InterrogateLLM: Zero-Resource Hallucination Detection in LLM-Generated Answers

TL;DR

This paper introduces a new method for detecting hallucinations in large language models, demonstrating high accuracy across multiple datasets and models without external knowledge, thus addressing a key barrier to their widespread adoption.

Contribution

The paper presents a novel hallucination detection technique for LLMs that is effective without external knowledge and validated across various models and datasets.

Findings

Up to 87% hallucination rate in Llama-2

Balanced Accuracy of 81% in detection

Effective across multiple datasets and models

Abstract

Despite the many advances of Large Language Models (LLMs) and their unprecedented rapid evolution, their impact and integration into every facet of our daily lives is limited due to various reasons. One critical factor hindering their widespread adoption is the occurrence of hallucinations, where LLMs invent answers that sound realistic, yet drift away from factual truth. In this paper, we present a novel method for detecting hallucinations in large language models, which tackles a critical issue in the adoption of these models in various real-world scenarios. Through extensive evaluations across multiple datasets and LLMs, including Llama-2, we study the hallucination levels of various recent LLMs and demonstrate the effectiveness of our method to automatically detect them. Notably, we observe up to 87% hallucinations for Llama-2 in a specific experiment, where our method achieves a Balanced Accuracy of 81%, all without relying on external knowledge.