Self-Ask
Self-ask prompting has the model explicitly pose and answer follow-up sub-questions before answering a multi-hop question, a format that can plug a search engine in to answer each sub-question.
Description
Press et al. used it to study the compositionality gap, the tendency of models to answer each sub-question correctly yet fail the composed question.
Sources
- Press et al. (2022). Measuring and Narrowing the Compositionality Gap in Language Models.
Cite this entry
Protologue. (2026). Self-Ask. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0042). https://protologue.com/t/self-ask/
BibTeX
@misc{protologue_self_ask,
title = {Self-Ask},
author = {{Protologue}},
year = {2026},
howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.0.0},
note = {Entry PTL-0042},
url = {https://protologue.com/t/self-ask/}
}