Universal Self-Consistency
Universal self-consistency extends self-consistency to free-form outputs by asking the model itself to select the most consistent response among several samples, instead of counting exact-match answers.
Description
This makes sampling-and-selecting usable for tasks such as summarization and open-ended question answering, where answers rarely match word for word.
Sources
- Chen et al. (2023). Universal Self-Consistency for Large Language Model Generation.
Cite this entry
Protologue. (2026). Universal Self-Consistency. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0029). https://protologue.com/t/universal-self-consistency/
BibTeX
@misc{protologue_universal_self_consistency,
title = {Universal Self-Consistency},
author = {{Protologue}},
year = {2026},
howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.0.0},
note = {Entry PTL-0029},
url = {https://protologue.com/t/universal-self-consistency/}
}