CoRT：基於反事實重播的詞元級別評分標準引導策略優化

摘要

基於評分標準的強化學習透過根據明確標準評估模型輸出，來豐富語言模型的訓練。然而，在GRPO風格的流程中，這些結構化的評判被簡化為一個標量式的回應層級獎勵，並轉換為回應層級的優勢值，再均勻分配給所有生成的詞元。這使得即使不同評分標準對應到不同的文本區段、格式決策或語義選擇，回應內部仍缺乏明確的信用分配機制。我們提出CoRT，一種基於評分標準條件化GRPO的詞元層級信用加權方法。CoRT不訓練輔助性的詞元評分模型，而是透過反事實重播，在同一取樣回應上，分別根據原始評分標準條件化提示與匹配的無評分標準提示重新評分。由此產生的逐詞元對數似然對比，可作為對評分標準上下文依賴程度的代理指標。CoRT將這些對比映射為有界且經回應正規化的權重，並用其將帶正負號的GRPO優勢值重新分配至各詞元，過程中無需引入輔助評分器或改變回應層級的獎勵。在指令微調模型與不同獎勵粒度上的實驗顯示，CoRT在絕大多數比較中優於對應的回應層級GRPO，平均提升4.4個百分點。此方法在避免獨立學習相關性階段的同時，仍能與學習式詞元層級信用基準競爭。這些結果表明，策略內部的反事實對數似然對比能提供有效的訓練訊號，用於回應內部的信用分配，同時保留GRPO的簡潔性與穩定性。

English

Rubric-based reinforcement learning enriches language model training by evaluating model outputs against explicit criteria. Yet in GRPO-style pipelines, these structured judgments are reduced to a scalar response-level reward and converted into a response-level advantage, which is broadcast uniformly to all generated tokens. This leaves no explicit mechanism for allocating credit within a response, even when different criteria are grounded in different spans, formatting decisions, or semantic choices. We propose CoRT, a token-level credit weighting method for rubric-conditioned GRPO. Instead of training an auxiliary token scoring model, CoRT uses counterfactual replay to rescore the same sampled response under the original rubric-conditioned prompt and a matched criteria-free prompt. The resulting tokenwise log-likelihood contrasts serve as a proxy for dependence on the rubric context. CoRT maps these contrasts to bounded, response-normalized weights and uses them to redistribute the signed GRPO advantage across tokens, without introducing an auxiliary scorer or changing the response-level reward. Experiments across instruction-tuned models and reward granularities show that CoRT improves over matched response-level GRPO in the vast majority of comparisons, with an average gain of 4.4 percentage points. The method remains competitive with learned token-level credit baselines while avoiding a separate relevance-learning stage. These results suggest that policy-internal counterfactual likelihood contrasts provide an effective training signal for within-response credit allocation while retaining the simplicity and stability of GRPO.