Papers › Lightweight Relevance Grader in RAG

Lightweight Relevance Grader in RAG

17 Jun 2025arXiv:2506.14084archive 2025-07-28

Taehee Jeong

Retrieval-Augmented Generation (RAG) addresses limitations of large language models (LLMs) by leveraging a vector database to provide more accurate and up-to-date information. When a user submits a query, RAG executes a vector search to find relevant documents, which are then used to generate a response. However, ensuring the relevance of retrieved documents with a query would be a big challenge. To address this, a secondary model, known as a relevant grader, can be served to verify its relevance. To reduce computational requirements of a relevant grader, a lightweight small language model is preferred. In this work, we finetuned llama-3.2-1b as a relevant grader and achieved a significant increase in precision from 0.1301 to 0.7750. Its precision is comparable to that of llama-3.1-70b. Our code is available at https://github.com/taeheej/Lightweight-Relevance-Grader-in-RAG.

Paper PDF Code

Code

taeheej/lightweight-relevance-grader-in-rag officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Language Modeling Language Modelling RAG Retrieval-augmented Generation Small Language Model

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Attention Dropout BART BERT BPE Dense Connections Dropout Layer Normalization Linear Warmup With Linear Decay RAG Softmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections