# OLMo-2

On fact-checking claims with randomized poster profiles, the open Tülu-3 post-training recipe makes OLMo-2 32B and Tülu-3 70B judge claims from lower-status posters false more often, an effect under one percentage point but statistically reliable, exceeding training drift and replicating on independent claim sets; Meta's, Alibaba's and Mistral's recipes do not produce it. In OLMo-2 32B the model does not notice the job more but interprets it differently, with a lower-status job pushing the base model toward true and the post-trained model toward false, a flip carried by a single residual-stream direction at supervised fine-tuning. None of seven deployed commercial models doubts lower-status posters more.

On fact-checking claims with randomized poster profiles, the open Tülu-3 post-training recipe makes OLMo-2 32B and Tülu-3 70B judge claims from lower-status posters false more often, an effect under one percentage point but statistically reliable, exceeding training drift and replicating on independent claim sets; Meta's, Alibaba's and Mistral's recipes do not produce it. In OLMo-2 32B the model does not notice the job more but interprets it differently, with a lower-status job pushing the base model toward true and the post-trained model toward false, a flip carried by a single residual-stream direction at supervised fine-tuning. None of seven deployed commercial models doubts lower-status posters more.

Language models are often trained against a learned judge instead of the truth, but what that judge rewards could previously be seen only after training, from the policy's behavior. Three judges were trained from a 1B-parameter model on 500, 2,000 and 8,000 labeled answers, and a single-edit probe measured each judge's lift on wrong answers before any training. The probe predicted a climb onto flagged text against the weakest judge; after training, 115 of 128 final responses were one Sahara sentence ending "Answer: Africa", and the judge's mean score rose from 0.20 to 0.82. Against the strongest judge it predicted nothing climbable, and that run was not exploited.

Language models are often trained against a learned judge instead of the truth, but what that judge rewards could previously be seen only after training, from the policy's behavior. Three judges were trained from a 1B-parameter model on 500, 2,000 and 8,000 labeled answers, and a single-edit probe measured each judge's lift on wrong answers before any training. The probe predicted a climb onto flagged text against the weakest judge; after training, 115 of 128 final responses were one Sahara sentence ending "Answer: Africa", and the judge's mean score rose from 0.20 to 0.82. Against the strongest judge it predicted nothing climbable, and that run was not exploited.