PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
May 7, 202410 citationsOpen Access

Large Language Models Cannot Explain Themselves

View Full Paper
ASAdvait Sarkar

Key Points

Key points are not available for this paper at this time.

Abstract

Large language models can be prompted to produce text. They can also be prompted to produce "explanations" of their output. But these are not really explanations, because they do not accurately reflect the mechanical process underlying the prediction. The illusion that they reflect the reasoning process can result in significant harms. These "explanations" can be valuable, but for promoting critical thinking rather than for understanding the model. I propose a recontextualisation of these "explanations", using the term "exoplanations" to draw attention to their exogenous nature. I discuss some implications for design and technology, such as the inclusion of appropriate guardrails and responses when models are prompted to generate explanations.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Advait Sarkar (2024) studied this question.

synapsesocial.com/papers/68e6b299b6db643587634283https://doi.org/10.48550/arxiv.2405.04382
Ask AI
Helpful
Bookmark
Share
View Full Paper