Why and When LLM-Based Assistants Can Go Wrong: Investigating the Effectiveness of Prompt-Based Interactions for Software Help-Seeking

Abstract

Large Language Model (LLM) assistants, such as ChatGPT, have emerged as potential alternatives to search methods for helping users navigate complex, feature-rich software. LLMs use vast training data from domain-specific texts, software manuals, and code repositories to mimic human-like interactions, offering tailored assistance, including step-by-step instructions. In this work, we investigated LLM-generated software guidance through a within-subject experiment with 16 participants and follow-up interviews. We compared a baseline LLM assistant with an LLM optimized for particular software contexts, SoftAIBot, which also offered guidelines for constructing appropriate prompts. We assessed task completion, perceived accuracy, relevance, and trust. Surprisingly, although SoftAIBot outperformed the baseline LLM, our results revealed no significant difference in LLM usage and user perceptions with or without prompt guidelines and the integration of domain context. Most users struggled to understand how the prompt's text related to the LLM's responses and often followed the LLM's suggestions verbatim, even if they were incorrect. This resulted in difficulties when using the LLM's advice for software tasks, leading to low task completion rates. Our detailed analysis also revealed that users remained unaware of inaccuracies in the LLM's responses, indicating a gap between their lack of software expertise and their ability to evaluate the LLM's assistance. With the growing push for designing domain-specific LLM assistants, we emphasize the importance of incorporating explainable, context-aware cues into LLMs to help users understand prompt-based interactions, identify biases, and maximize the utility of LLM assistants.

arXiv commentAccepted for publication in the Proceedings of the 29th International Conference on Intelligent User Interfaces (IUI'24), March 18--21, 2024, in Greenville, SC, USA

Cited by in corpus (8)

• VeriPlan: Integrating Formal Verification and LLMs into End-User Planning
• Do It For Me vs. Do It With Me: Investigating User Perceptions of Different Paradigms of Automation in Copilots for Feature-Rich Software
• Interaction Configurations and Prompt Guidance in Conversational AI for Question Answering in Human-AI Teams
• A Risk Taxonomy and Reflection Tool for Large Language Model Adoption in Public Health
• Thoughtful, Confused, or Untrustworthy: How Text Presentation Influences Perceptions of AI Writing Tools
• Analyzing the Presentation, Content, and Utilization of References in LLM-powered Conversational AI Systems
• Evaluating the Effects of Prompt Perturbation on Bias and Hallucination in Large Language Models
• The Invisible Mentor: Inferring User Actions from Screen Recordings to Recommend Better Workflows