Practice — Training Reasoning Models: STaR, RLVR, and Reward Models (15 questions)

Your team is bootstrapping reasoning-trace training data for a model on a dataset of word problems where 70% are "easy" (the base model already gets these right most of the time when sampled) and 30% are "hard" (the base model almost never reaches the correct answer unassisted, even across many samples). Two options: (a) plain rejection-sampling fine-tuning (RFT) — sample many attempts per question, keep only ones with a verified-correct final answer; or (b) STaR with rationalization — same as (a), but for questions where no sampled attempt succeeds, show the model the correct answer and ask it to construct a plausible reasoning trace toward it.

1. Predict what happens to the training set's composition under plain RFT (option a) specifically for the hard 30%, and why.
2. Explain what rationalization changes about that outcome, and name the concrete risk it introduces that plain RFT does not have.
3. Would you use rationalized traces at the same weight/frequency in training as genuinely-discovered correct traces? Justify your answer.