Entity · paper

From Plausible to Actionable: A Position on LLM Self-Explanations

paperactiveprovisionalfrom-plausible-to-actionable-a-position-on-llm-self-explanations-2043882b·1 events·first seen 35h ago

Aliases: From Plausible to Actionable: A Position on LLM Self-Explanations

More like this (12)

Moral Safety in LLMs: Exposing Performative Compliance with Puzzled Cues Flaws in the LLM Automation Narrative Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias Metacognition in LLMs: Foundations, Progress, and Opportunities Metacognition in LLMs: Foundations, Progress, and Opportunities LLM-judged explanation score Can LLMs Reliably Self-Report Adversarial Prefills, and How?It's Not What You Say, It's How You Say It: Evaluating LLM Responses to Expressions of Belief Revising Context, Shifting Simulated Stance: Auditing LLM-Based Stance Simulation in Online Discussions Knowledge Knows, Verbalization Tells: Disentangling Latent Directions for Mathematical Solvability in LLMs Surrogate Fidelity: When Can Open LLMs Explain Closed Ones?What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates

Recent events (1)

4arXiv · cs.CL·35h ago·source ↗

Position paper argues LLM self-explanations are actionable despite questionable faithfulness

An opinion paper from arXiv argues that LLM self-explanations — natural language rationalizations of model decisions — can be plausible and actionable even when they do not faithfully reflect the model's underlying reasoning. The authors critique standard XAI evaluation protocols for self-explanations and propose guidelines covering plausibility, faithfulness, and a third criterion: actionability. The paper reframes the self-explanation debate away from faithfulness as the sole standard toward practical utility for diverse stakeholders.

Evaluation and Benchmarking AI Safety Research From Plausible to Actionable: A Position on LLM Self-Explanations