all AI news
Softmax Probabilities (Mostly) Predict Large Language Model Correctness on Multiple-Choice Q&A
Feb. 21, 2024, 5:43 a.m. | Benjamin Plaut, Khanh Nguyen, Tu Trinh
cs.LG updates on arXiv.org arxiv.org
Abstract: Although large language models (LLMs) perform impressively on many tasks, overconfidence remains a problem. We hypothesized that on multiple-choice Q&A tasks, wrong answers would be associated with smaller maximum softmax probabilities (MSPs) compared to correct answers. We comprehensively evaluate this hypothesis on ten open-source LLMs and five datasets, and find strong evidence for our hypothesis among models which perform well on the original Q&A task. For the six LLMs with the best Q&A performance, the …
abstract arxiv cs.ai cs.cl cs.lg hypothesis language language model language models large language large language model large language models llms multiple softmax tasks type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Senior ML Engineer
@ Carousell Group | Ho Chi Minh City, Vietnam
Data and Insight Analyst
@ Cotiviti | Remote, United States