This paper investigates how large language models withhold responses under uncertainty or safety risks, and why this withholding (called abstention) is important for trustworthy models. Practitioners might care about understanding abstention to improve the reliability of language models in applications where they must make decisions that could have safety implications.
Firehose
Filtered to Papers, tagged “mechanism explanation” · clear filters
Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives