TuCo quantifies the contribution of fine-tuning to individual LLM responses as the ratio of fine-tuning to pre-training component magnitudes, and shows jailbreak attacks lower this ratio.
Many-shot jailbreaking
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs
TuCo quantifies the contribution of fine-tuning to individual LLM responses as the ratio of fine-tuning to pre-training component magnitudes, and shows jailbreak attacks lower this ratio.