两篇新研究论文探讨了改进大型语言模型（LLM）输出的高级技术。第一篇论文《用于一致性DSL生成的元模型引导LLM解码》介绍了MeMoDecode框架，该框架旨在确保生成的领域特定语言（DSL）代码同时遵守具体和抽象语法规则，平均提高一致性23%。第二篇论文《稀疏强化学习松弛用于LLM推理》提出了SpaRLax方法，该方法使用具有自适应稀疏性的强化学习来增强思维链（Chain-of-Thought）推理，在九个基准测试中取得了最高的平均性能。 AI
影响 这些进步可能带来更可靠的代码生成和LLM更强大的推理能力。
排序理由 两篇arXiv论文详细介绍了改进LLM输出质量和推理的新颖方法。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2610.29749v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to generate software engineering artifacts written in domain-specific languages (DSLs). Correct DSL instances usually must comply with not only the concrete syntax but also the ab…
arXiv:2610.27220v1 Announce Type: new Abstract: Recent work has explored continuous representations in place of discrete tokens during Chain-of-Thought (CoT) reasoning, often referred to as soft CoT. This is motivated by the idea that a mixture of token embeddings can represent a…
Recent work has explored continuous representations in place of discrete tokens during Chain-of-Thought (CoT) reasoning, often referred to as soft CoT. This is motivated by the idea that a mixture of token embeddings can represent a superposition of multiple reasoning possibiliti…