To what extent does the marginal accuracy improvement of extending context windows from 32K to 128K tokens in

Abstract

Abstract: Retrieval-Augmented Generation (RAG) has quickly grown into a pivotal paradigm in the development of Large Language Models (LLMs). Although existing research mainly emphasizes accuracy and efficiency, the trustworthiness of RAG systems remains insufficiently explored. RAG can improve LLM reliability by grounding responses in external and up-to-date knowledge, reducing hallucinations. However, unreliable retrieval or improper knowledge utilization may still lead to undesirable outputs. To address these concerns, we propose a unified framework, Trust-RAG Compass, that assesses the trustworthines

Research Question

To what extent does the marginal accuracy improvement of extending context windows from 32K to 128K tokens in RAG-based multi-hop reasoning on HotPotQA saturate after 3 retrieval steps, and how does this saturation differ between 7B and 70B parameter LLMs when controlling for retrieval precision?

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