A Definition of Good Explanations and the Challenges Explaining LLM Outputs
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Explaining Image Classifiers
We focus on explaining image classifiers, taking the work of Mothilal et al. [2021] (MMTS) as our point of departure. We observe that, although MMTS claim to be using the definition of explanation proposed by Halpern [20…
Causal Explanations for Image Classifiers
Existing algorithms for explaining the output of image classifiers use different definitions of explanations and a variety of techniques to extract them. However, none of the existing tools use a principled approach base…
Explainable AI: Definition and attributes of a good explanation for health AI
Proposals of artificial intelligence (AI) solutions based on increasingly complex and accurate predictive models are becoming ubiquitous across many disciplines. As the complexity of these models grows, transparency and …
Distribution-Based Feature Attribution for Explaining the Predictions of Any Classifier
The proliferation of complex, black-box AI models has intensified the need for techniques that can explain their decisions. Feature attribution methods have become a popular solution for providing post-hoc explanations, …
Explaining Knowledge Graph Embedding via Latent Rule Learning
Knowledge Graph Embeddings (KGEs) embed entities and relations into continuous vector space following certain assumption, and are a powerful tools for representation learning of knowledge graphs. However, following vecto…
Graph EmbeddingKnowledge DistillationKnowledge Graph EmbeddingKnowledge Graph Embeddings+4