Don't Just Translate, Agitate: Using Large Language Models as Devil's Advocates for AI Explanations

• URL: http://arxiv.org/abs/2504.12424v1
• Date: Wed, 16 Apr 2025 18:45:18 GMT
• Title: Don't Just Translate, Agitate: Using Large Language Models as Devil's Advocates for AI Explanations
• Authors: Ashley Suh, Kenneth Alperin, Harry Li, Steven R Gomez,
• Abstract summary: Large Language Models (LLMs) are used to translate outputs from explainability techniques, like feature-attribution weights, into a natural language explanation.<n>Recent findings suggest translating into human-like explanations does not necessarily enhance user understanding and may instead lead to overreliance on AI systems.
• Score: 1.6855625805565164
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This position paper highlights a growing trend in Explainable AI (XAI) research where Large Language Models (LLMs) are used to translate outputs from explainability techniques, like feature-attribution weights, into a natural language explanation. While this approach may improve accessibility or readability for users, recent findings suggest that translating into human-like explanations does not necessarily enhance user understanding and may instead lead to overreliance on AI systems. When LLMs summarize XAI outputs without surfacing model limitations, uncertainties, or inconsistencies, they risk reinforcing the illusion of interpretability rather than fostering meaningful transparency. We argue that - instead of merely translating XAI outputs - LLMs should serve as constructive agitators, or devil's advocates, whose role is to actively interrogate AI explanations by presenting alternative interpretations, potential biases, training data limitations, and cases where the model's reasoning may break down. In this role, LLMs can facilitate users in engaging critically with AI systems and generated explanations, with the potential to reduce overreliance caused by misinterpreted or specious explanations.

Related papers

• LLMs for Explainable AI: A Comprehensive Survey [0.7373617024876725]
  Large Language Models (LLMs) offer a promising approach to enhancing Explainable AI (XAI)<n>LLMs transform complex machine learning outputs into easy-to-understand narratives.<n>LLMs can bridge the gap between sophisticated model behavior and human interpretability.
  arXiv  Detail & Related papers  (2025-03-31T18:19:41Z)
• Explainable artificial intelligence (XAI): from inherent explainability to large language models [0.0]
  Explainable AI (XAI) techniques facilitate the explainability or interpretability of machine learning models.<n>This paper details the advancements of explainable AI methods, from inherently interpretable models to modern approaches.<n>We review explainable AI techniques that leverage vision-language model (VLM) frameworks to automate or improve the explainability of other machine learning models.
  arXiv  Detail & Related papers  (2025-01-17T06:16:57Z)
• LLMs for XAI: Future Directions for Explaining Explanations [50.87311607612179]
  We focus on refining explanations computed using existing XAI algorithms. Initial experiments and user study suggest that LLMs offer a promising way to enhance the interpretability and usability of XAI.
  arXiv  Detail & Related papers  (2024-05-09T19:17:47Z)
• Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era [77.174117675196]
  XAI is being extended towards Large Language Models (LLMs) This paper analyzes how XAI can benefit LLMs and AI systems. We introduce 10 strategies, introducing the key techniques for each and discussing their associated challenges.
  arXiv  Detail & Related papers  (2024-03-13T20:25:27Z)
• FaithLM: Towards Faithful Explanations for Large Language Models [67.29893340289779]
  Large Language Models (LLMs) have become proficient in addressing complex tasks by leveraging their internal knowledge and reasoning capabilities. The black-box nature of these models complicates the task of explaining their decision-making processes. We introduce FaithLM to explain the decision of LLMs with natural language (NL) explanations.
  arXiv  Detail & Related papers  (2024-02-07T09:09:14Z)
• Rethinking Interpretability in the Era of Large Language Models [76.1947554386879]
  Large language models (LLMs) have demonstrated remarkable capabilities across a wide array of tasks. The capability to explain in natural language allows LLMs to expand the scale and complexity of patterns that can be given to a human. These new capabilities raise new challenges, such as hallucinated explanations and immense computational costs.
  arXiv  Detail & Related papers  (2024-01-30T17:38:54Z)
• Towards Effective Disambiguation for Machine Translation with Large Language Models [65.80775710657672]
  We study the capabilities of large language models to translate "ambiguous sentences" Experiments show that our methods can match or outperform state-of-the-art systems such as DeepL and NLLB in four out of five language directions.
  arXiv  Detail & Related papers  (2023-09-20T22:22:52Z)
• LMExplainer: Grounding Knowledge and Explaining Language Models [37.578973458651944]
  Language models (LMs) like GPT-4 are important in AI applications, but their opaque decision-making process reduces user trust, especially in safety-critical areas. We introduce LMExplainer, a novel knowledge-grounded explainer that clarifies the reasoning process of LMs through intuitive, human-understandable explanations.
  arXiv  Detail & Related papers  (2023-03-29T08:59:44Z)
• Making Things Explainable vs Explaining: Requirements and Challenges under the GDPR [2.578242050187029]
  ExplanatorY AI (YAI) builds over XAI with the goal to collect and organize explainable information. We represent the problem of generating explanations for Automated Decision-Making systems (ADMs) into the identification of an appropriate path over an explanatory space.
  arXiv  Detail & Related papers  (2021-10-02T08:48:47Z)
• Explainable AI without Interpretable Model [0.0]
  It has become more important than ever that AI systems would be able to explain the reasoning behind their results to end-users. Most Explainable AI (XAI) methods are based on extracting an interpretable model that can be used for producing explanations. The notions of Contextual Importance and Utility (CIU) presented in this paper make it possible to produce human-like explanations of black-box outcomes directly.
  arXiv  Detail & Related papers  (2020-09-29T13:29:44Z)
• Explainability in Deep Reinforcement Learning [68.8204255655161]
  We review recent works in the direction to attain Explainable Reinforcement Learning (XRL) In critical situations where it is essential to justify and explain the agent's behaviour, better explainability and interpretability of RL models could help gain scientific insight on the inner workings of what is still considered a black box.
  arXiv  Detail & Related papers  (2020-08-15T10:11:42Z)

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.