Introduces MOOD benchmark for OOD LLM alignment failures and shows guard models plus Mahalanobis and perplexity OOD detectors improve recall from 39% to 45% with positive scaling.
Title resolution pending
2 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
2
Pith papers citing it
1
external citations · external index
representative citing papers
Fine-tuning on new knowledge induces propagating hallucinations in LLMs by weakening attention to key entities, with mitigation via reintroducing known knowledge during later training stages.
citing papers explorer
-
Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs
Introduces MOOD benchmark for OOD LLM alignment failures and shows guard models plus Mahalanobis and perplexity OOD detectors improve recall from 39% to 45% with positive scaling.
-
Understanding New-Knowledge-Induced Factual Hallucinations in LLMs: Analysis and Interpretation
Fine-tuning on new knowledge induces propagating hallucinations in LLMs by weakening attention to key entities, with mitigation via reintroducing known knowledge during later training stages.