arXiv AI
NeuroActiSep: Detecting Factual Hallucinations from Feed-Forward Neurons in a Single Pass
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 18
HalluTracer: Hallucination Detection via Depth-Averaging Truth Signals
arXiv:2608. 16353v1 Announce Type: cross Abstract: Even well-aligned large language models confidently generate factually incorrect text, making hallucination a persistent reliability risk in high-stakes deployments.
arXiv Machine Learning
Aug 4
Attention Sinks as Internal Signals for Hallucination Detection in Large Language Models
arXiv:2604. 10697v2 Announce Type: replace-cross Abstract: Large language models frequently exhibit hallucinations: fluent and confident outputs that are factually incorrect or unsupported by the input context.
arXiv AI
Jun 3
Automatic Layer Selection for Hallucination Detection
arXiv:2605. 26366v3 Announce Type: replace Abstract: Recent studies on hallucination detection have shown that hallucination-related signals are more strongly encoded in intermediate layers than in the final layer of large language models (LLMs).
arXiv AI
Jun 29
From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Models
arXiv:2606. 27679v1 Announce Type: cross Abstract: Probe-based uncertainty estimation (UE) has emerged as a prominent approach to detect hallucinations in Large Language Models (LLMs) by learning uncertainty from internal model signals.
arXiv AI
Jun 4
From Out-of-Distribution Detection to Hallucination Detection: A Geometric View
arXiv:2602. 07253v3 Announce Type: replace Abstract: Detecting hallucinations in large language models is a critical open problem with significant implications for safety and reliability.
arXiv AI
1d ago
Alleviating Hallucination in Reasoning Tasks with Training-Free Uncertainty-Guided Steering
arXiv:2609.38962v1 Announce Type: new Abstract: Recent work on hallucination detection in large language models has shown that, for a fixed pre-trained model and reasoning task, it is possible to est...