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

• URL: http://arxiv.org/abs/2607.11771v1
• Date: Mon, 13 Jul 2026 16:28:45 GMT
• Title: Evaluating RE Practices for Explainability: Synthesizing Insights from Daimler Truck into an Explainable RE Framework Proposal
• Abstract summary: This paper reports findings from an ongoing industry-based study investigating how explainability requirements are elicited, specified, and validated.<n>Our preliminary analysis reveals recurring challenges across all steps, including conceptual ambiguity during elicitation, limited testability and expressiveness during specification, and fragmented validation due to vague criteria and regulatory uncertainty.<n>The paper contributes empirical insights into step-specific and cross-cutting challenges and outlines a research vision toward developing an empirically grounded RE framework for explainable AI-based systems.
• Score: 4.854198429397777
• License: http://creativecommons.org/licenses/by-sa/4.0/
• 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 explainability, there is limited empirical understanding of how existing Requirements Engineering (RE) practices support explainability requirements across the RE lifecycle, especially in an industrial context. This paper reports early findings from an ongoing industry-based study investigating how explainability requirements are elicited, specified, and validated using established RE techniques. We conducted a multi-phase qualitative study with eight practitioners at Daimler Truck, employing think-aloud protocols and moderated group discussions across requirements elicitation, specification, and validation steps. Our preliminary analysis reveals recurring challenges across all steps, including conceptual ambiguity during elicitation, limited testability and expressiveness during specification, and fragmented validation due to vague criteria and regulatory uncertainty. These findings indicate that current RE practices provide limited support to systematically address explainability requirements. The paper contributes empirical insights into step-specific and cross-cutting challenges and outlines a research vision toward developing an empirically grounded RE framework for explainable AI-based systems.

Related papers

• Position: Anthropomorphic Misalignment Research Needs Stronger Evidence [52.76826423649968]
  We show how conceptual ambiguity, non-robust datasets, experimental design, and insufficient causal interventions can lead to overinterpretation of model behaviors.<n>This position paper aims to offer guidance on evidentiary considerations that can help improve methodological rigor in AMR.
  arXiv  Detail & Related papers  (2026-05-29T16:38:53Z)
• A Rapid Review Regarding the Concept of Legal Requirements in Requirements Engineering [0.0]
  Legal requirements (LRs) are often characterized as vague and complex, requiring a lot of effort to elicit, implement, and validate.<n>LRs seem to be also reluctantly implemented, often providing only a minimal baseline for other requirements.
  arXiv  Detail & Related papers  (2025-09-07T11:02:45Z)
• Towards a Framework for Operationalizing the Specification of Trustworthy AI Requirements [1.2184324428571227]
  Growing concerns around the trustworthiness of AI-enabled systems highlight the role of requirements engineering (RE)<n>We propose the integration of two complementary approaches: AMDiRE and PerSpecML.
  arXiv  Detail & Related papers  (2025-07-14T12:49:26Z)
• CTRLS: Chain-of-Thought Reasoning via Latent State-Transition [57.51370433303236]
  Chain-of-thought (CoT) reasoning enables large language models to break down complex problems into interpretable intermediate steps.<n>We introduce groundingS, a framework that formulates CoT reasoning as a Markov decision process (MDP) with latent state transitions.<n>We show improvements in reasoning accuracy, diversity, and exploration efficiency across benchmark reasoning tasks.
  arXiv  Detail & Related papers  (2025-07-10T21:32:18Z)
• Domain Knowledge in Requirements Engineering: A Systematic Mapping Study [1.0396117988046165]
  Domain knowledge is recognized as a key component for the success of Requirements Engineering (RE)<n>Despite its relevance, the scientific literature still lacks a systematic consolidation of how domain knowledge can be effectively used and operationalized in RE.
  arXiv  Detail & Related papers  (2025-06-25T18:27:51Z)
• RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning [60.84707424369494]
  Chain-of-Thought (CoT) reasoning has proven effective in enhancing large language models (LLMs) on complex tasks.<n>We introduce the Reasoning Boundary Framework++ (RBF++), a framework for evaluating and optimizing measurable boundaries of CoT capability.
  arXiv  Detail & Related papers  (2025-05-19T16:25:55Z)
• Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities [101.77467538102924]
  Recent advancements in Large Reasoning Models (LRMs) have demonstrated remarkable performance in specialized reasoning tasks.<n>We show that acquiring deliberative reasoning capabilities significantly reduces the foundational capabilities of LRMs.<n>We demonstrate that adaptive reasoning -- employing modes like Zero-Thinking, Less-Thinking, and Summary-Thinking -- can effectively alleviate these drawbacks.
  arXiv  Detail & Related papers  (2025-03-23T08:18:51Z)
• An Adaptive Framework for Generating Systematic Explanatory Answer in Online Q&A Platforms [62.878616839799776]
  We propose SynthRAG, an innovative framework designed to enhance Question Answering (QA) performance. SynthRAG improves on conventional models by employing adaptive outlines for dynamic content structuring. An online deployment on the Zhihu platform revealed that SynthRAG's answers achieved notable user engagement.
  arXiv  Detail & Related papers  (2024-10-23T09:14:57Z)
• Towards a Unified Framework for Evaluating Explanations [0.6138671548064356]
  We argue that explanations serve as mediators between models and stakeholders, whether for intrinsically interpretable models or opaque black-box models. We illustrate these criteria, as well as specific evaluation methods, using examples from an ongoing study of an interpretable neural network for predicting a particular learner behavior.
  arXiv  Detail & Related papers  (2024-05-22T21:49:28Z)
• On Developing an Artifact-based Approach to Regulatory Requirements Engineering [18.256422026527986]
  Regulatory acts are a challenging source when eliciting, interpreting, and analyzing requirements. No existing approach considers explicating and managing legal domain knowledge and engineering-legal coordination. We introduce the first version of our Artifact Model for Regulatory Requirements Engineering (AM4RRE) and its conceptual foundation.
  arXiv  Detail & Related papers  (2024-05-01T09:51:56Z)
• A Survey on Interpretable Cross-modal Reasoning [64.37362731950843]
  Cross-modal reasoning (CMR) has emerged as a pivotal area with applications spanning from multimedia analysis to healthcare diagnostics. This survey delves into the realm of interpretable cross-modal reasoning (I-CMR) This survey presents a comprehensive overview of the typical methods with a three-level taxonomy for I-CMR.
  arXiv  Detail & Related papers  (2023-09-05T05:06:48Z)

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.