Sukmin Cho

Self-Knowledge Distillation for Learning Ambiguity

2024 · arXiv (Cornell University)

Recent language models have shown remarkable performance on natural language understanding (NLU) tasks. However, they are often sub-optimal when faced with ambiguous samples that can be interpreted in multiple ways, over-confidently predicting a single label …

Upcycling Candidate Tokens of Large Language Models for Query Expansion

2025 · arXiv (Cornell University)

Query Expansion (QE) improves retrieval performance by enriching queries with related terms. Recently, Large Language Models (LLMs) have been used for QE, but existing methods face a trade-off: generating diverse terms boosts performance but increases …