Making Sense of the Unsensible: Reflection, Survey, and Challenges for XAI in Large Language Models Toward Human-Centered AI

TL;DR

This paper surveys the challenges and strategies for making large language models more transparent and accountable, emphasizing human-centered explainability in high-stakes domains.

Contribution

It provides a comprehensive framework for understanding XAI in LLMs, highlighting core dimensions, evaluation methods, and future research directions for responsible deployment.

Findings

Identifies faithfulness, truthfulness, plausibility, and contrastivity as key explainability dimensions.

Discusses evaluation methods and emerging developments like audience-sensitive XAI.

Highlights challenges in aligning LLM explanations with societal and ethical standards.

Abstract

As large language models (LLMs) are increasingly deployed in sensitive domains such as healthcare, law, and education, the demand for transparent, interpretable, and accountable AI systems becomes more urgent. Explainable AI (XAI) acts as a crucial interface between the opaque reasoning of LLMs and the diverse stakeholders who rely on their outputs in high-risk decisions. This paper presents a comprehensive reflection and survey of XAI for LLMs, framed around three guiding questions: Why is explainability essential? What technical and ethical dimensions does it entail? And how can it fulfill its role in real-world deployment? We highlight four core dimensions central to explainability in LLMs, faithfulness, truthfulness, plausibility, and contrastivity, which together expose key design tensions and guide the development of explanation strategies that are both technically sound and contextually appropriate. The paper discusses how XAI can support epistemic clarity, regulatory compliance, and audience-specific intelligibility across stakeholder roles and decision settings. We further examine how explainability is evaluated, alongside emerging developments in audience-sensitive XAI, mechanistic interpretability, causal reasoning, and adaptive explanation systems. Emphasizing the shift from surface-level transparency to governance-ready design, we identify critical challenges and future research directions for ensuring the responsible use of LLMs in complex societal contexts. We argue that explainability must evolve into a civic infrastructure fostering trust, enabling contestability, and aligning AI systems with institutional accountability and human-centered decision-making.