Article

Mind the Gap: From Plausible to Valid Self-Explanations in Large Language Models

2025-04-02

Abstract excerpt

<title>Abstract</title> <p>This paper investigates the reliability of explanations generated by large language models (LLMs) when prompted to explain their previous output. We evaluate two kinds of such self-explanations (SE) – extractive and counterfactual – using state-of-the-art LLMs (1B to 70B parameters) on two different classification tasks (objective and subjective). In line with Agarwal et al. (2024), our...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: c8d373c8-962e-57cd-8fb9-f360960cfe65
DOI: 10.21203/rs.3.rs-6263278/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Mind the Gap: From Plausible to Valid Self-Explanations in Large Language ModelsDOI 10.21203/rs.3.rs-6263278/v1Read

Exploring Explainability in Large Language ModelsSemantic proximity Read

What have we learned about human reasoning from large reasoning models? Response to de Varda et al.Semantic proximity Read

Studying and improving reasoning in humans and machinesSemantic proximity Read

Post Hoc Explanations of Language Models Can Improve Language ModelsSemantic proximity Read

Hallucination or confabulation? A psychological reinterpretation of erroneous outputs in large language modelsSemantic proximity Read

Limits of Self-Correction in LLMs: An Information-Theoretic Analysis of Correlated ErrorsSemantic proximity Read

Nonlinear Transformation of Probabilities by Large Language ModelsSemantic proximity Read

Cognitive dissonance in large language models is neither cognitive nor dissonantSemantic proximity Read

Inductive reasoning in minds and machinesSemantic proximity Read

Anchoring Bias in Large Language Models: An Experimental StudySemantic proximity Read

Large language models as linguistic simulators and cognitive models in human researchSemantic proximity Read

The effect of medical explanations from large language models on diagnostic accuracy in radiologySemantic proximity Read