‡a
distillseqaframeworkforsafetyalignmenttestinginlargelanguagemodelsusingknowledgedistillation
‡A
DistillSeq: A Framework for Safety Alignment Testing in Large Language Models using Knowledge Distillation
‡9
1
‡a
drowzeemetamorphictestingforfactconflictinghallucinationdetectioninlargelanguagemodels
‡A
Drowzee: Metamorphic Testing for Fact-Conflicting Hallucination Detection in Large Language Models
‡9
1
‡a
glitchtokensinlargelanguagemodelscategorizationtaxonomyandeffectivedetection
‡A
Glitch Tokens in Large Language Models: Categorization Taxonomy and Effective Detection
‡9
1
