让大模型自由推理后，仅约束输出结尾格式，效果更好。
Suffix-Constrained Greedy Search Algorithms for Causal Language Models
- 只约束生成结果末尾部分的格式，更灵活实用。
- 在多个数据集上保持甚至提升生成质量。
- 适合需要自由思考后输出固定格式的任务。
大语言模型（LLMs）已广泛应用于人机交互之外的领域。除了自由文本生成，受限生成也受到关注，即要求模型生成符合形式语法的输出。然而，这种设定对下游任务可能过于严格。例如，许多任务需模型先自由推理，再以特定格式输出最终回答。本文提出后缀受限生成（suffix-constrained generation），即仅对响应末尾施加语法约束，这是现有方法无法支持的场景。我们设计了几种基于贪婪搜索的后缀受限生成算法，并在多个数据集上进行实验，结果表明该方法能保证后缀约束，且不影响甚至提升了生成性能。
原文摘要 · Abstract (English)
Large language models (LLMs) are powerful tools that have found applications beyond human-machine interfaces and chatbots. Beside free-form generation, there has been an interest in constrained generation, a setting where LLMs are constrained to generate well-formed outputs with respect to the language defined by a formal grammar. Although appealing, this setting may be over restrictive for downstream applications. For example, many LLM tasks require the model to reason freely before generating its final response in a specific format. In this work, we introduce suffix-constrained generation, a constrained generation setting in which only the end of the response is constrained by a grammar, a scenario that is not supported by existing constrained generation methods. We introduce several suffix-constrained generation algorithms that are based on greedy search. We experiment on several datasets, and show that our approach allows to guarantee suffix constraints without having a negative impact on results, and even improving them in many settings.
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。