Vendi-RAG Inference Efficiency Across Model Sizes and Noisy Retrieval Contexts

Abstract

Abstract: This report synthesises findings from 9 peer-reviewed papers addressing the following research question: How does the inference efficiency (measured in tokens per second) of Vendi-RAG with different model sizes (7B vs. 70B) vary when processing noisy retrieval contexts on TriviaQA and WebQuestions,. Retrieval-augmented generation (RAG) enhances large language models (LLMs) for domain-specific question-answering (QA) tasks by leveraging external knowledge sources. However, traditional RAG systems primarily focus on relevance-based retrieval and often struggle with. 8 claims were extracted from source literature; 2 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 5.2/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How does the inference efficiency (measured in tokens per second) of Vendi-RAG with different model sizes (7B vs. 70B) vary when processing noisy retrieval contexts on TriviaQA and WebQuestions, while maintaining a fixed retrieval accuracy threshold?

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