← Search

Brian S. Lin

1 accepted papers

2025

On LLM-Based Scientific Inductive Reasoning Beyond Equations

EMNLP 2025

As large language models (LLMs) increasingly exhibit human-like capabilities, a fundamental question emerges: How can we enable LLMs to learn the underlying patterns from limited examples in entirely novel environments and apply them effectively? This question is central to the ability of LLMs in in