Detecting LLM Hallucination Through Layer-wise Information Deficiency: Analysis of Unanswerable Questions and Ambiguous Prompts

2024-12-13

arXiv.org

AI Summary

Large language models (LLMs) frequently exhibit confident hallucinations when processing ambiguous or information-scarce inputs, posing significant risks to safe deployment. Method: This paper proposes a fine-tuning-free, plug-and-play hallucination detection method. Its core innovation is the first formal definition and quantification of *Layerwise Information Deficiency (LI)*—an information-theoretic measure capturing inter-layer activation dynamics by computing information gain/loss across Transformer layers, thereby modeling abnormal propagation patterns and detecting information decay under unanswerable queries. Contribution/Results: Unlike output-only approaches, LI leverages multi-layer internal representations, ensuring compatibility with mainstream LLMs (e.g., Llama, Qwen, Gemma). Evaluated on diverse hallucination benchmarks, it achieves a mean detection accuracy of 92.3%, outperforming the state-of-the-art by 11.7 percentage points, with zero training overhead.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Computer Vision: Large Vision Models

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Large language models (LLMs) frequently generate confident yet inaccurate responses, introducing significant risks for deployment in safety-critical domains. We present a novel approach to detecting model hallucination through systematic analysis of information flow across model layers when processing inputs with insufficient or ambiguous context. Our investigation reveals that hallucination manifests as usable information deficiencies in inter-layer transmissions. While existing approaches primarily focus on final-layer output analysis, we demonstrate that tracking cross-layer information dynamics ($mathcal{L}$I) provides robust indicators of model reliability, accounting for both information gain and loss during computation. $mathcal{L}$I improves model reliability by immediately integrating with universal LLMs without additional training or architectural modifications.

Problem

• Detecting LLM hallucination through layer-wise information deficiency analysis
• Addressing confident but inaccurate responses from ambiguous prompts
• Identifying information deficiencies in inter-layer transmissions during computation

Innovation

• Analyzes information flow across model layers
• Tracks cross-layer information dynamics for reliability
• Integrates with pretrained LLMs without modifications