mlsanityData to 14 Oct 2026

LLMs for XAI: Future Directions for Explaining Explanations

arXiv 2405.06064 ↗First posted 9 May 2024cs.AI cs.CL cs.HCcited by 19

Not on the map. Why?

Abstract (arXiv)

In response to the demand for Explainable Artificial Intelligence (XAI), we investigate the use of Large Language Models (LLMs) to transform ML explanations into natural, human-readable narratives. Rather than directly explaining ML models using LLMs, we focus on refining explanations computed using existing XAI algorithms. We outline several research directions, including defining evaluation metrics, prompt design, comparing LLM models, exploring further training methods, and integrating external data. Initial experiments and user study suggest that LLMs offer a promising way to enhance the interpretability and usability of XAI.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Builds on 11 of its 21 references that are in the map. First posted on arXiv 9 May 2024.

Builds on

11 of 21 references.

References · 11

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  2. 2019Explainable Machine Learning in Deploymentcited by 211
  3. 2022TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversationscited by 66
  4. 2024Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Eracited by 46
  5. 2023Towards LLM-guided Causal Explainability for Black-box Text Classifierscited by 44
  6. 2023ConvXAI: Delivering Heterogeneous AI Explanations via Conversations to Support Human-AI Scientific Writingcited by 31
  7. 2021Sibyl: Understanding and Addressing the Usability Challenges of Machine Learning In High-Stakes Decision Makingcited by 19
  8. 2022From Black Boxes to Conversations: Incorporating XAI in a Conversational Agentcited by 14
  9. 2023In-Context Explainers: Harnessing LLMs for Explaining Black Box Modelscited by 9
  10. 2021On Two XAI Cultures: A Case Study of Non-technical Explanations in Deployed AI Systemcited by 5
  11. 2022Interpretation Quality Score for Measuring the Quality of interpretability methodscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 10; 2026: 6.

19 papers.

Sort:

By area:

  1. 2025LLMs for Explainable AI: A Comprehensive Surveycited by 45
  2. 2025Decision Information Meets Large Language Models: The Future of Explainable Operations Researchcited by 9
  3. 2024Don't be Fooled: The Misinformation Effect of Explanations in Human-AI Collaborationcited by 8
  4. 2025Thoughts without Thinking: Reconsidering the Explanatory Value of Chain-of-Thought Reasoning in LLMs through Agentic Pipelinescited by 7
  5. 2024Explingo: Explaining AI Predictions using Large Language Modelscited by 6
  6. 2025Retrieval Augmented Generation with Multi-Modal LLM Framework for Wireless Environmentscited by 5
  7. 2026An Agentic Approach to Generating XAI-Narrativescited by 4
  8. 2025Don't Just Translate, Agitate: Using Large Language Models as Devil's Advocates for AI Explanationscited by 2
  9. 2025A three-Level Framework for LLM-Enhanced eXplainable AI: From technical explanations to natural languagecited by 2
  10. 2025Explain First, Trust Later: LLM-Augmented Explanations for Graph-Based Crypto Anomaly Detectioncited by 2
  11. 2026From XAI to Stories: A Factorial Study of LLM-Generated Explanation Qualitycited by 2
  12. 2026Quality Without Usefulness: LLM-Generated XAI Narratives as Trust Heuristics Rather Than Decision Aidscited by 2
7 more
  1. 2026A Two-Stage LLM Framework for Accessible and Verified XAI Explanationscited by 1
  2. 2024GUIDEQ: Framework for Guided Questioning for progressive informational collection and classificationcited by 0
  3. 2025ProfileXAI: User-Adaptive Explainable AIcited by 0
  4. 2025Why is "Chicago" Predictive of Deceptive Reviews? Using LLMs to Discover Language Phenomena from Lexical Cuescited by 0
  5. 2026Textual Explanations and Their Evaluations for Reinforcement Learning Policycited by 0
  6. 2025A Mobile Application Front-End for Presenting Explainable AI Results in Diabetes Risk Estimationcited by 0
  7. 2026NEURON: A Neuro-symbolic System for Grounded Clinical Explainabilitycited by 0