XAI Handbook: Towards a Unified Framework for Explainable AI

• URL: http://arxiv.org/abs/2105.06677v1
• Date: Fri, 14 May 2021 07:28:21 GMT
• Title: XAI Handbook: Towards a Unified Framework for Explainable AI
• Authors: Sebastian Palacio, Adriano Lucieri, Mohsin Munir, J\"orn Hees, Sheraz Ahmed, Andreas Dengel
• Abstract summary: The field of explainable AI (XAI) has quickly become a thriving and prolific community. Each new contribution seems to rely on its own (and often intuitive) version of terms like "explanation" and "interpretation" We propose a theoretical framework that not only provides concrete definitions for these terms, but it also outlines all steps necessary to produce explanations and interpretations.
• Score: 5.716475756970092
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: The field of explainable AI (XAI) has quickly become a thriving and prolific community. However, a silent, recurrent and acknowledged issue in this area is the lack of consensus regarding its terminology. In particular, each new contribution seems to rely on its own (and often intuitive) version of terms like "explanation" and "interpretation". Such disarray encumbers the consolidation of advances in the field towards the fulfillment of scientific and regulatory demands e.g., when comparing methods or establishing their compliance with respect to biases and fairness constraints. We propose a theoretical framework that not only provides concrete definitions for these terms, but it also outlines all steps necessary to produce explanations and interpretations. The framework also allows for existing contributions to be re-contextualized such that their scope can be measured, thus making them comparable to other methods. We show that this framework is compliant with desiderata on explanations, on interpretability and on evaluation metrics. We present a use-case showing how the framework can be used to compare LIME, SHAP and MDNet, establishing their advantages and shortcomings. Finally, we discuss relevant trends in XAI as well as recommendations for future work, all from the standpoint of our framework.

Related papers

• Sparsity-Guided Holistic Explanation for LLMs with Interpretable Inference-Time Intervention [53.896974148579346]
  Large Language Models (LLMs) have achieved unprecedented breakthroughs in various natural language processing domains. The enigmatic black-box'' nature of LLMs remains a significant challenge for interpretability, hampering transparent and accountable applications. We propose a novel methodology anchored in sparsity-guided techniques, aiming to provide a holistic interpretation of LLMs.
  arXiv  Detail & Related papers  (2023-12-22T19:55:58Z)
• How Well Do Text Embedding Models Understand Syntax? [50.440590035493074]
  The ability of text embedding models to generalize across a wide range of syntactic contexts remains under-explored. Our findings reveal that existing text embedding models have not sufficiently addressed these syntactic understanding challenges. We propose strategies to augment the generalization ability of text embedding models in diverse syntactic scenarios.
  arXiv  Detail & Related papers  (2023-11-14T08:51:00Z)
• Goodhart's Law Applies to NLP's Explanation Benchmarks [57.26445915212884]
  We critically examine two sets of metrics: the ERASER metrics (comprehensiveness and sufficiency) and the EVAL-X metrics. We show that we can inflate a model's comprehensiveness and sufficiency scores dramatically without altering its predictions or explanations on in-distribution test inputs. Our results raise doubts about the ability of current metrics to guide explainability research, underscoring the need for a broader reassessment of what precisely these metrics are intended to capture.
  arXiv  Detail & Related papers  (2023-08-28T03:03:03Z)
• Categorical Foundations of Explainable AI: A Unifying Theory [8.637435154170916]
  This paper presents the first mathematically rigorous definitions of key XAI notions and processes, using the well-funded formalism of Category theory. We show that our categorical framework allows to: (i) model existing learning schemes and architectures, (ii) formally define the term "explanation", (iii) establish a theoretical basis for XAI, and (iv) analyze commonly overlooked aspects of explaining methods.
  arXiv  Detail & Related papers  (2023-04-27T11:10:16Z)
• Charting the Sociotechnical Gap in Explainable AI: A Framework to Address the Gap in XAI [29.33534897830558]
  We argue that charting the gap improves our problem understanding, which can reflexively provide actionable insights to improve explainability. We empirically derive a framework that facilitates systematic charting of the sociotechnical gap. By making conceptual and practical contributions to understanding the sociotechnical gap in XAI, the framework expands the XAI design space.
  arXiv  Detail & Related papers  (2023-02-01T23:21:45Z)
• Explainable Artificial Intelligence in Construction: The Content, Context, Process, Outcome Evaluation Framework [1.3375143521862154]
  We develop a content, context, process, and outcome evaluation framework that can be used to justify the adoption and effective management of XAI. While our novel framework is conceptual, it provides a frame of reference for construction organisations to make headway toward realising XAI business value and benefits.
  arXiv  Detail & Related papers  (2022-11-12T03:50:14Z)
• Rationale-Augmented Ensembles in Language Models [53.45015291520658]
  We reconsider rationale-augmented prompting for few-shot in-context learning. We identify rationale sampling in the output space as the key component to robustly improve performance. We demonstrate that rationale-augmented ensembles achieve more accurate and interpretable results than existing prompting approaches.
  arXiv  Detail & Related papers  (2022-07-02T06:20:57Z)
• Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AI [65.44737844681256]
  A lack of consensus on how to evaluate explainable AI (XAI) hinders the advancement of the field. We argue that one way to close the gap is to develop evaluation methods that account for different user requirements.
  arXiv  Detail & Related papers  (2022-06-22T05:17:33Z)
• Towards Unification of Discourse Annotation Frameworks [0.0]
  We will investigate the systematic relations between different frameworks and devise methods of unifying the frameworks. Although the issue of framework unification has been a topic of discussion for a long time, there is currently no comprehensive approach. We plan to use automatic means for the unification task and evaluate the result with structural complexity and downstream tasks.
  arXiv  Detail & Related papers  (2022-04-16T11:34:00Z)
• On the Faithfulness Measurements for Model Interpretations [100.2730234575114]
  Post-hoc interpretations aim to uncover how natural language processing (NLP) models make predictions. To tackle these issues, we start with three criteria: the removal-based criterion, the sensitivity of interpretations, and the stability of interpretations. Motivated by the desideratum of these faithfulness notions, we introduce a new class of interpretation methods that adopt techniques from the adversarial domain.
  arXiv  Detail & Related papers  (2021-04-18T09:19:44Z)
• Metrics and continuity in reinforcement learning [34.10996560464196]
  We introduce a unified formalism for defining topologies through the lens of metrics. We establish a hierarchy amongst these metrics and demonstrate their theoretical implications on the Markov Decision Process. We complement our theoretical results with empirical evaluations showcasing the differences between the metrics considered.
  arXiv  Detail & Related papers  (2021-02-02T14:30:41Z)

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.