PulseAugur
EN
LIVE 00:18:34

New research highlights challenges in AI explainability requirements engineering

By PulseAugur Editorial · [2 sources] ·

A new research paper explores the challenges of integrating explainability requirements into existing Requirements Engineering (RE) practices within the AI domain. The study, which involved eight practitioners at Daimler Truck, identified recurring issues across elicitation, specification, and validation phases. These challenges include conceptual ambiguity, limited testability, and regulatory uncertainty, suggesting that current RE methods offer insufficient support for systematically addressing explainability needs in AI systems. AI

IMPACT Highlights the need for improved methodologies to ensure AI systems are understandable and trustworthy in critical applications.

RANK_REASON The cluster contains an academic paper discussing research findings and proposing a framework.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New research highlights challenges in AI explainability requirements engineering

COVERAGE [2]

  1. arXiv cs.AI TIER_1 English(EN) · Umm-e- Habiba, Lucas Mauser, Jonas Fritzsch, Justus Bogner, Stefan Wagner ·

    Evaluating RE Practices for Explainability: Synthesizing Insights from Daimler Truck into an Explainable RE Framework Proposal

    arXiv:2607.11771v1 Announce Type: cross Abstract: Explainability has emerged as a critical requirement for AI-based systems, particularly in safety-critical and regulated domains. Although prior research has proposed frameworks, patterns, and user-centered approaches to support e…

  2. arXiv cs.AI TIER_1 English(EN) · Stefan Wagner ·

    Evaluating RE Practices for Explainability: Synthesizing Insights from Daimler Truck into an Explainable RE Framework Proposal

    Explainability has emerged as a critical requirement for AI-based systems, particularly in safety-critical and regulated domains. Although prior research has proposed frameworks, patterns, and user-centered approaches to support explainability, there is limited empirical understa…

RELATED ENTITIES

RELATED TOPICS