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

• URL: http://arxiv.org/abs/2505.20305v1
• Date: Sun, 18 May 2025 17:30:10 GMT
• Title: Making Sense of the Unsensible: Reflection, Survey, and Challenges for XAI in Large Language Models Toward Human-Centered AI
• Authors: Francisco Herrera,
• Abstract summary: Explainable AI (XAI) acts as a crucial interface between the opaque reasoning of large language models (LLMs) and diverse stakeholders.<n>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?<n>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.
• Score: 11.454716478837014
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Mind the XAI Gap: A Human-Centered LLM Framework for Democratizing Explainable AI [3.301842921686179]
  We introduce a framework that ensures transparency and human-centered explanations tailored to the needs of experts and non-experts.<n>Our framework encapsulates in one response explanations understandable by non-experts and technical information to experts.
  arXiv  Detail & Related papers  (2025-06-13T21:41:07Z)
• Explainability in Context: A Multilevel Framework Aligning AI Explanations with Stakeholder with LLMs [11.11196150521188]
  This paper addresses how trust in AI is influenced by the design and delivery of explanations.<n>The framework consists of three layers: algorithmic and domain-based, human-centered, and social explainability.
  arXiv  Detail & Related papers  (2025-06-06T08:54:41Z)
• A Multi-Layered Research Framework for Human-Centered AI: Defining the Path to Explainability and Trust [2.4578723416255754]
  Human-Centered AI (HCAI) emphasizes alignment with human values, while Explainable AI (XAI) enhances transparency by making AI decisions more understandable.<n>This paper presents a novel three-layered framework that bridges HCAI and XAI to establish a structured explainability paradigm.<n>Our findings advance Human-Centered Explainable AI (HCXAI), fostering AI systems that are transparent, adaptable, and ethically aligned.
  arXiv  Detail & Related papers  (2025-04-14T01:29:30Z)
• An Overview of Large Language Models for Statisticians [109.38601458831545]
  Large Language Models (LLMs) have emerged as transformative tools in artificial intelligence (AI)<n>This paper explores potential areas where statisticians can make important contributions to the development of LLMs.<n>We focus on issues such as uncertainty quantification, interpretability, fairness, privacy, watermarking and model adaptation.
  arXiv  Detail & Related papers  (2025-02-25T03:40:36Z)
• Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey [46.617998833238126]
  Large language models (LLMs) and computer vision (CV) systems driving advancements in natural language understanding and visual processing.<n>The convergence of these technologies has catalyzed the rise of multimodal AI, enabling richer, cross-modal understanding that spans text, vision, audio, and video modalities.<n>Multimodal large language models (MLLMs) have emerged as a powerful framework, demonstrating impressive capabilities in tasks like image-text generation, visual question answering, and cross-modal retrieval.<n>Despite these advancements, the complexity and scale of MLLMs introduce significant challenges in interpretability and explainability, essential for establishing
  arXiv  Detail & Related papers  (2024-12-03T02:54:31Z)
• The Impossibility of Fair LLMs [59.424918263776284]
  The need for fair AI is increasingly clear in the era of large language models (LLMs) We review the technical frameworks that machine learning researchers have used to evaluate fairness. We develop guidelines for the more realistic goal of achieving fairness in particular use cases.
  arXiv  Detail & Related papers  (2024-05-28T04:36:15Z)
• Towards Responsible AI in Banking: Addressing Bias for Fair Decision-Making [69.44075077934914]
  "Responsible AI" emphasizes the critical nature of addressing biases within the development of a corporate culture. This thesis is structured around three fundamental pillars: understanding bias, mitigating bias, and accounting for bias. In line with open-source principles, we have released Bias On Demand and FairView as accessible Python packages.
  arXiv  Detail & Related papers  (2024-01-13T14:07:09Z)
• Path To Gain Functional Transparency In Artificial Intelligence With Meaningful Explainability [0.0]
  As AI systems become increasingly sophisticated, ensuring their transparency and explainability becomes crucial.<n>We propose a design for user-centered compliant-by-design transparency in transparent systems.<n>By providing a comprehensive understanding of the challenges associated with transparency in AI systems, we aim to facilitate the development of AI systems that are accountable, trustworthy, and aligned with societal values.
  arXiv  Detail & Related papers  (2023-10-13T04:25:30Z)
• Revisiting the Performance-Explainability Trade-Off in Explainable Artificial Intelligence (XAI) [0.0]
  We argue that it is best approached in a nuanced way that incorporates resource availability, domain characteristics, and considerations of risk. This work aims to advance the field of Requirements Engineering for AI.
  arXiv  Detail & Related papers  (2023-07-26T15:07:40Z)
• The Role of Large Language Models in the Recognition of Territorial Sovereignty: An Analysis of the Construction of Legitimacy [67.44950222243865]
  We argue that technology tools like Google Maps and Large Language Models (LLM) are often perceived as impartial and objective. We highlight the case of three controversial territories: Crimea, West Bank and Transnitria, by comparing the responses of ChatGPT against Wikipedia information and United Nations resolutions.
  arXiv  Detail & Related papers  (2023-03-17T08:46:49Z)
• Bridging the Transparency Gap: What Can Explainable AI Learn From the AI Act? [0.8287206589886881]
  European Union has introduced detailed requirements of transparency for AI systems. There is a fundamental difference between XAI and the Act regarding what transparency is. By comparing the disparate views of XAI and regulation, we arrive at four axes where practical work could bridge the transparency gap.
  arXiv  Detail & Related papers  (2023-02-21T16:06:48Z)
• Causal Fairness Analysis [68.12191782657437]
  We introduce a framework for understanding, modeling, and possibly solving issues of fairness in decision-making settings. The main insight of our approach will be to link the quantification of the disparities present on the observed data with the underlying, and often unobserved, collection of causal mechanisms. Our effort culminates in the Fairness Map, which is the first systematic attempt to organize and explain the relationship between different criteria found in the literature.
  arXiv  Detail & Related papers  (2022-07-23T01:06:34Z)
• Counterfactual Explanations as Interventions in Latent Space [62.997667081978825]
  Counterfactual explanations aim to provide to end users a set of features that need to be changed in order to achieve a desired outcome. Current approaches rarely take into account the feasibility of actions needed to achieve the proposed explanations. We present Counterfactual Explanations as Interventions in Latent Space (CEILS), a methodology to generate counterfactual explanations.
  arXiv  Detail & Related papers  (2021-06-14T20:48:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.