根据用户反馈差异，精准调整大模型行为，提升持续学习效果。
Different Feedback, Different Updates: Selective Self-Learning from User Interactions for Large Language Models
- 将反馈拆解为任务修复、条件优化、无效三类，分层处理。
- 在多任务测试中，内存与真实反馈数据集表现优于基线。
- 适合需要精细化迭代的对话系统与个性化模型优化场景。
用户反馈为大语言模型的持续改进提供了自然监督信号，但单条反馈可能蕴含多种不同泛化范围的行为调整需求。本文提出SLIFT，一种基于任务相对视角的可选自学习框架。SLIFT将每条反馈分解为原子成分，并相对于原始任务划分为：修正（Fix）——任务有效性要求；特定条件优化（Spec）——兼容的条件细化；无有效更新方向（Null）。为在适当范围内整合变化，SLIFT在共享冻结主干上训练两个互补的LoRA适配器：通用型适配器通过反馈条件自蒸馏，将修复需求归纳为默认行为；专用型适配器仅观察任务和通用响应，提供未满足的特定条件优化的残差指导。无效成分不引发正向更新。在多个主干模型上，SLIFT在MemoryBench和WildFB基准上均取得优异性能，目标分析进一步揭示其内在机制。代码已开源。
原文摘要 · Abstract (English)
User feedback offers natural supervision for persistent LLM improvement, but a single message may support multiple behavioral changes with different scopes of generalization. We introduce SLIFT, a selective self-learning framework built on a task-relative view of user feedback. SLIFT decomposes each feedback message into atomic components and interprets each component relative to the original task as Fix, Spec, or Null: requirements for task validity, compatible condition-specific refinements, or content with no reliable positive update direction. To incorporate each change at the appropriate scope, SLIFT trains two complementary LoRA adapters on a shared frozen backbone: a Generalist that consolidates Fix requirements into default behavior through feedback-conditioned self-distillation, and a Specialist that observes only the task and Generalist response to supply residual guidance for applicable, unmet Spec refinements. Null components induce no positive update. Across backbones, SLIFT achieves strong performance on both MemoryBench and WildFB, with targeted analyses further examining its underlying mechanisms. We release our code at https://anonymous.4open.science/r/SLIFT.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。