用小模型修正大模型输出，让AI更听话地按格式答题。
DICE: Structured Reasoning in LLMs through SLM-Guided Chain-of-Thought Correction
- 用小模型分析大模型的思考过程，再按要求改写输出。
- 格式准确率提升35.4%，内容正确率提升29.4%。
- 适合需要精准输出格式的场景，如表格生成、结构化回答。
在执行需满足用户特定要求的推理任务时，大型语言模型（LLMs）常忽视详细指令而优先追求推理逻辑。由于微调成本高且参数不可控，直接优化LLM不现实。为此，我们提出DICE框架，通过小型语言模型（SLMs）引导链式思维（CoT）修正，实现对LLM输出的结构化优化。该框架先以两阶段方法构建结构化CoT适配数据集，再采用双微调策略训练SLMs，使其以‘分析-回答’模式生成符合规范的输出。实验表明，DICE使LLM输出的平均格式准确率和内容正确率分别提升35.4%和29.4%，优于现有主流基线，达到当前最优性能。
原文摘要 · Abstract (English)
When performing reasoning tasks with user-specific requirements, such as strict output formats, large language models (LLMs) often prioritize reasoning over adherence to detailed instructions. Fine-tuning LLMs on supervised datasets to address this is impractical due to high computational costs and limited parameter access. To tackle this, we propose DICE, a lightweight framework that guides small language models (SLMs) to refine LLMs' outputs through chain-of-thought (CoT) correction. DICE decouples the process by first prompting LLMs to generate natural language responses, then using trained SLMs to analyze and refine these outputs to meet structured output specifications. This framework preserves LLMs' broad knowledge and reasoning capabilities while ensuring the outputs conform to user demands. Specifically, DICE first constructs structured CoT adaptation datasets via a two-stage method and subsequently applies a dual-tuning strategy to fine-tune SLMs for generating structured outputs in an analyze-then-answer pattern. Experiments demonstrate that DICE improves the average format accuracy and content correctness of LLM outputs by 35.4\% and 29.4\%, respectively, achieving state-of-the-art (SOTA) performance over other competitive baselines.
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。