Does GPT-4's multi-hop reasoning accuracy on HotpotQA degrade monotonically with increasing retrieval steps (2

Abstract

Abstract: Few-shot prompting is a surprisingly powerful way to use Large Language Models (LLMs) to solve various tasks. However, this approach struggles as the task complexity increases or when the individual reasoning steps of the task themselves are hard to learn, especially when embedded in more complex tasks. To address this, we propose Decomposed Prompting, a new approach to solve complex tasks by decomposing them (via prompting) into simpler sub-tasks that can be delegated to a library of prompting-based LLMs dedicated to these sub-tasks. This modular structure allows each prompt to be optimized f

Research Question

Does GPT-4's multi-hop reasoning accuracy on HotpotQA degrade monotonically with increasing retrieval steps (2 vs 5) under controlled context length, and how does the accuracy-throughput trade-off compare against a single-step retrieval with wider context window?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance