Emotional Strain and Frustration in LLM Interactions in Software Engineering

2025-04-14

AI Summary

This study investigates how large language models (LLMs) induce emotional stress and frustration among software engineers during real-world engineering practice. Method: We conducted a mixed-methods study with 62 industry and academic practitioners, combining surveys, semi-structured interviews, and emotion-attribution modeling. Contribution/Results: We systematically identify three primary triggers of frustration—correctness defects, insufficient contextual adaptability, and formatting/style deviations—and reveal that while correctness issues most frequently provoke immediate frustration, low-salience *non-functional defects* (e.g., formatting mismatches) drive chronic frustration due to high-frequency rework (reported by 75% of participants). We introduce the “cumulative frustration effect” as a novel explanatory framework and derive eight empirically grounded, actionable guidelines for LLM interaction design—spanning UX improvements and toolchain integration—to enhance developer well-being and support human-centered adoption of LLMs in software engineering.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Cognitive Modeling & Cognitive Systems: Affective Computing

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Large Language Models (LLMs) are increasingly integrated into various daily tasks in Software Engineering such as coding and requirement elicitation. Despite their various capabilities and constant use, some interactions can lead to unexpected challenges (e.g. hallucinations or verbose answers) and, in turn, cause emotions that develop into frustration. Frustration can negatively impact engineers' productivity and well-being if they escalate into stress and burnout. In this paper, we assess the impact of LLM interactions on software engineers' emotional responses, specifically strains, and identify common causes of frustration when interacting with LLMs at work. Based on 62 survey responses from software engineers in industry and academia across various companies and universities, we found that a majority of our respondents experience frustrations or other related emotions regardless of the nature of their work. Additionally, our results showed that frustration mainly stemmed from issues with correctness and less critical issues such as adaptability to context or specific format. While such issues may not cause frustration in general, artefacts that do not follow certain preferences, standards, or best practices can make the output unusable without extensive modification, causing frustration over time. In addition to the frustration triggers, our study offers guidelines to improve the software engineers' experience, aiming to minimise long-term consequences on mental health.

Problem

• Assess emotional impact of LLMs on software engineers
• Identify causes of frustration in LLM interactions
• Improve guidelines to minimize mental health consequences

Innovation

• Assessing emotional impact of LLM interactions
• Identifying frustration causes in LLM usage
• Providing guidelines to improve engineer experience