Papers › RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs
RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs
Yue Yu, Wei Ping, Zihan Liu, Boxin Wang, Jiaxuan You, Chao Zhang, Mohammad Shoeybi, Bryan Catanzaro
Large language models (LLMs) typically utilize the top-k contexts from a retriever in retrieval-augmented generation (RAG). In this work, we propose a novel instruction fine-tuning framework RankRAG, which instruction-tunes a single LLM for the dual purpose of context ranking and answer generation in RAG. In particular, the instruction-tuned LLMs work surprisingly well by adding a small fraction of ranking data into the training blend, and outperform existing expert ranking models, including the same LLM exclusively fine-tuned on a large amount of ranking data. For generation, we compare our model with many strong baselines, including GPT-4-0613, GPT-4-turbo-2024-0409, and ChatQA-1.5, an open-sourced model with the state-of-the-art performance on RAG benchmarks. Specifically, our Llama3-RankRAG significantly outperforms Llama3-ChatQA-1.5 and GPT-4 models on nine knowledge-intensive benchmarks. In addition, it also performs comparably to GPT-4 on five RAG benchmarks in the biomedical domain without instruction fine-tuning on biomedical data, demonstrating its superb capability for generalization to new domains.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Question Answering | Natural Questions | RankRAG-llama3-70b (Zero-Shot, KILT) | EM | 54.2 | #8 of 47 | Archive leaderboard | report |
| Question Answering | Natural Questions | RankRAG-llama3-8b (Zero-Shot, KILT) | EM | 50.6 | #11 of 47 | Archive leaderboard | report |
| Question Answering | Natural Questions | RankRAG-llama3-70b (Zero-Shot, DPR) | EM | 50.0 | #12 of 47 | Archive leaderboard | report |
| Question Answering | Natural Questions | RankRAG-llama3-8b (Zero-Shot, DPR) | EM | 46.1 | #14 of 47 | Archive leaderboard | report |
| Question Answering | PubMedQA | RankRAG-llama3-70B (Zero-Shot) | Accuracy | 79.8 | #3 of 30 | Archive leaderboard | report |
| Question Answering | TriviaQA | RankRAG-llama3-70b (Zero-Shot, KILT) | EM | 86.5 | #4 of 56 | Archive leaderboard | report |
| Question Answering | TriviaQA | RankRAG-llama3-8b (Zero-Shot, KILT) | EM | 82.9 | #9 of 56 | Archive leaderboard | report |
| Question Answering | TriviaQA | RankRAG-llama3-70b (Zero-Shot, DPR) | EM | 72.6 | #26 of 56 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
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