用3个例子实现高效参数化学习，让模型从自然语言中快速吸收知识。
SIEVE: Sample-Efficient Parametric Learning from Natural Language
- 通过分解上下文生成高质量合成数据，只使用相关部分提升效果。
- 仅需3个示例即超越已有方法，在推理任务中表现更优。
- 适合需要快速适应新领域或缺乏标注数据的场景。
自然语言上下文（如指令、知识或反馈）蕴含丰富信号，可用于适配语言模型。尽管上下文学习可通过提示实现适应，但参数化学习能持久作用于模型权重并进一步提升性能，却往往数据需求大，且高度依赖高质量轨迹或自动验证器。本文提出SIEVE，一种从自然语言上下文中实现样本高效参数化学习的方法，仅需三个查询示例即可生效。SIEVE采用创新的合成数据生成流程SIEVE-GEN，基于上下文可分解的洞察：将合成查询与仅相关的上下文配对，生成更高质量的推理轨迹，并通过上下文蒸馏将信息内化至模型。我们在需上下文的推理任务中评估，包括定制领域、RuleArena及《一本书中的机器翻译》任务。结果表明，仅用三个示例，SIEVE即优于先前上下文蒸馏方法，展示了如何实现从自然语言中高效参数化学习。
原文摘要 · Abstract (English)
Natural language context-such as instructions, knowledge, or feedback-contains rich signal for adapting language models. While in-context learning provides adaptation via the prompt, parametric learning persists into model weights and can improve performance further, though is data hungry and heavily relies on either high-quality traces or automated verifiers. We propose SIEVE, a method for sample-efficient parametric learning from natural language context that requires as few as three query examples. SIEVE uses a novel synthetic data generation pipeline, SIEVE-GEN, that leverages the insight that context is decomposable. Decomposing context allows us to generate higher quality rollouts by pairing synthetic queries with only the applicable context rather than the entirety, then using context distillation to internalize context into the model. We evaluate in reasoning settings where context is necessary, including custom domains and the RuleArena and Machine Translation from One Book tasks. Our results show that SIEVE outperforms prior context distillation methods using just three query examples, demonstrating how to achieve sample-efficient parametric learning from natural language.
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。