Impact of LoRA Injection in Attention versus Feed-Forward Networks on Latency-Throughput Trade-offs in Llama-3.2-3B RAG Inference

Abstract

Abstract: We study quality-latency-resource trade-offs in a documentation-grounded retrieval-augmented generation (RAG) system that uses Low-Rank Adaptation (LoRA) of the generator. We build a manually verified benchmark of 5,144 question-answer pairs over the official Kubernetes documentation and combine it with a fixed hybrid-retrieval pipeline (BGE-M3 dense, BGE-M3 native sparse, Reciprocal Rank Fusion, cross-encoder reranking). Over this benchmark we ablate 20 LoRA configurations on Llama-3.2-3B-Instruct and Llama-3.1-8B-Instruct across rank and target-module choices, and evaluate each on token-leve

Research Question

What is the impact of injecting LoRA adapters exclusively into attention mechanisms versus feed-forward networks in Llama-3.2-3B on the latency-throughput trade-off during hybrid-retrieval RAG inference?

Verification Level

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

Truth-Engine Gate Verdict

This record has passed Gate 2: a Lean4 proof source type-checks, or a sealed-sandbox run reproduced the reported results within the stated tolerance. A reproducible artifact (proof source or repro script and results) is attached to this record. VERIFIED requires an attached reproducible artifact (Lean4 proof source, or repro script and results) before this status can be set; it is not derived from review score or claim count.

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