Detecting Contextual Hallucinations in LLMs with Frequency-Aware Attention

Siya Qi, Yudong Chen, Runcong Zhao, Qinglin Zhu, Zhanghao Hu, Wei Liu, Yulan He, Zheng Yuan, Lin Gui · Feb 20, 2026 · Citations: 0

Automatic Metrics General

Open arXiv RSS feed

Abstract

Hallucination detection is critical for ensuring the reliability of large language models (LLMs) in context-based generation. Prior work has explored intrinsic signals available during generation, among which attention offers a direct view of grounding behavior. However, existing approaches typically rely on coarse summaries that fail to capture fine-grained instabilities in attention. Inspired by signal processing, we introduce a frequency-aware perspective on attention by analyzing its variation during generation. We model attention distributions as discrete signals and extract high-frequency components that reflect rapid local changes in attention. Our analysis reveals that hallucinated tokens are associated with high-frequency attention energy, reflecting fragmented and unstable grounding behavior. Based on this insight, we develop a lightweight hallucination detector using high-frequency attention features. Experiments on the RAGTruth and HalluRAG benchmarks show that our approach achieves performance gains over verification-based, internal-representation-based, and attention-based methods across models and tasks.

Human Data Lens

Uses human feedback: No
Feedback types: None
Rater population: Unknown
Unit of annotation: Unknown
Expertise required: General

Evaluation Lens

Evaluation modes: Automatic Metrics
Agentic eval: None
Quality controls: Not reported
Confidence: 0.30
Flags: low_signal, possible_false_positive

Research Summary

Contribution Summary

Hallucination detection is critical for ensuring the reliability of large language models (LLMs) in context-based generation.
Prior work has explored intrinsic signals available during generation, among which attention offers a direct view of grounding behavior.
However, existing approaches typically rely on coarse summaries that fail to capture fine-grained instabilities in attention.

Why It Matters For Eval

Experiments on the RAGTruth and HalluRAG benchmarks show that our approach achieves performance gains over verification-based, internal-representation-based, and attention-based methods across models and tasks.