publications
Research publications in Natural Language Processing, Machine Learning, and AI. Browse our latest papers, conference proceedings, and academic research contributions from our NLP research group.
2025
- EMNLPCheckEval: A reliable LLM-as-a-Judge framework for evaluating text generation using checklistsIn Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025
- EMNLPCOUNTDOWN: Contextually Sparse Activation Filtering Out Unnecessary Weights in Down ProjectionIn Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025
- EMNLP FindingsPre-Storage Reasoning for Episodic Memory: Shifting Inference Burden to Memory for Personalized DialogueIn Findings of the Association for Computational Linguistics: EMNLP 2025, 2025
- ACLVerbosity-Aware Rationale Reduction: Sentence-Level Rationale Reduction for Efficient and Effective ReasoningIn Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics, 2025
- ACLWhat Really Matters in Many-Shot Attacks? An Empirical Study of Long-Context Vulnerabilities in LLMsIn Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics, 2025
- ACL FindingsAn Empirical Study of Group Conformity in Multi-Agent SystemsIn Findings of the Association for Computational Linguistics: ACL 2025, 2025
- ACL FindingsEXPERT: An Explainable Image Captioning Evaluation Metric with Structured ExplanationsIn Findings of the Association for Computational Linguistics: ACL 2025, 2025
- ICLRDo You Keep an Eye on What I Ask? Mitigating Multimodal Hallucination via Attention-Guided Ensemble DecodingIn International Conference on Learning Representations, 2025
- NAACLLLM-guided Plan and Retrieval: A Strategic Alignment for Interpretable User Satisfaction Estimation in DialogueIn Proceedings of the 2025 Conference of the North American Chapter of the Association for Computational Linguistics, 2025
- NAACL FindingsHEISIR: Hierarchical Expansion of Inverted Semantic Indexing for Training-free Retrieval of Conversational Data using LLMsIn Findings of the 2025 Conference of the North American Chapter of the Association for Computational Linguistics, 2025
- CIKMUpcycling Candidate Tokens of Large Language Models for Query ExpansionIn Proceedings of the 34th ACM International Conference on Information and Knowledge Management, 2025
- IP&MHuman-Guided Collective LLM Intelligence for Strategic Planning via Two-Stage Information RetrievalInformation Processing & Management, 2025
- arXivCL3DOR: Contrastive Learning for 3D Large Multimodal Models via Odds Ratio on High-Resolution Point CloudsarXiv preprint arXiv:2025, 2025
- NeurIPSLLM Unlearning for Removing Hazardous KnowledgeAdvances in Neural Information Processing Systems, 2025Under Review
- NeurIPSA Novel Optimization Algorithm for Machine UnlearningAdvances in Neural Information Processing Systems, 2025Under Review
- EMNLPAre Vision-Language Models Safe in the Wild? A Meme-Based Benchmark StudyIn Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025
- EMNLP FindingsHow Diversely Can Language Models Solve Problems? Exploring the Algorithmic Diversity of Model-Generated CodeIn Findings of the Association for Computational Linguistics: EMNLP 2025, 2025
- Technical ReportEXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes2025
- ACL FindingsVerbosity-Aware Rationale Reduction: Effective Reduction of Redundant Rationale via Principled CriteriaIn Findings of the Association for Computational Linguistics: ACL 2025, 2025
2024
- ACL FindingsDEBATE: Devil’s Advocate-Based Assessment and Text EvaluationIn Findings of the Association for Computational Linguistics: ACL 2024, 2024
- KnowledgeLMSafe-Embed: Unveiling the Safety-Critical Knowledge of Sentence EncodersIn KnowledgeLM Workshop at ACL 2024, 2024
- NeurIPSA Gradient Accumulation Method for Dense Retriever under Memory ConstraintIn Advances in Neural Information Processing Systems, 2024
- CHI WorkshopCheckEval: Robust Evaluation Framework using Large Language Model via ChecklistIn CHI 2024 Workshop on Human-centered Evaluation and Auditing of Language Models, 2024
- EMNLP WorkshopEPR: An Expert Behavior-enhanced Paper Ranking Framework for the Automotive IndustryIn EMNLP 2024 Workshop, 2024
- EMNLP FindingsEliciting Instruction-tuned Code Language Models’ Capabilities to Utilize Auxiliary Function for Code GenerationIn Findings of the Association for Computational Linguistics: EMNLP 2024, 2024
- NAACLRectifying Demonstration Shortcut in In-Context LearningIn Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics, 2024
- LREC-COLINGHierarchical Graph Convolutional Network Approach for Detecting Low-Quality DocumentsIn Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, 2024
2023
- EMNLP FindingsBoosting Prompt-Based Self-Training With Mapping-Free Automatic Verbalizer for Multi-Class ClassificationIn Findings of the Association for Computational Linguistics: EMNLP 2023, 2023
- EMNLP FindingsDRAFT: Dense Retrieval Augmented Few-shot Topic classifier frameworkIn Findings of the Association for Computational Linguistics: EMNLP 2023, 2023
- ACL WorkshopPainsight: An Extendable Opinion Mining Framework for Detecting Pain Points Based on Online Customer ReviewsIn ACL 2023 13th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis, 2023
- NeurIPSMEMTO: Memory-guided Transformer for Multivariate Time Series Anomaly detectionIn Advances in Neural Information Processing Systems, 2023
- ACL FindingsFixed Input Parameterization for Efficient PromptingIn Findings of the Association for Computational Linguistics: ACL 2023, 2023
- JITSEco-friendly platooning operation algorithm of the autonomous vehiclesJournal of Intelligent Transportation Systems: Technology, Planning, and Operations, 2023
- EACL FindingsHeadline Token-based Discriminative Learning for Subheading Generation in News ArticleIn Findings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, 2023
2022
- InterNLPUCDF: User-defined Content Detection FrameworkIn InterNLP Workshop at NeurIPS 2022, 2022
- CVPR WorkshopREVECA - Rich Encoder-decoder framework for Video Event CAptionerIn CVPR 2022 Workshop on LOng-form VidEo Understanding Challenge, 2022
- ESWADetecting incongruent news headlines with auxiliary textual informationExpert Systems with Applications, 2022