A decodability criterion predicts when hidden-state selection beats majority voting in large language models
Source
Zhixiang wang, Ziliang Hong, Ulas Bagci
Author
Zhixiang wang, Ziliang Hong, Ulas Bagci
Date
Terms in this piece · Glossary
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
Why it matters
Gives a measurable criterion for choosing between self-consistency voting and hidden-state answer selection on a given task, and warns that probe accuracy reported without leakage controls is inflated.
articleWhen LLM judges agree, should we believe them?www.amazon.science
articleMemorization Diagnostics for Code LLMs Should be Scale-AwarePrateek Kumar Rajput, Abdoul Aziz Bonkoungou, Alberick Euraste Djir\'e, Xunzhu Tang, Yewei Song, Iyiola Emmanuel Olatunji, El Hacen Diallo, Jacques Klein, Tegawend\'e F. Bissyand\'e
articleMeasure, Don't Optimize: Forecasting Recovery in LLM UnlearningZirui Song, Huaxing Liu, Xiang Wang, Shuai Li, Xinye Li, Lang Gao, Jinghui Zhang, Zheng Lu, Fengxian Ji, Xiaojun Chang, Xiuying Chen