> ML_LITERATURE // WANG-2022-SELF-CONSISTENCY-CHAIN-OF-THOUGHT_v1.0
Self-Consistency Improves Chain of Thought Reasoning in Language Models
Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, Denny Zhou · International Conference on Learning Representations (ICLR) (2022)
algorithm2022industry-standardthirdPartyReproduced
Principal Contribution
Replaced greedy decoding in Chain-of-Thought with temperature sampling of diverse reasoning paths followed by majority-voting marginalization over final answers.
Operational Relevance
Directly guides architectural decisions, alignment strategy, and serving infrastructure for task-text-generation.
Assumptions
- Empirical distribution regularity holds and target domain adheres to pretraining linguistic/visual support
Limitations
- Resource scaling, inference memory requirements, and alignment robustness vary with model size and hardware topology
Connected Algorithms, Architectures & Tools
Related Algorithms:
Related Architectures:
Implementing Libraries: