# Large Language Models Cannot Explain Themselves

arXiv: https://arxiv.org/abs/2405.04382 · HTML: https://mlsanity.com/paper/2405.04382/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2024.

## Built on by (most cited first, 11 of 11)

- [Privileged Self-Access Matters for Introspection in AI](https://mlsanity.com/paper/2508.14802/) (2025)
- [SPEX: Scaling Feature Interaction Explanations for LLMs](https://mlsanity.com/paper/2502.13870/) (2025)
- [Thoughts without Thinking: Reconsidering the Explanatory Value of Chain-of-Thought Reasoning in LLMs through Agentic Pipelines](https://mlsanity.com/paper/2505.00875/) (2025)
- [State over Tokens: Characterizing the Role of Reasoning Tokens](https://mlsanity.com/paper/2512.12777/) (2025)
- [Measuring What LLMs Think They Do: SHAP Faithfulness and Deployability on Financial Tabular Classification](https://mlsanity.com/paper/2512.00163/) (2025)
- [Protein Counterfactuals via Diffusion-Guided Latent Optimization](https://mlsanity.com/paper/2603.10811/) (2026)
- [Interpreting LLMs as Credit Risk Classifiers: Do Their Feature Explanations Align with Classical ML?](https://mlsanity.com/paper/2510.25701/) (2025)
- [Leveraging NTPs for Efficient Hallucination Detection in VLMs](https://mlsanity.com/paper/2509.20379/) (2025)
- [Interpretability from the Ground Up: Stakeholder-Centric Design of Automated Scoring in Educational Assessments](https://mlsanity.com/paper/2511.17069/) (2025)
- [From Binary Groundedness to Support Relations: Towards a Reader-Centred Taxonomy for Comprehension of AI Output](https://mlsanity.com/paper/2604.08082/) (2026)
- [From Plausible to Actionable: A Position on LLM Self-Explanations](https://mlsanity.com/paper/2607.15957/) (2026)

## Abstract (arXiv)

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.