AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

qa-FLoRA: Data-free query-adaptive Fusion of LoRAs for LLMs

Shreya Shukla, Aditya Sriram, Milinda Kuppur Narayanaswamy, Hiteshi Jain

AAAI 2026 · Large language models › Instruction and fine-tuning · approach: Low-rank adaptation variants · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace static equal-weight fusion with qa-FLoRALoRA fusion · Average across 3 domainsscore: 20.4 -> 25.8 (LLaMA-2); 38.5 -> 44.2 (LLaMA-3)Improved
replace centroid similarity with KL-divergence weightsLoRA fusion · Average across 3 domainsscore: 18.8 -> 25.8 (LLaMA-2); 34.4 -> 44.2 (LLaMA-3)Improved
compute KL on last token rather than averaging all query tokens (ablation)qa-FLoRA · Average across 3 domainsscore: 23.5 -> 25.8Improved
qa-FLoRA vs centroid on codeLoRA fusion · HumanEval compositepass@1: 18.8 -> 17.7 (LLaMA-2); 33.3 -> 34.4 (LLaMA-3)No clear effect
qa-FLoRA vs supervised LoRAFlowLoRA fusion · Average across 3 domainsscore: 30.9 -> 25.8 (LLaMA-2); 46.1 -> 44.2 (LLaMA-3)Hurt
qa-FLoRA vs static fusion on code (LLaMA-2)LoRA fusion · HumanEval compositepass@1: 17.7 -> 17.7No clear effect
qa-FLoRA vs LoRAHubLoRA fusion · Average across 3 domains (LLaMA-2)score: 26.4 -> 25.8Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy