Iterative self-finetuning of LLMs mostly fails to amplify seeded behavioral traits, with amplification limited to specific DPO setups and often harming coherence.
πθ is the policy, or the current model at every step
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Iterative Finetuning is Mostly Idempotent
Iterative self-finetuning of LLMs mostly fails to amplify seeded behavioral traits, with amplification limited to specific DPO setups and often harming coherence.