← Search

Sungjun Han

3 accepted papers

2026

Predicting LLM Reasoning Performance with Small Proxy Model

ICLR 2026poster

Given the prohibitive cost of pre-training large language models, it is essential to leverage smaller proxy models to optimize recipes before scaling up. However, this approach becomes challenging for reasoning capabilities, which exhibit \textit{emergent} behavior that only appears reliably at larg…

Cited by 0SourcecodeScholar
2024

Towards Understanding the Relationship between In-context Learning and Compositional Generalization

COLING 2024main

According to the principle of compositional generalization, the meaning of a complex expression can be understood as a function of the meaning of its parts and of how they are combined. This principle is crucial for human language processing and also, arguably, for NLP models in the face of out-of-d…

Cited by 0SourcePDFScholar