AI训练新招：用“如果没这条规则”来给每个词打分
训练大模型时，我们常给一堆规则（比如“回答要简洁”“引用要准确”），但现有方法只给整段回答一个总分，无法区分哪个词做对了、哪个词跑偏了。这篇论文提出一个巧妙的替代方案：让模型自己对比“有规则”和“没规则”两种情况下生成同一句话的概率差异——如果某个词在有规则时更可能被选，那它就是在执行这条规则。研究者用这个差值给每个词分配权重，再调整训练信号，在多个模型上平均提升4.4个百分点。它不是你明天能用上的，但指向一个趋势：AI训练正从“给整篇打分”走向“给每个词打分”，而且不需要额外训练一个打分模型。
📄 原文摘要(英文)
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.