Local Explanations and Self-Explanations for Assessing Faithfulness in black-box LLMs
This paper introduces a novel task to assess the faithfulness of large language models (LLMs) using local perturbations and self-explanations. Many LLMs often require additional context to answer certain questions correctly. For this purpose, we propose a new efficient alternative explainability technique, inspired by the commonly used leave-one-out approach. Using this approach, we identify the sufficient and necessary parts for the LLM to generate correct answers, serving as explanations. We propose a metric for assessing faithfulness that compares these crucial parts with the self-explanations of the model. Using the Natural Questions dataset, we validate our approach, demonstrating its effectiveness in explaining model decisions and assessing faithfulness.
Code (0)
등록된 구현이 없습니다.
Tasks
Natural QuestionsSimilar Papers 제목 키워드 기반
From Plausible to Actionable: A Position on LLM Self-Explanations
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 directio…
Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models
Large Language Models (LLMs) are deployed as powerful tools for several natural language processing (NLP) applications. Recent works show that modern LLMs can generate self-explanations (SEs), which elicit their intermed…
Decision MakingTowards Faithful Agentic XAI: A Verification Method and an Open-World Benchmark for Better Model Faithfulness
Explainable AI (XAI) helps users interpret model behavior and identify potential faults. Agentic XAI systems use Large Language Models (LLMs) to make explanations more accessible through natural-language interaction, but…
Reinforcement LearningAre self-explanations from Large Language Models faithful?
Instruction-tuned Large Language Models (LLMs) excel at many tasks and will even explain their reasoning, so-called self-explanations. However, convincing and wrong self-explanations can lead to unsupported confidence in…
counterfactualFaithfulness CriticNatural Language InferenceQuestion Answering+2A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior
LLM self-explanations are often presented as a promising tool for AI oversight, yet their faithfulness to the model's true reasoning process is poorly understood. Existing faithfulness metrics have critical limitations, …