A Definition of Good Explanations and the Challenges Explaining LLM Outputs
This paper proposes a definition of good explanations inspired by counterfactual explanations, incorporating the interlocutor's prior beliefs, and explores its implications for AI explainability, particularly why LLM outputs are difficult to explain well.
[2606.14838] A Definition of Good Explanations and the Challenges Explaining LLM Outputs
[Submitted on 12 Jun 2026]
Title:A Definition of Good Explanations and the Challenges Explaining LLM Outputs
View a PDF of the paper titled A Definition of Good Explanations and the Challenges Explaining LLM Outputs, by Louis Mahon and 2 other authors
View PDF HTML (experimental)
Abstract:How to define a good explanation is a long-standing philosophical debate which has found recent renewed interest in the context of AI outputs. Explainability is crucial for AI adoption in many contexts, but in order to produce good explanations of AI systems, we must first have an understanding of what good explanations are. In this paper we propose a definition inspired by the notion of counterfactual explanations, however we argue that one must also take into account the interlocutor's prior beliefs in each fact that could be offered in an explanation. We explore the ramifications of this definition for AI explainability and, in particular, why LLM outputs are difficult to produce good explanations for.
Subjects:
Artificial Intelligence (cs.AI)
Cite as: arXiv:2606.14838 [cs.AI]
(or arXiv:2606.14838v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.14838
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Louis Mahon [view email] [v1] Fri, 12 Jun 2026 17:11:27 UTC (39 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled A Definition of Good Explanations and the Challenges Explaining LLM Outputs, by Louis Mahon and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new | recent | 2026-06
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)