SinkProbe detects hallucinations in LLMs by analyzing attention sinks in attention maps, showing they indicate transitions to prior-dominated computation and achieving state-of-the-art results.
URL https://www.sciencedirect.com/ science/article/pii/S157401372600078X
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Attention Sinks as Internal Signals for Hallucination Detection in Large Language Models
SinkProbe detects hallucinations in LLMs by analyzing attention sinks in attention maps, showing they indicate transitions to prior-dominated computation and achieving state-of-the-art results.