2 papers
cs.LG2025
Inference-Time Chain-of-Thought Pruning with Latent Informativeness Signals
Sophie Li, Nicholas Huang, Nayan Saxena +4
Large language models (LLMs) improve reasoning accuracy when generating multiple candidate solutions at test time, but standard methods like Best-of-N (BoN) incur high computationa…
cs.CL2024
Revisiting Absence withSymptoms that *T* Show up Decades Later to Recover Empty Categories
Emily Chen, Nicholas Huang, Casey Robinson +3
This paper explores null elements in English, Chinese, and Korean Penn treebanks. Null elements contain important syntactic and semantic information, yet they have typically been t…