approaches to literature analysis lack transparency and information retrieval module. |
| Approach: | GraphMind is an easy-to-use interactive web tool designed to assist users in evaluating novelty of scientific papers or drafted ideas. |
| Outcome: | GraphMind enables users to capture the main structure of a scientific paper, explore related ideas through various perspectives, and assess novelty via providing verifiable contextual insights. |
Weak Reward Model Transforms Generative Models into Robust Causal Event Extraction Systems (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing evaluation metrics that reflect the performance of causal event extraction tasks are poorly reflecting the inherent ambiguity of cause and effect boundaries. |
| Approach: | They propose to use a weak-to-strong supervision method to train an evaluation model while still achieving high performance in training an RL model. |
| Outcome: | The proposed method achieves high agreement with human-annotated data while still achieving high performance in training an RL model. |
Event-Centric Question Answering via Contrastive Learning and Invertible Event Transformation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing QA frameworks that use event-centric reasoning are lacking. |
| Approach: | They propose a novel QA model with contrastive learning and invertible event transformation . they use an invertable transformation matrix to project event vectors into a common event embedding space . |
| Outcome: | The proposed model achieves 8.4% gain in token-level F1 score and 3.0% gain in Exact Match score on the ESTER dataset. |
Learning “O” Helps for Learning More: Handling the Unlabeled Entity Problem for Class-incremental NER (2023.acl-long)
Copied to clipboard
Ruotian Ma, Xuanting Chen, Zhang Lin, Xin Zhou, Junzhe Wang, Tao Gui, Qi Zhang, Xiang Gao, Yun Wen Chen
| Challenge: | Existing Named Entity Recognition systems are typically trained on a large-scale dataset with predefined entity classes, then deployed for entity recognition on the test data without further adaptation or refinement. |
| Approach: | They propose a representation learning method that adaptively detects entity clusters in "O" and two effective distance-based relabeling strategies for better learning the old classes. |
| Outcome: | The proposed method achieves 10.62% improvement over the baseline methods. |
MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning (2026.findings-acl)
Copied to clipboard
Jiahang Lin, Kai Hu, Binghai Wang, Yuhao Zhou, Zhiheng Xi, Honglin Guo, Shichun Liu, Junzhe Wang, Shihan Dou, Enyu Zhou, Hang Yan, Zhenhua Han, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing work on long document visual question answering is based on Retrieval-Augmented Generation (RAG) where textual or visual content is encoded into embeddings and relevance is determined by similarity scores with respect to the original query. |
| Approach: | They propose a framework that employs an agentic, vision-aware workflow to address long document visual question answering through iterative information discovery and synthesis. |
| Outcome: | The proposed framework outperforms existing RL systems by 10.4% on the MMLongbench-Doc benchmark and demonstrates superior training performance over GRPO. |
Neural Topic Model with Reinforcement Learning (D19-1)
Copied to clipboard
| Challenge: | Experimental results show superior performance on perplexity and topic coherence measures compared to state-of-the-art topic models. |
| Approach: | They propose to incorporate topic coherence measures as reward signals to guide the learning of a VAE-based topic model. |
| Outcome: | The proposed model is able to separating background words dynamically from topic words eliminating the pre-processing step of filtering infrequent and/or top frequent words, typically required for learning traditional topic models. |
Addressing Order Sensitivity of In-Context Demonstration Examples in Causal Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | In-context learning is a popular paradigm in natural language processing, but its performance can be significantly influenced by the order of in-concept demonstration examples. |
| Approach: | They propose an unsupervised fine-tuning method to reduce the sensitivity of causal language models to the order of in-context demonstration examples. |
| Outcome: | The proposed method reduces the sensitivity of CausalLMs to the order of in-context examples and exhibits robust generalizability. |
Mirror: Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoning (2024.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) struggle with knowledge-rich problems without external resources. |
| Approach: | They propose a Multiple-perspective self-reflection method that allows LLMs to reflect from multiple-perceptive clues, achieved through a heuristic interaction between a Navigator and a Reasoner. |
| Outcome: | The proposed method is superior to other self-reflection methods on five reasoning datasets. |
A Knowledge Regularized Hierarchical Approach for Emotion Cause Analysis (D19-1)
Copied to clipboard
| Challenge: | Emotion cause analysis aims to identify the reasons behind emotions . previous models focus on learning architecture with local textual information . |
| Approach: | They propose a method to extract emotion cause with hierarchical neural model and knowledge-based regularizations by sentiment lexicon and common knowledge. |
| Outcome: | The proposed method outperforms baselines on two public datasets in different languages and outperformed competitive baselines by 2.08%. |
Lost in the Context: Insufficient and Distracted Attention to Contexts in Preference Modeling (2025.acl-long)
Copied to clipboard
Shihan Dou, Jiayi Chen, Chenhao Huang, Feng Chen, Wei Chengzhi, Huiyuan Zheng, Shichun Liu, Yan Liu, Chenxiao Liu, Chao Xin, Lin Yan, Zongzhang Zhang, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing reward models concatenate contexts and responses, but they often ignore crucial segments of the context that are important for evaluating the response quality. |
| Approach: | They propose a reward model that evaluates the response quality based on a given context and assigns a rewards reward. |
| Outcome: | The proposed framework significantly improves preference modeling by increasing attention to relevant information within the context and achieves better generalizability. |
Flexibly Utilize Memory for Long-Term Conversation via a Fragment-then-Compose Framework (2025.emnlp-main)
Copied to clipboard
Cai Ke, Yiming Du, Bin Liang, Yifan Xiang, Lin Gui, Zhongyang Li, Baojun Wang, Yue Yu, Hui Wang, Kam-Fai Wong, Ruifeng Xu
| Challenge: | Large language models extract useful information from conversation history to enhance the response in long-term conversations. |
| Approach: | They propose a Fragment-then-Compose framework to optimize memory utilization for long-term open-domain conversation. |
| Outcome: | The proposed framework can be used to extract useful information from conversation history . it can be adapted to different situations and improve response generation . |
Benchmarking Automated Clinical Language Simplification: Dataset, Algorithm, and Evaluation (2022.coling-1)
Copied to clipboard
| Challenge: | Existing studies to translate medical jargon into layperson-understandable language focus on accuracy and readability aspects of clinical language. |
| Approach: | They propose to construct a dataset to support automated clinical language simplification and propose a model that mimics the human annotation procedure. |
| Outcome: | The proposed model matches human annotation procedures and achieves state-of-the-art performance compared with baselines. |
Boosting Low-Resource Biomedical QA via Entity-Aware Masking Strategies (2021.eacl-main)
Copied to clipboard
| Challenge: | Biomedical question-answering (QA) provides users with high-quality information from a vast scientific literature. |
| Approach: | They propose to use a biomedical entity-aware masking strategy to fine-tune masked language models to their domains. |
| Outcome: | The proposed approach is an adaptation process for masked LMs, not memory or components. |
SymbolicThought: Integrating Language Models and Symbolic Reasoning for Consistent and Interpretable Human Relationship Understanding (2026.acl-demo)
Copied to clipboard
| Challenge: | Existing methods for constructing character relationships from plain text are time-consuming and low in coverage. |
| Approach: | They propose a human-in-the-loop framework that combines LLM-based extraction with symbolic reasoning. |
| Outcome: | The proposed framework improves annotation accuracy and consistency while significantly reducing time cost. |
OSCR-Attack: One-Shot Character Level Attacks through Self-Optimizing Continuous Relaxation (2026.findings-acl)
Copied to clipboard
Lingyi Kong, Zhuo Liu, Zhanghao Hu, Qilong Qiu, Yutao Yang, Jingjing Xue, Zheng Wang, Lin Gui, Feiping Nie
| Challenge: | Character-level adversarial attacks preserve semantics but are costly and inefficient . generative LLMs are gaining popularity due to their uncertainty and vulnerability to textual adversarials . |
| Approach: | They propose an end-to-end framework that transforms discrete choices into continuous representations and a conflict resolution strategy that maps them back into discrete insertion operations. |
| Outcome: | The proposed framework improves ASR by 21.45% points and accelerates the attack by 3.66 times compared to baselines. |
Towards Unified Task Embeddings Across Multiple Models: Bridging the Gap for Prompt-Based Large Language Models and Beyond (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing task embedding methods rely on fine-tuned, task-specific language models, which hinders their adaptability to prompt-guided Large Language Models (LLMs). |
| Approach: | They propose a framework for unified task embedding that harmonizes task embeds from various models within a single vector space. |
| Outcome: | The proposed framework harmonizes task embeddings from various models within a single vector space. |
Distinguishability Calibration to In-Context Learning (2023.findings-eacl)
Copied to clipboard
| Challenge: | Recent studies have shown that pre-trained language models generate similar output embeddings which makes it difficult to discriminate for the prompt-based classifier. |
| Approach: | They propose a calibration method which rotates the embedding feature into a new metric space and adapts the ratio of each dimension to a uniform distribution. |
| Outcome: | The proposed method improves the distinguishability of learning embeddings on three datasets under various settings. |
A Disentangled Adversarial Neural Topic Model for Separating Opinions from Plots in User Reviews (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing topic models may extract topics associated with writers’ subjective opinions mixed with those related to factual descriptions. |
| Approach: | They propose a neural topic model combined with adversarial training to disentangle opinion topics from plot and neutral ones. |
| Outcome: | The proposed model shows improved coherence and variety of topics, consistent disentanglement rate, and superior sentiment classification performance to other supervised topic models. |
ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use (2025.acl-long)
Copied to clipboard
Junjie Ye, Zhengyin Du, Xuesong Yao, Weijian Lin, Yufei Xu, Zehui Chen, Zaiyuan Wang, Sining Zhu, Zhiheng Xi, Siyu Yuan, Tao Gui, Qi Zhang, Xuanjing Huang, Jiecao Chen
| Challenge: | Effective evaluation of multi-hop tool use is critical for analyzing the understanding, reasoning, and function-calling capabilities of large language models. |
| Approach: | They propose a dataset that provides rigorous evaluation of multi-hop tool use. |
| Outcome: | The proposed model achieves 49.04% accuracy across five model families. |
Are NLP Models Good at Tracing Thoughts: An Overview of Narrative Understanding (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) excel in generating coherent texts, but their ability to comprehend the author’s thoughts remains uncertain. |
| Approach: | They conduct a comprehensive survey of narrative understanding tasks, examining their key features, definitions, taxonomy, associated datasets, evaluation metrics, and limitations. |
| Outcome: | The proposed framework could be extended to address novel narrative understanding tasks. |
PANACEA: An Automated Misinformation Detection System on COVID-19 (2023.eacl-demo)
Copied to clipboard
Runcong Zhao, Miguel Arana-catania, Lixing Zhu, Elena Kochkina, Lin Gui, Arkaitz Zubiaga, Rob Procter, Maria Liakata, Yulan He
| Challenge: | Using social media and fact-checking to detect misinformation is not enough to prevent the spread of false information. |
| Approach: | They propose a web-based misinformation detection system PANACEA which has two modules, fact-checking and rumour detection. |
| Outcome: | The system outperforms state-of-the-art methods and adapts graph convolutional networks model to detect rumours based on tweets rather than knowledge bases. |
CHIME: Cross-passage Hierarchical Memory Network for Generative Review Question Answering (2020.coling-main)
Copied to clipboard
| Challenge: | Existing QA systems deal with factoid questions and assume a simplified setup such as multiple-choice questions, retrieving spans of text from given documents, and filling in the blanks. |
| Approach: | They propose a cross-passage hierarchical memory network for question answering via text generation that extends XLNet by adding an auxiliary memory module to the context memory and answer memory. |
| Outcome: | The proposed architecture outperforms the state-of-the-art generative QA framework with better syntactically well-formed answers and increased precision on the AmazonQA review dataset. |
Multi-Modal Sarcasm Detection via Cross-Modal Graph Convolutional Network (2022.acl-long)
Copied to clipboard
| Challenge: | Existing studies on multimodal sarcasm detection using textual and visual information have been limited to text-only approaches. |
| Approach: | They propose to construct a cross-modal graph for each multi-modal instance to explicitly draw the ironic relations between textual and visual modalities. |
| Outcome: | The proposed model achieves state-of-the-art in multi-modal sarcasm detection. |
Navigating the OverKill in Large Language Models (2024.acl-long)
Copied to clipboard
Chenyu Shi, Xiao Wang, Qiming Ge, Songyang Gao, Xianjun Yang, Tao Gui, Qi Zhang, Xuanjing Huang, Xun Zhao, Dahua Lin
| Challenge: | Recent studies have highlighted a tendency among large language models to refuse to answer benign queries. |
| Approach: | They propose a model-agnostic approach to reduce excessive attention to harmful words like ‘kill’ and a method to decode the next-token predictions by contrastive decoding. |
| Outcome: | The proposed approach reduces the refusal rate by 20% while having little impact on safety. |
Mitigating Biases of Large Language Models in Stance Detection with Counterfactual Augmented Calibration (2025.naacl-long)
Copied to clipboard
Ang Li, Jingqian Zhao, Bin Liang, Lin Gui, Hui Wang, Xi Zeng, Xingwei Liang, Kam-Fai Wong, Ruifeng Xu
| Challenge: | Large language models generate biased stances due to spurious correlations and preference towards certain individuals and topics. |
| Approach: | They propose a counterfactual Augmented Calibration Network to calibrate potential bias in stance detection of large language models. |
| Outcome: | The proposed calibration network can mitigate biases of large language models, achieving state-of-the-art results. |