Experiments on four models and three datasets show SFT increases sensitivity to easy contexts while later stages (DPO, RLVR) can reinforce or reverse those preferences depending on the dataset.
Bulletin de la Société Vaudoise des Sciences Naturelles
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Emergence of Context Characteristics Sensitivity in Large Language Models
Experiments on four models and three datasets show SFT increases sensitivity to easy contexts while later stages (DPO, RLVR) can reinforce or reverse those preferences depending on the dataset.