Bridging HCI and AI Research for the Evaluation of Conversational SE Assistants

2025-02-11

AI Summary

To address the misalignment with user needs, poor scalability, and weak interpretability in evaluating LLM-driven software engineering (SE) dialogue assistants, this paper proposes the first interdisciplinary evaluation framework integrating human-computer interaction (HCI) principles with AI-based automated assessment. Methodologically, it systematically unifies HCI-driven requirement modeling with LLM behavioral modeling, designs a developer-centered automated metric suite, and ensures reliability through multi-dimensional validity validation. Key contributions include: (1) articulating six core human-centered requirements and associated challenges for automated SE assistant evaluation; (2) establishing a scalable, reproducible, and user-aligned evaluation paradigm; and (3) providing both theoretical foundations and an open, implementable toolchain. The framework significantly enhances the practicality, transparency, and human-factor compatibility of SE assistant evaluation.

Technology Category

• Humans and AI: User Experience and Usability
• Machine Learning: Large Multimodal Models (LMMs)
• Search and Optimization: Evaluation and Analysis

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

As Large Language Models (LLMs) are increasingly adopted in software engineering, recently in the form of conversational assistants, ensuring these technologies align with developers' needs is essential. The limitations of traditional human-centered methods for evaluating LLM-based tools at scale raise the need for automatic evaluation. In this paper, we advocate combining insights from human-computer interaction (HCI) and artificial intelligence (AI) research to enable human-centered automatic evaluation of LLM-based conversational SE assistants. We identify requirements for such evaluation and challenges down the road, working towards a framework that ensures these assistants are designed and deployed in line with user needs.

Problem

• Evaluate LLM-based conversational assistants
• Combine HCI and AI research insights
• Ensure alignment with developers' needs

Innovation

• Combines HCI and AI insights
• Human-centered automatic evaluation
• Framework for user-aligned deployment