Reranking an LLM's top-k candidate tokens by cosine similarity to predefined negative concept embeddings reduces unsafe responses and jailbreak success without retraining, but the reported gains are partly tuned to the evaluation data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DIESEL -- Dynamic Inference-Guidance via Evasion of Semantic Embeddings in LLMs
Reranking an LLM's top-k candidate tokens by cosine similarity to predefined negative concept embeddings reduces unsafe responses and jailbreak success without retraining, but the reported gains are partly tuned to the evaluation data.