HILL: A Hallucination Identifier for Large Language Models

Abstract

Large language models (LLMs) are prone to hallucinations, i.e., nonsensical, unfaithful, and undesirable text. Users tend to overrely on LLMs and corresponding hallucinations which can lead to misinterpretations and errors. To tackle the problem of overreliance, we propose HILL, the "Hallucination Identifier for Large Language Models". First, we identified design features for HILL with a Wizard of Oz approach with nine participants. Subsequently, we implemented HILL based on the identified design features and evaluated HILL's interface design by surveying 17 participants. Further, we investigated HILL's functionality to identify hallucinations based on an existing question-answering dataset and five user interviews. We find that HILL can correctly identify and highlight hallucinations in LLM responses which enables users to handle LLM responses with more caution. With that, we propose an easy-to-implement adaptation to existing LLMs and demonstrate the relevance of user-centered designs of AI artifacts.

References in corpus (5)

• Survey of Hallucination in Natural Language Generation
• Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems
• Extracting Training Data from Large Language Models
• Appropriate Reliance on AI Advice: Conceptualization and the Effect of Explanations
• Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond

Cited by in corpus (3)

• Can Large Language Models Grasp Concepts in Visual Content? A Case Study on YouTube Shorts about Depression
• Learning from AVA: Early Lessons from a Curated and Trustworthy Generative AI for Policy and Development Research
• From Mind Mapping to Dream Interpretation: Understanding Muslim Users' Engagement with GenAI Tools in Religious Context