Cleanse: Uncertainty Estimation Approach Using Clustering-based Semantic Consistency in LLMs

TL;DR

This paper introduces Cleanse, a clustering-based semantic consistency method for uncertainty estimation in LLMs, effectively detecting hallucinations to improve the safety and reliability of NLP applications.

Contribution

Cleanse is a novel approach that uses intra-cluster semantic consistency to quantify uncertainty in LLM responses, enhancing hallucination detection.

Findings

Effective in detecting hallucinations across multiple LLMs

Validated on SQuAD and CoQA benchmarks

Improves reliability of LLM outputs

Abstract

Despite the outstanding performance of large language models (LLMs) across various NLP tasks, hallucinations in LLMs--where LLMs generate inaccurate responses--remains as a critical problem as it can be directly connected to a crisis of building safe and reliable LLMs. Uncertainty estimation is primarily used to measure hallucination levels in LLM responses so that correct and incorrect answers can be distinguished clearly. This study proposes an effective uncertainty estimation approach, \textbf{Cl}ust\textbf{e}ring-based sem\textbf{an}tic con\textbf{s}ist\textbf{e}ncy (\textbf{Cleanse}). Cleanse quantifies the uncertainty with the proportion of the intra-cluster consistency in the total consistency between LLM hidden embeddings which contain adequate semantic information of generations, by employing clustering. The effectiveness of Cleanse for detecting hallucination is validated using four off-the-shelf models, LLaMA-7B, LLaMA-13B, LLaMA2-7B and Mistral-7B and two question-answering benchmarks, SQuAD and CoQA.