Pith. sign in

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

arxiv 2405.04382 v1 pith:UDUTRFJJ submitted 2024-05-07 cs.HC

classification cs.HC
keywords explanationsmodelspromptedtheylanguagelargeprocessproduce
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 9 citations worldwide. Full citation record

  1. Privileged Self-Access Matters for Introspection in AI

    cs.AI 2025-08 conditional novelty 6.0 of 10

    LLMs' temperature self-reports are confounded by prompt style and show no privileged self-access, supporting a thicker definition of AI introspection.

  2. Dynamic Prompt Middleware: Contextual Prompt Refinement Controls for Comprehension Tasks

    cs.HC 2024-12 conditional novelty 6.0 of 10

    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...

  3. Thoughts without Thinking: Reconsidering the Explanatory Value of Chain-of-Thought Reasoning in LLMs through Agentic Pipelines

    cs.AI 2025-05 conditional novelty 4.0 of 10

    In an agentic task-guidance pipeline, chain-of-thought reasoning did not improve output quality or provide genuine explainability.

Pith tools