analiza aiqbench
This opinion paper shifts the focus of LLM self-explanations from mere plausibility to practical actionability, arguing that generated rationales can effectively support decision-making even if they do not perfectly mirror internal reasoning paths. The authors propose updated evaluation guidelines that move beyond standard XAI metrics to assess how well these explanations enable appropriate stakeholder actions across diverse scenarios.
From Plausible to Actionable: A Position on LLM Self-Explanations
arXiv:2607.15957v2 Announce Type: replace Abstract: Large Language Models (LLMs) can generate natural language explanations that rationalize their own decisions, a phenomenon commonly referred to as self-explanations. Such explanations have emerged as a promising direction for explainable artificial intelligence (XAI), particularly for interpreting LLM behavior. However, while self-explanations often appear plausible, whether they faithfully reflect a model's underlying reasoning process remains an open question. In this opinion paper, we argue that self-explanations can be highly plausible, questionably faithful, and yet highly actionable. From a traditional XAI perspective, we identify the limitations of standard evaluation protocols for LLM-generated self-explanations and propose practical guidelines for assessing their plausibility and faithfulness.Moreover, we argue that evaluation should extend beyond these criteria to actionability, highlighting applications of LLM rationalization capabilities that support informed decision-making and appropriate action across diverse stakeholders.
Abstract:Large Language Models (LLMs) can generate natural language explanations that rationalize their own decisions, a phenomenon commonly referred to as self-explanations. Such explanations have emerged as a promising direction for explainable artificial intelligence (XAI), particularly for interpreting LLM behavior. However, while self-explanations often appear plausible, whether they faithfully reflect a model's underlying reasoning process remains an open question. In this opinion paper, we argue that self-explanations can be highly plausible, questionably faithful, and yet highly actionable. From a traditional XAI perspective, we identify the limitations of standard evaluation protocols for LLM-generated self-explanations and propose practical guidelines for assessing their plausibility and this http URL, we argue that evaluation should extend beyond these criteria to actionability, highlighting applications of LLM rationalization capabilities that support informed decision-making and appropriate action across diverse stakeholders.
Computation and Language (cs.CL)
arXiv:2607.15957 [cs.CL]
(or arXiv:2607.15957v2 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2607.15957 Focus to learn more arXiv-issued DOI via DataCite
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.
Text integral sub licența deschisă a publicației · 224 cuvinte
Subiecte conexe
From Plausible to Actionable: A Position on LLM Self-Explanations
arXiv · 20 iul. 2026
The current bottleneck is political will, not research
AI Alignment Forum · 11 iul. 2026
[AINews] not much happened today
Latent Space · 18 sept. 2026
Biological Superintelligence
LessWrong · 30 iul. 2026