事後学習が言語モデルの言語化されたアルゴリズム計算に与える影響
How Post-Training Influences Verbalized Algorithmic Computation in Language Models
Olmo-3-7B-Instructの多桁加算タスクでSFT・DPO・RLVRの各チェックポイントを比較し、事後学習が内部状態の利用や言語化された推論(CoT)の有用性をどう変えるかを調べた論文。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Niall Dalton
分類: cs.CL, cs.LG
原文アブストラクト
Post-training improves language-model reasoning, but how it changes the use of internal information and verbalized chain of thought (CoT) remains unclear. We study successive SFT, DPO, and RLVR checkpoints of Olmo-3-7B-Instruct on multi-digit addition, using carry values as known intermediate state. Probes recover carry information from internal activations with similar accuracy in SFT and RLVR, although manipulating this information does not reliably control model outputs. In contrast, the usefulness of verbalized reasoning differs: CoTs produced by RLVR yield higher accuracy across receiving checkpoints than those produced by SFT or DPO. We also show that carry-related statements receive higher importance scores after RLVR than matched random controls. DPO shows similar sensitivity to carry-related statements but without comparable accuracy gains. These results suggest that post-training changes the usefulness of written reasoning and sensitivity to its content in meaningful ways, although greater sensitivity does not necessarily coincide with better problem performance.