4 papers · 1 filter
Does Chain-of-Thought Reliance Follow a Scaling Law?Larger Models Follow Their Steps More, Independent of Post-Training
Esther Xin
Monitoring a model's chain of thought (CoT) is useful for safety only if the final answer depends on the written steps. Prior measurements use natural tasks where true reasoning is…
What Should We Remove? Evaluating the Reliability and Costs of RLVR Data Decontamination
Esther Xin
Reinforcement learning with verifiable rewards (RLVR) math corpora are routinely screened for benchmark overlap, but the reliability and data-loss costs of cleaning policies remain…
When a Data Artifact Isn't a Shortcut: Causal Auditing of Synthetic RLVR Corpora
Esther Xin
Several recent pipelines build RLVR training data by masking a span of real corpus text and asking a language model to invent plausible wrong answers around it. The correct option…
Where the Verifier Fails: A Category-Level Audit of Reward Signals in RLVR
Esther Xin
Reinforcement learning with verifiable rewards (RLVR) and standard benchmark evaluation both rely on an automatic verifier that turns a free text answer into a binary reward. Prior…