Tell Me a Story! Narrative-Driven XAI with Large Language Models

• URL: http://arxiv.org/abs/2309.17057v2
• Date: Wed, 12 Jun 2024 18:18:37 GMT
• Title: Tell Me a Story! Narrative-Driven XAI with Large Language Models
• Authors: David Martens, James Hinns, Camille Dams, Mark Vergouwen, Theodoros Evgeniou,
• Abstract summary: In many AI applications today, the predominance of black-box machine learning models amplifies the need for Explainable AI (XAI) Existing XAI approaches, such as the widely used SHAP values or counterfactual (CF) explanations, are arguably too technical for users to understand and act upon. We introduce XAIstories, which leverage Large Language Models to provide narratives about how AI predictions are made.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In many AI applications today, the predominance of black-box machine learning models, due to their typically higher accuracy, amplifies the need for Explainable AI (XAI). Existing XAI approaches, such as the widely used SHAP values or counterfactual (CF) explanations, are arguably often too technical for users to understand and act upon. To enhance comprehension of explanations of AI decisions and the overall user experience, we introduce XAIstories, which leverage Large Language Models to provide narratives about how AI predictions are made: SHAPstories do so based on SHAP explanations, while CFstories do so for CF explanations. We study the impact of our approach on users' experience and understanding of AI predictions. Our results are striking: over 90% of the surveyed general audience finds the narratives generated by SHAPstories convincing. Data scientists primarily see the value of SHAPstories in communicating explanations to a general audience, with 83% of data scientists indicating they are likely to use SHAPstories for this purpose. In an image classification setting, CFstories are considered more or equally convincing as the users' own crafted stories by more than 75% of the participants. CFstories additionally bring a tenfold speed gain in creating a narrative. We also find that SHAPstories help users to more accurately summarize and understand AI decisions, in a credit scoring setting we test, correctly answering comprehension questions significantly more often than they do when only SHAP values are provided. The results thereby suggest that XAIstories may significantly help explaining and understanding AI predictions, ultimately supporting better decision-making in various applications.

Related papers

• Not All Explanations are Created Equal: Investigating the Pitfalls of Current XAI Evaluation [0.0]
  XAI aims to create transparency in modern AI models by offering explanations of the models to human users.<n>Most studies done within this field conduct simple user surveys to analyze the difference between no explanations and those generated by their proposed solution.<n>Our study looks to highlight this pitfall: most explanations, regardless of quality or correctness, will increase user satisfaction.
  arXiv  Detail & Related papers  (2025-09-27T08:30:38Z)
• Fool Me Once? Contrasting Textual and Visual Explanations in a Clinical Decision-Support Setting [43.110187812734864]
  We evaluate three types of explanations: visual explanations (saliency maps), natural language explanations, and a combination of both modalities. We find that text-based explanations lead to significant over-reliance, which is alleviated by combining them with saliency maps. We also observe that the quality of explanations, that is, how much factually correct information they entail, and how much this aligns with AI correctness, significantly impacts the usefulness of the different explanation types.
  arXiv  Detail & Related papers  (2024-10-16T06:43:02Z)
• Measuring User Understanding in Dialogue-based XAI Systems [2.4124106640519667]
  State-of-the-art in XAI is still characterized by one-shot, non-personalized and one-way explanations. In this paper, we measure understanding of users in three phases by asking them to simulate the predictions of the model they are learning about. We analyze the data to reveal patterns of how the interaction between groups with high vs. low understanding gain differ.
  arXiv  Detail & Related papers  (2024-08-13T15:17:03Z)
• Tell me more: Intent Fulfilment Framework for Enhancing User Experiences in Conversational XAI [0.6333053895057925]
  This paper explores how different types of explanations collaboratively meet users' XAI needs. We introduce the Intent Fulfilment Framework (IFF) for creating explanation experiences. The Explanation Experience Dialogue Model integrates the IFF and "Explanation Followups" to provide users with a conversational interface.
  arXiv  Detail & Related papers  (2024-05-16T21:13:43Z)
• XAI for All: Can Large Language Models Simplify Explainable AI? [0.0699049312989311]
  "x-[plAIn]" is a new approach to make XAI more accessible to a wider audience through a custom Large Language Model. Our goal was to design a model that can generate clear, concise summaries of various XAI methods. Results from our use-case studies show that our model is effective in providing easy-to-understand, audience-specific explanations.
  arXiv  Detail & Related papers  (2024-01-23T21:47:12Z)
• Explaining Explainability: Towards Deeper Actionable Insights into Deep Learning through Second-order Explainability [70.60433013657693]
  Second-order explainable AI (SOXAI) was recently proposed to extend explainable AI (XAI) from the instance level to the dataset level. We demonstrate for the first time, via example classification and segmentation cases, that eliminating irrelevant concepts from the training set based on actionable insights from SOXAI can enhance a model's performance.
  arXiv  Detail & Related papers  (2023-06-14T23:24:01Z)
• Towards Human Cognition Level-based Experiment Design for Counterfactual Explanations (XAI) [68.8204255655161]
  The emphasis of XAI research appears to have turned to a more pragmatic explanation approach for better understanding. An extensive area where cognitive science research may substantially influence XAI advancements is evaluating user knowledge and feedback. We propose a framework to experiment with generating and evaluating the explanations on the grounds of different cognitive levels of understanding.
  arXiv  Detail & Related papers  (2022-10-31T19:20:22Z)
• The Who in XAI: How AI Background Shapes Perceptions of AI Explanations [61.49776160925216]
  We conduct a mixed-methods study of how two different groups--people with and without AI background--perceive different types of AI explanations. We find that (1) both groups showed unwarranted faith in numbers for different reasons and (2) each group found value in different explanations beyond their intended design.
  arXiv  Detail & Related papers  (2021-07-28T17:32:04Z)
• A general framework for scientifically inspired explanations in AI [76.48625630211943]
  We instantiate the concept of structure of scientific explanation as the theoretical underpinning for a general framework in which explanations for AI systems can be implemented. This framework aims to provide the tools to build a "mental-model" of any AI system so that the interaction with the user can provide information on demand and be closer to the nature of human-made explanations.
  arXiv  Detail & Related papers  (2020-03-02T10:32:21Z)
• Explainable Active Learning (XAL): An Empirical Study of How Local Explanations Impact Annotator Experience [76.9910678786031]
  We propose a novel paradigm of explainable active learning (XAL), by introducing techniques from the recently surging field of explainable AI (XAI) into an Active Learning setting. Our study shows benefits of AI explanation as interfaces for machine teaching--supporting trust calibration and enabling rich forms of teaching feedback, and potential drawbacks--anchoring effect with the model judgment and cognitive workload.
  arXiv  Detail & Related papers  (2020-01-24T22:52:18Z)
• Deceptive AI Explanations: Creation and Detection [3.197020142231916]
  We investigate how AI models can be used to create and detect deceptive explanations. As an empirical evaluation, we focus on text classification and alter the explanations generated by GradCAM. We evaluate the effect of deceptive explanations on users in an experiment with 200 participants.
  arXiv  Detail & Related papers  (2020-01-21T16:41:22Z)

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.