论文精选

Constitutional Midtraining:中期插入宪法内容可提升模型对齐

Constitutional Midtraining: Content Presence Drives Alignment Gains

精选理由

Anthropic提出了在模型训练中期加入宪法性内容来提升对齐持久性,在blackmail任务上降了17.5pp,而且不牺牲MMLU等能力,值得搞对齐的人看看。

AI 摘要

研究在120B参数规模上测试了宪法中期训练(constitutional midtraining),使用394M token的宪法语料库(基于Anthropic's Constitution)进行2x2因子设计(curriculum ordering × deliberative reasoning)。与仅回放的对照组相比,宪法中期训练的模型在对齐泛化和持久性上表现更好,尤其在blackmail测试中降低了17.5pp,且优势在良性微调后依然存在。该优势不适用于需要主动抵抗上下文压力的场景,且在SFT后减弱。宪法中期训练对MMLU、ARC-Easy、piqa、GSM8K等能力指标无平均损失。

原文 · arXiv: Anthropic

Constitutional Midtraining: Content Presence Drives Alignment Gains

Post-training alignment is often shallow, eroding under fine-tuning. Whether midtraining interventions, cleanly isolated from post-training, can produce durable alignment remains untested. We test this via constitutional midtraining: inserting principled, values-based content into midtraining against a replay-only control at 120B scale. Our 394M-token constitutional corpus, built from Anthropic's Constitution, uses a 2x2 factorial design (curriculum ordering x deliberative reasoning) to produce four constitutionally midtrained conditions plus a control, evaluated on self-generated and established benchmarks including alignment under pressure, value conflict resolution, blackmail, and emergent misalignment across three stages: post-midtraining, post-SFT, and post-benign fine-tuning. Constitutionally midtrained models outperform the control on alignment generalization and durability, notably on blackmail: SFT instills a blackmail propensity in all models, but constitutional midtraining blunts it, with the advantage surviving benign fine-tuning (-17.5pp). This durability does not extend to settings requiring active resistance to in-context pressure or conflict, where the advantage attenuates after SFT. The presence of constitutional content at midtraining also matters more than its structure, and constitutional midtraining incurs no cost, on average, on the capabilities we test (MMLU, ARC-Easy, piqa, GSM8K) at any stage. A modest amount of constitutional content at midtraining could therefore yield broad, persistent alignment gains, offering a cheap, complementary addition to SFT-centered pipelines. Code, data, and models are available.