Moontae Lee

Efficiently Learning To Reason or Not to Reason: Root-token Policy Optimization for Adaptive Thinking ACL 2026 IRPO: Implicit Policy Regularized Preference Optimization EACL 2026 Adaptive Retrieval for Reasoning ACL 2026 Learning to Explore and Select for Coverage-Conditioned Retrieval-Augmented Generation NAACL 2025 The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models NAACL 2025 Counterfactual Voting Adjustment for Quality Assessment and Fairer Voting in Online Platforms with Helpfulness Evaluation ICML 2025 Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs ICLR 2025 Mind the Blind Spots: A Focus-Level Evaluation Framework for LLM Reviews EMNLP 2025 3D Denoisers Are Good 2D Teachers: Molecular Pretraining via Denoising and Cross-Modal Distillation AAAI 2025 One Missing Piece for Open-Source Reasoning Models: A Dataset to Mitigate Cold-Starting Short CoT LLMs in RL ACL 2025 Revisiting LLM Value Probing Strategies: Are They Robust and Expressive? EMNLP 2025 Overlapping Context with Variable-Length Stride Increases Diversity when Training Large Language Model for Code ACL 2025 Shifting from Ranking to Set Selection for Retrieval Augmented Generation ACL 2025 Code Models are Zero-shot Precondition Reasoners NAACL 2024 Learning to Unlearn: Instance-Wise Unlearning for Pre-trained Classifiers AAAI 2024 YTCommentQA: Video Question Answerability in Instructional Videos AAAI 2024 Semantic Skill Grounding for Embodied Instruction-Following in Cross-Domain Environments ACL 2024 Small Language Models Need Strong Verifiers to Self-Correct Reasoning ACL 2024 Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models EMNLP 2024 Prospector: Improving LLM Agents with Self-Asking and Trajectory Ranking EMNLP 2024 When ”A Helpful Assistant” Is Not Really Helpful: Personas in System Prompts Do Not Improve Performances of Large Language Models EMNLP 2024 Degeneration-free Policy Optimization: RL Fine-Tuning for Language Models without Degeneration ICML 2024 You don’t need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instruments NAACL 2024 Understanding the Capabilities and Limitations of Large Language Models for Cultural Commonsense NAACL 2024 LG AI Research & KAIST at EHRSQL 2024: Self-Training Large Language Models with Pseudo-Labeled Unanswerable Questions for a Reliable Text-to-SQL System on EHRs NAACL 2024 Merging Generated and Retrieved Knowledge for Open-Domain QA EMNLP 2023 From Heuristic to Analytic: Cognitively Motivated Strategies for Coherent Physical Commonsense Reasoning EMNLP 2023 On Sample-Efficient Code Generation EMNLP 2023 GRACE: Discriminator-Guided Chain-of-Thought Reasoning EMNLP 2023 Knowledge Unlearning for Mitigating Privacy Risks in Language Models ACL 2023 Grouping Matrix Based Graph Pooling with Adaptive Number of Clusters AAAI 2023 SafeDICE: Offline Safe Imitation Learning with Non-Preferred Demonstrations NIPS 2023 Exploring the Benefits of Training Expert Language Models over Instruction Tuning ICML 2023 QASA: Advanced Question Answering on Scientific Articles ICML 2023 Neural Stochastic Differential Games for Time-series Analysis ICML 2023 Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion Models NIPS 2023 When to Read Documents or QA History: On Unified and Selective Open-domain QA ACL 2023 Unsupervised Task Graph Generation from Instructional Video Transcripts ACL 2023 Few-shot Reranking for Multi-hop QA via Language Model Prompting ACL 2023 Rebalancing Batch Normalization for Exemplar-Based Class-Incremental Learning CVPR 2023 CEDe: A collection of expert-curated datasets with atom-level entity annotations for Optical Chemical Structure Recognition NIPS 2022 Transferring Pre-trained Multimodal Representations with Cross-modal Similarity Matching NIPS 2022 Few-shot Subgoal Planning with Language Models NAACL 2022 Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost NIPS 2022 Path-Aware and Structure-Preserving Generation of Synthetically Accessible Molecules ICML 2022 Pure Transformers are Powerful Graph Learners NIPS 2022 On-the-fly Rectification for Robust Large-Vocabulary Topic Inference ICML 2021 Prior-aware Composition Inference for Spectral Topic Models AISTATS 2020 Practical Correlated Topic Modeling and Analysis via the Rectified Anchor Word Algorithm EMNLP 2019 Practical Correlated Topic Modeling and Analysis via the Rectified Anchor Word Algorithm IJCNLP 2019 Beyond Exchangeability: The Chinese Voting Process NIPS 2016 Robust Spectral Inference for Joint Stochastic Matrix Factorization NIPS 2015 Low-dimensional Embeddings for Interpretable Anchor-based Topic Inference EMNLP 2014