Showing cs.CLShow all
2 papers · 1 filter
cs.CL2025
On LLM-Based Scientific Inductive Reasoning Beyond Equations
Brian S. Lin, Jiaxin Yuan, Zihan Zhou +8
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 e…
cs.CL2022
COMPILING: A Benchmark Dataset for Chinese Complexity Controllable Definition Generation
Jiaxin Yuan, Cunliang Kong, Chenhui Xie +2
The definition generation task aims to generate a word's definition within a specific context automatically. However, owing to the lack of datasets for different complexities, the…