APCD adaptively branches LLM decoding paths based on token entropy and contrasts divergent paths to improve factual accuracy while preserving efficiency.
In-context sharpness as alerts: An inner representation perspective for hallucination mitigation,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
A framework detects LLM anomalies including hallucinations, jailbreaks, and backdoors by forensic inspection of layer-wise hidden state patterns, reporting over 95% accuracy with minimal computational overhead.
citing papers explorer
-
APCD: Adaptive Path-Contrastive Decoding for Reliable Large Language Model Generation
APCD adaptively branches LLM decoding paths based on token entropy and contrasts divergent paths to improve factual accuracy while preserving efficiency.
-
Exposing the Ghost in the Transformer: Abnormal Detection for Large Language Models via Hidden State Forensics
A framework detects LLM anomalies including hallucinations, jailbreaks, and backdoors by forensic inspection of layer-wise hidden state patterns, reporting over 95% accuracy with minimal computational overhead.