Kyomin Jung

Don’t Judge Code by Its Cover: Exploring Biases in LLM Judges for Code Evaluation EACL 2026 Confidence-Guided Stepwise Model Routing for Cost-Efficient Reasoning AAAI 2026 Persona Switch: Mixing Distinct Perspectives in Decoding Time EACL 2026 Evaluating Visual Narrative Coherence in Story Visualization via Diversified Storylines ACL 2026 How Training Data Shapes the Use of Parametric and In-Context Knowledge in Language Models ACL 2026 Fooling the LVLM Judges: Visual Biases in LVLM-Based Evaluation EMNLP 2025 Harmful Prompt Laundering: Jailbreaking LLMs with Abductive Styles and Symbolic Encoding EMNLP 2025 ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflection EMNLP 2025 Drift: Decoding-time Personalized Alignments with Implicit User Preferences EMNLP 2025 Generating Diverse Hypotheses for Inductive Reasoning NAACL 2025 Persona is a Double-Edged Sword: Rethinking the Impact of Role-play Prompts in Zero-shot Reasoning Tasks AACL 2025 LLMs can be easily Confused by Instructional Distractions ACL 2025 A Character-Centric Creative Story Generation via Imagination ACL 2025 AdvisorQA: Towards Helpful and Harmless Advice-seeking Question Answering with Collective Intelligence NAACL 2025 VLind-Bench: Measuring Language Priors in Large Vision-Language Models NAACL 2025 Are LLM-Judges Robust to Expressions of Uncertainty? Investigating the effect of Epistemic Markers on LLM-based Evaluation NAACL 2025 Avoidance Decoding for Diverse Multi-Branch Story Generation EMNLP 2025 Conditional [MASK] Discrete Diffusion Language Model EMNLP 2025 FaithUn: Toward Faithful Forgetting in Language Models by Investigating the Interconnectedness of Knowledge EMNLP 2025 Return of EM: Entity-driven Answer Set Expansion for QA Evaluation COLING 2025 Persona is a Double-Edged Sword: Rethinking the Impact of Role-play Prompts in Zero-shot Reasoning Tasks IJCNLP 2025 Guaranteed Generation from Large Language Models ICLR 2025 Public Data Assisted Differentially Private In-Context Learning EMNLP 2025 Can You Trick the Grader? Adversarial Persuasion of LLM Judges EMNLP 2025 Mitigating Hallucinations in Large Vision-Language Models via Summary-Guided Decoding NAACL 2025 SWITCH: Studying with Teacher for Knowledge Distillation of Large Language Models NAACL 2025 LifeTox: Unveiling Implicit Toxicity in Life Advice NAACL 2024 Kosmic: Korean Text Similarity Metric Reflecting Honorific Distinctions COLING 2024 MP2D: An Automated Topic Shift Dialogue Generation Framework Leveraging Knowledge Graphs EMNLP 2024 Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination ACL 2024 IterCQR: Iterative Conversational Query Reformulation with Retrieval Guidance NAACL 2024 Fine-grained Gender Control in Machine Translation with Large Language Models NAACL 2024 Can LLMs Recognize Toxicity? A Structured Investigation Framework and Toxicity Metric EMNLP 2024 DPP-TTS: Diversifying prosodic features of speech via determinantal point processes EMNLP 2023 BREAK: Breaking the Dialogue State Tracking Barrier with Beam Search and Re-ranking ACL 2023 Injecting Comparison Skills in Task-Oriented Dialogue Systems for Database Search Results Disambiguation ACL 2023 Critic-Guided Decoding for Controlled Text Generation ACL 2023 Task-specific Compression for Multi-task Language Models using Attribution-based Pruning EACL 2023 Weakly Supervised Semantic Parsing with Execution-based Spurious Program Filtering EMNLP 2023 Dialogizer: Context-aware Conversational-QA Dataset Generation from Textual Sources EMNLP 2023 Target-Agnostic Gender-Aware Contrastive Learning for Mitigating Bias in Multilingual Machine Translation EMNLP 2023 Asking Clarification Questions to Handle Ambiguity in Open-Domain QA EMNLP 2023 PR-MCS: Perturbation Robust Metric for MultiLingual Image Captioning EMNLP 2023 MILAB at PragTag-2023: Enhancing Cross-Domain Generalization through Data Augmentation with Reduced Uncertainty EMNLP 2023 Factual Error Correction for Abstractive Summaries Using Entity Retrieval EMNLP 2022 Improving Multiple Documents Grounded Goal-Oriented Dialog Systems via Diverse Knowledge Enhanced Pretrained Language Model ACL 2022 Masked Summarization to Generate Factually Inconsistent Summaries for Improved Factual Consistency Checking NAACL 2022 Contrastive Learning for Context-aware Neural Machine Translation Using Coreference Information EMNLP 2021 UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning IJCNLP 2021 Self-Adapter at SemEval-2021 Task 10: Entropy-based Pseudo-Labeler for Source-free Domain Adaptation IJCNLP 2021 QACE: Asking Questions to Evaluate an Image Caption EMNLP 2021 Self-Adapter at SemEval-2021 Task 10: Entropy-based Pseudo-Labeler for Source-free Domain Adaptation ACL 2021 KPQA: A Metric for Generative Question Answering Using Keyphrase Weights NAACL 2021 Learning to Select Question-Relevant Relations for Visual Question Answering NAACL 2021 Neural Sequence-to-grid Module for Learning Symbolic Rules AAAI 2021 UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning ACL 2021 Bidirectional Variational Inference for Non-Autoregressive Text-to-Speech ICLR 2021 Self-Adapter at SemEval-2021 Task 10: Entropy-based Pseudo-Labeler for Source-free Domain Adaptation SEMEVAL 2021 Improving Context-Aware Neural Machine Translation Using Self-Attentive Sentence Embedding AAAI 2020 Fast and Accurate Deep Bidirectional Language Representations for Unsupervised Learning ACL 2020 Multimodal Speech Emotion Recognition Using Cross Attention with Aligned Audio and Text INTERSPEECH 2020 ViLBERTScore: Evaluating Image Caption Using Vision-and-Language BERT EMNLP 2020 Detecting Incongruity between News Headline and Body Text via a Deep Hierarchical Encoder AAAI 2019 Effective Sentence Scoring Method Using BERT for Speech Recognition ACML 2019 Surf at MEDIQA 2019: Improving Performance of Natural Language Inference in the Clinical Domain by Adopting Pre-trained Language Model ACL 2019 MILAB at SemEval-2019 Task 3: Multi-View Turn-by-Turn Model for Context-Aware Sentiment Analysis SEMEVAL 2019 Improving Neural Question Generation Using Answer Separation AAAI 2019 Number Sequence Prediction Problems for Evaluating Computational Powers of Neural Networks AAAI 2019 Comparative Studies of Detecting Abusive Language on Twitter EMNLP 2018 Multi-scale Nystrom Method AISTATS 2018 Learning to Rank Question-Answer Pairs Using Hierarchical Recurrent Encoder with Latent Topic Clustering NAACL 2018 AttnConvnet at SemEval-2018 Task 1: Attention-based Convolutional Neural Networks for Multi-label Emotion Classification SEMEVAL 2018 Double Nyström Method: An Efficient and Accurate Nyström Scheme for Large-Scale Data Sets ICML 2015 Local Rules for Global MAP: When Do They Work ? NIPS 2009 Local Algorithms for Approximate Inference in Minor-Excluded Graphs NIPS 2007