在推理阶段为候选生成、搜索、验证或优化分配额外的计算资源
Loading technique guide…
模式： 在推理时投入额外算力，通过多次尝试与验证提升性能
原因： 在复杂任务上提升准确率，实现灵活的算力分配，并在无需重训的情况下扩展性能
关键洞察： 在推理任务上，更多的推理时算力可以替代更大的模型或更多训练数据
通过这些精选资源加深理解
Self-Consistency Improves Chain of Thought Reasoning in Language Models (Wang et al., 2022)
Complexity-Based Prompting for Multi-Step Reasoning (Zhou et al., 2022)
Least-to-Most Prompting Enables Complex Reasoning (Zhou et al., 2022)
Universal Self-Consistency for Large Language Model Generation (Chen et al., 2023)
CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models (Wang et al., 2021)
Competition-Level Code Generation with AlphaCode (Li et al., 2022)
Code as Policies: Language Model Programs for Embodied Control (Liang et al., 2022)
Self-Debugging: Teaching Language Models to Debug Programs (Chen et al., 2023)