7 papers
Correctness-Dependent Asymmetric Target Distributions for Self-Distillation Policy Optimization
Suwan Yoon, Seongryong Jung, Changhee Lee
Self-distillation policy optimization provides dense token-level supervision for LLM post-training through feedback-conditioned self-teachers. However, directly matching the self-t…
Position: AI Lock-In Is in Progress, and We Must Be Prepared
Jaeho Kim, Seokhyun Lee, Jieun Lee +1
AI safety research has mainly focused on two areas: technical alignment (ensuring AI systems produce human-aligned outputs) and the regulation of generative AI's societal impacts (…
Representing Time Series as Structured Programs for LLM Reasoning
Jaeho Kim, Changhun Oh, Seokhyun Lee +2
Large language models (LLMs) have demonstrated strong reasoning and instruction-following capabilities, making them potentially powerful tools for time-series analysis. However, ti…
Explaining Black-Box Language Models: Learning to Optimize Linguistically-Structured Word Subsets
Minyoung Hwang, Seokhyun Lee, Changhee Lee
As deep language models (DLMs) are increasingly deployed in high-stakes domains such as healthcare, understanding their decision rationale becomes paramount for ensuring trust, saf…
Agentic Molecular Recovery via Molecule-Aware Exploration
Suwan Yoon, Changhee Lee
Text-guided molecular generation with LLMs often yields invalid SMILES. We argue that invalid drafts should be addressed through a shift from validity-oriented repair to identity-p…
Localizing Input Uncertainty Quantification for Large Language Models via Shapley Values
Seongjun Lee, Suwan Yoon, Changhee Lee
As large language models (LLMs) are increasingly integrated into high-stakes decision-making, the ability to reliably quantify uncertainty has become a critical requirement for saf…
INSHAPE: Instance-Level Shapelets for Interpretable Time-Series Classification
Seongjun Lee, Seokhyun Lee, Changhee Lee
Discovering shapelets -- i.e., discriminative temporal patterns within time series -- has been widely studied to address the inherent complexity of time-series classification (TSC)…