3 papers
cs.CL2025
The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction
Yihuai Hong, Dian Zhou, Meng Cao +2
Large language models (LLMs) excel on a variety of reasoning benchmarks, but previous studies suggest they sometimes struggle to generalize to unseen questions, potentially due to…
cs.CL2024
Geometric Signatures of Compositionality Across a Language Model's Lifetime
Jin Hwa Lee, Thomas Jiralerspong, Lei Yu +2
By virtue of linguistic compositionality, few syntactic rules and a finite lexicon can generate an unbounded number of sentences. That is, language, though seemingly high-dimension…
cs.CL2023
Systematic word meta-sense extension
Lei Yu
The meaning of polysemous words often varies in a highly productive yet predictable way. Generalizing the regularity between conventional senses to derive novel word meaning is cru…