An Information-Flow Perspective on Explainability Requirements: Specification and Verification

• URL: http://arxiv.org/abs/2509.01479v2
• Date: Tue, 23 Sep 2025 14:27:05 GMT
• Title: An Information-Flow Perspective on Explainability Requirements: Specification and Verification
• Abstract summary: We argue that explainable systems expose information about why certain observed effects are happening to the agents interacting with them.<n>This constitutes a positive flow of information that needs to be specified, verified, and balanced against negative information flow that may, e.g., violate privacy guarantees.<n>We show how this principle can be used to specify explainability as a system-level requirement and provide an algorithm for checking finite-state models against such specifications.
• Score: 5.849736173068869
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Explainable systems expose information about why certain observed effects are happening to the agents interacting with them. We argue that this constitutes a positive flow of information that needs to be specified, verified, and balanced against negative information flow that may, e.g., violate privacy guarantees. Since both explainability and privacy require reasoning about knowledge, we tackle these tasks with epistemic temporal logic extended with quantification over counterfactual causes. This allows us to specify that a multi-agent system exposes enough information such that agents acquire knowledge on why some effect occurred. We show how this principle can be used to specify explainability as a system-level requirement and provide an algorithm for checking finite-state models against such specifications. We present a prototype implementation of the algorithm and evaluate it on several benchmarks, illustrating how our approach distinguishes between explainable and unexplainable systems, and how it allows to pose additional privacy requirements.

Related papers

• Towards A Unified Information Bottleneck Framework for Time Series Explanations [27.646760316510356]
  We show that existing explainers are vulnerable to trivial solutions and distributional shifts.<n>We propose a unified objective function for explainable time series learning that bridges attribution and counterfactual reasoning.<n>Our formulation explicitly prevents trivial explanations and out-of-distribution counterfactuals.
  arXiv  Detail & Related papers  (2026-08-26T15:14:52Z)
• On the Definition and Detection of Cherry-Picking in Counterfactual Explanations [0.0]
  We formally define cherry-picking for counterfactual explanations.<n>We show that detection is extremely limited in practice.<n>We argue that safeguards should prioritise, standardisation, and procedural constraints over post-hoc detection.
  arXiv  Detail & Related papers  (2026-01-08T14:29:24Z)
• Private Counterfactual Retrieval [34.11302393278422]
  Transparency and explainability are two extremely important aspects to be considered when employing black-box machine learning models in high-stake applications.<n>Providing counterfactual explanations is one way of fulfilling this requirement.<n>We propose multiple schemes inspired by private information retrieval (PIR) techniques which ensure the emphuser's privacy when retrieving counterfactual explanations.
  arXiv  Detail & Related papers  (2024-10-17T17:45:07Z)
• New Rules for Causal Identification with Background Knowledge [59.733125324672656]
  We propose two novel rules for incorporating BK, which offer a new perspective to the open problem. We show that these rules are applicable in some typical causality tasks, such as determining the set of possible causal effects with observational data.
  arXiv  Detail & Related papers  (2024-07-21T20:21:21Z)
• A Model-oriented Reasoning Framework for Privacy Analysis of Complex Systems [2.001711587270359]
  This paper proposes a reasoning framework for privacy properties of systems and their environments. It can capture any knowledge leaks on different logical levels to answer the question: which entity can learn what?
  arXiv  Detail & Related papers  (2024-05-14T06:52:56Z)
• 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)
• Justification vs. Transparency: Why and How Visual Explanations in a Scientific Literature Recommender System [0.0]
  We identify relationships between Why and How explanation intelligibility types and the explanation goals of justification and transparency. Our study shows that the choice of the explanation intelligibility types depends on the explanation goal and user type.
  arXiv  Detail & Related papers  (2023-05-26T15:40:46Z)
• How (Not) To Evaluate Explanation Quality [29.40729766120284]
  We formulate desired characteristics of explanation quality that apply across tasks and domains. We propose actionable guidelines to overcome obstacles that limit today's evaluation of explanation quality.
  arXiv  Detail & Related papers  (2022-10-13T16:06:59Z)
• Explainability in Process Outcome Prediction: Guidelines to Obtain Interpretable and Faithful Models [77.34726150561087]
  We define explainability through the interpretability of the explanations and the faithfulness of the explainability model in the field of process outcome prediction. This paper contributes a set of guidelines named X-MOP which allows selecting the appropriate model based on the event log specifications.
  arXiv  Detail & Related papers  (2022-03-30T05:59:50Z)
• Uncertainty Quantification of Surrogate Explanations: an Ordinal Consensus Approach [1.3750624267664155]
  We produce estimates of the uncertainty of a given explanation by measuring the consensus amongst a set of diverse bootstrapped surrogate explainers. We empirically illustrate the properties of this approach through experiments on state-of-the-art Convolutional Neural Network ensembles.
  arXiv  Detail & Related papers  (2021-11-17T13:55:58Z)
• Nested Counterfactual Identification from Arbitrary Surrogate Experiments [95.48089725859298]
  We study the identification of nested counterfactuals from an arbitrary combination of observations and experiments. Specifically, we prove the counterfactual unnesting theorem (CUT), which allows one to map arbitrary nested counterfactuals to unnested ones.
  arXiv  Detail & Related papers  (2021-07-07T12:51:04Z)
• Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation [51.29486247405601]
  We design a framework to generate counterfactuals for raw data instances with the proposed Attribute-Informed Perturbation (AIP) By utilizing generative models conditioned with different attributes, counterfactuals with desired labels can be obtained effectively and efficiently. Experimental results on real-world texts and images demonstrate the effectiveness, sample quality as well as efficiency of our designed framework.
  arXiv  Detail & Related papers  (2021-01-18T08:37:13Z)
• Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty [66.17147341354577]
  We argue for considering a complementary form of transparency by estimating and communicating the uncertainty associated with model predictions. We describe how uncertainty can be used to mitigate model unfairness, augment decision-making, and build trustworthy systems. This work constitutes an interdisciplinary review drawn from literature spanning machine learning, visualization/HCI, design, decision-making, and fairness.
  arXiv  Detail & Related papers  (2020-11-15T17:26:14Z)

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.