REVIEW 3 cited by
Large Language Models Cannot Explain Themselves
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original 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.
Forward citations
Cited by 3 Pith papers
-
Privileged Self-Access Matters for Introspection in AI
LLMs' temperature self-reports are confounded by prompt style and show no privileged self-access, supporting a thicker definition of AI introspection.
-
Dynamic Prompt Middleware: Contextual Prompt Refinement Controls for Comprehension Tasks
Users preferred dynamically generated prompt-refinement controls over a fixed preset list when steering AI explanations, reporting more control and lower context-providing barriers, despite difficulty predicting optio...
-
Thoughts without Thinking: Reconsidering the Explanatory Value of Chain-of-Thought Reasoning in LLMs through Agentic Pipelines
In an agentic task-guidance pipeline, chain-of-thought reasoning did not improve output quality or provide genuine explainability.
Discussion (0). Continue with ORCID to comment.