这篇论文提出CALMRec框架，通过分离记忆和因果校正解决推荐系统的反馈循环，在三个场景提升长期价值6-7%，做推荐系统的值得看看。
CALMRec使用冻结多模态语言模型将用户物品内容和反馈转换为证据基础语义原子，并维护短期、长期和暴露三种记忆。通过倾向性加权更新减少策略引起的暴露偏差，保守离线批评者重新排序候选以优化延迟满足。在电商类、新闻类和短视频类三个环境中，CALMRec相比最强基线将折扣长期价值分别提升6.1%、7.6%和6.7%。二十种子消融实验显示，缺失倾向性校正或保守支持正则化后价值显著下降（0.739±0.191和0.523±0.234）。冻结指令语言模型在语义原子NDCG上比TF-IDF提升超过一倍。
CALMRec: Causally Aligned Language Memory for Long-Horizon Recommendation
Large language models (LLMs) can summarize heterogeneous user evidence in natural language, but current LLM recommenders often collapse enduring preferences, transient intent, and exposure-induced behavior into one profile. This makes recommendation vulnerable to feedback loops: repeated exposure is mistaken for preference, immediate clicks dominate delayed satisfaction, and fluent explanations need not reflect the ranking decision. We propose our method, a model-agnostic framework for long-horizon recommendation. Our method uses a frozen multimodal language model to convert item content and feedback into evidence-grounded semantic atoms, then maintains separate short-term, long-term, and exposure memories. Propensity-weighted updates reduce policy-induced exposure bias, while a conservative offline critic reranks candidates for delayed satisfaction under a behavior-support constraint. Explanations use only influential evidence atoms and are checked by counterfactual deletion. We provide an identification result and evaluate the framework in e-commerce-like, news-like, and short-video-like environments. Across ten seeds, our method improves discounted long-term value over the strongest alternative by 6.1%, 7.6%, and 6.7%, respectively. Twenty-seed paired ablations show significant value drops after removing propensity correction (0.739 +/- 0.191) or conservative support regularization (0.523 +/- 0.234). A frozen instruction language model also more than doubles semantic-atom NDCG over TF-IDF on a held-out paraphrase benchmark.