List your company

Reward Model Transfer on RAIL

4.62AOGANCHOR
-0.18481.06262.313.5574May 25, 2026

Evaluation results

MethodLinks
ANCHORTransfer Pair=Llama-3.2-1B-Instruct -> Llama-3.1-8B-Instruct, Source Domain=PKU, Evaluation Setting=Zero-shot transfer2026.054.62——4.62
NaiveTransfer Pair=Llama-3.2-1B-Instruct -> Llama-3.1-8B-Instruct, Source Domain=PKU, Evaluation Setting=Zero-shot transfer2026.052.26——2.26
NaiveTransfer Pair=Qwen3-1.7B -> Qwen3-8B, Source Domain=PKU, Evaluation Setting=Zero-shot transfer2026.051.85——1.85
ANCHORTransfer Pair=Qwen3-1.7B -> Qwen3-8B, Source Domain=PKU, Evaluation Setting=Zero-shot transfer2026.051.85——1.85
ANCHORTransfer Pair=Qwen3-1.7B -> Qwen3-8B, Source Domain=AHar, Evaluation Setting=Zero-shot transfer2026.051.65——1.65
NaiveTransfer Pair=Qwen3-1.7B -> Qwen3-8B, Source Domain=AHar, Evaluation Setting=Zero-shot transfer2026.050.52——0.52
ANCHORTransfer Pair=Llama-3.2-1B-Instruct -> Llama-3.1-8B-Instruct, Source Domain=AHar, Evaluation Setting=Zero-shot transfer2026.050.31——0.31
NaiveTransfer Pair=Llama-3.2-1B-Instruct -> Llama-3.1-8B-Instruct, Source Domain=AHar, Evaluation Setting=Zero-shot transfer2026.050——0
ANCHORTransfer Pair=Llama-3.2-1B-Instruct -> Llama-3.1-8B-Instruct, Source Domain=RAIL, Evaluation Setting=In-distribution2026.05—77.81.44—
ANCHORTransfer Pair=Qwen3-1.7B -> Qwen3-8B, Source Domain=RAIL, Evaluation Setting=In-distribution2026.05—00—
NaiveTransfer Pair=Llama-3.2-1B-Instruct -> Llama-3.1-8B-Instruct, Source Domain=RAIL, Evaluation Setting=In-distribution2026.05—55.71.03—
NaiveTransfer Pair=Qwen3-1.7B -> Qwen3-8B, Source Domain=RAIL, Evaluation Setting=In-distribution2026.05—-19.1-0.51—