RELIC: Investigating Large Language Model Responses using Self-Consistency
This addresses the issue of unreliable text generation for users interacting with LLMs, but it is incremental as it builds on existing self-consistency methods.
The authors tackled the problem of LLM hallucinations by proposing RELIC, an interactive system that uses self-consistency across multiple LLM responses to help users assess reliability, and a user study with ten participants showed it improved verification.
Large Language Models (LLMs) are notorious for blending fact with fiction and generating non-factual content, known as hallucinations. To address this challenge, we propose an interactive system that helps users gain insight into the reliability of the generated text. Our approach is based on the idea that the self-consistency of multiple samples generated by the same LLM relates to its confidence in individual claims in the generated texts. Using this idea, we design RELIC, an interactive system that enables users to investigate and verify semantic-level variations in multiple long-form responses. This allows users to recognize potentially inaccurate information in the generated text and make necessary corrections. From a user study with ten participants, we demonstrate that our approach helps users better verify the reliability of the generated text. We further summarize the design implications and lessons learned from this research for future studies of reliable human-LLM interactions.