Intersectional Fairness in Large Language Models

Large Language Models (LLMs) are increasingly deployed in socially sensitive settings, raising concerns about fairness and biases, particularly across intersectional demographic attributes. In this paper, we systematically evaluate intersectional fairness in six LLMs using ambiguous and disambiguated contexts from two benchmark datasets. We assess LLM behavior using bias scores, subgroup fairness metrics, accuracy, and consistency through multi-run analysis across contexts and negative and non-negative question polarities. Our results show that while modern LLMs generally perform well in ambiguous contexts, this limits the informativeness of fairness metrics due to sparse non-unknown predictions. In disambiguated contexts, LLM accuracy is influenced by stereotype alignment, with models being more accurate when the correct answer reinforces a stereotype than when it contradicts it. This pattern is especially pronounced in race-gender intersections, where directional bias toward stereotypes is stronger. Subgroup fairness metrics further indicate that, despite low observed disparity in some cases, outcome distributions remain uneven across intersectional groups. Across repeated runs, responses also vary in consistency, including stereotype-aligned responses. Overall, our findings show that apparent model competence is partly associated with stereotype-consistent cues, and no evaluated LLM achieves consistently reliable or fair behavior across intersectional settings. These findings highlight the need for evaluation beyond accuracy, emphasizing the importance of combining bias, subgroup fairness, and consistency metrics across intersectional groups, contexts, and repeated runs.

From Inductive to Deductive: LLMs-Based Qualitative Data Analysis in Requirements Engineering

Requirements Engineering (RE) is essential for developing complex and regulated software projects. Given the challenges in transforming stakeholder inputs into consistent software designs, Qualitative Data Analysis (QDA) provides a systematic approach to handling free-form data. However, traditional QDA methods are time-consuming and heavily reliant on manual effort. In this paper, we explore the use of Large Language Models (LLMs), including GPT-4, Mistral, and LLaMA-2, to improve QDA tasks in RE. Our study evaluates LLMs' performance in inductive (zero-shot) and deductive (one-shot, few-shot) annotation tasks, revealing that GPT-4 achieves substantial agreement with human analysts in deductive settings, with Cohen's Kappa scores exceeding 0.7, while zero-shot performance remains limited. Detailed, context-rich prompts significantly improve annotation accuracy and consistency, particularly in deductive scenarios, and GPT-4 demonstrates high reliability across repeated runs. These findings highlight the potential of LLMs to support QDA in RE by reducing manual effort while maintaining annotation quality. The structured labels automatically provide traceability of requirements and can be directly utilized as classes in domain models, facilitating systematic software design.

A Survey for What Developers Require in AI-powered Tools that Aid in Component Selection in CBSD

Although it has been more than four decades that the first components-based software development (CBSD) studies were conducted, there is still no standard method or tool for component selection which is widely accepted by the industry. The gulf between industry and academia contributes to the lack of an accepted tool. We conducted a mixed methods survey of nearly 100 people engaged in component-based software engineering practice or research to better understand the problems facing industry, how these needs could be addressed, and current best practices employed in component selection. We also sought to identify and prioritize quality criteria for component selection from an industry perspective. In response to the call for CBSD component selection tools to incorporate recent technical advances, we also explored the perceptions of professionals about AI-driven tools, present and envisioned.

Pattern Discovery and Validation Using Scientific Research Methods

Pattern discovery, the process of discovering previously unrecognized patterns, is often performed as an ad-hoc process with little resulting certainty in the quality of the proposed patterns. Pattern validation, the process of validating the accuracy of proposed patterns, remains dominated by the simple heuristic of "the rule of three". This article shows how to use established scientific research methods for the purpose of pattern discovery and validation. We present a specific approach, called the handbook method, that uses the qualitative survey, action research, and case study research for pattern discovery and evaluation, and we discuss the underlying principle of using scientific methods in general. We evaluate the handbook method using three exploratory studies and demonstrate its usefulness.