Token-wise minimum and base-relative consensus over per-source fine-tunes suppress hidden and explicit poisoning that union training and weight averaging retain.
14 A Illustrative Examples: Two Disagreement Policies The following examples isolate the rules’ different responses to disputed mass
1 Pith paper cite this work, alongside 2 external citations. Polarity classification is still indexing.
1
Pith paper citing it
2
external citations · OpenAlex
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning
Token-wise minimum and base-relative consensus over per-source fine-tunes suppress hidden and explicit poisoning that union training and weight averaging retain.