{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/rankrag-unifying-context-ranking-with","title":"RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs","arxiv_id":"2407.02485","date":"2024-07-02","proceeding":null,"authors":["Yue Yu","Wei Ping","Zihan Liu","Boxin Wang","Jiaxuan You","Chao Zhang","Mohammad Shoeybi","Bryan Catanzaro"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2407.02485v1","url_pdf":"https://arxiv.org/pdf/2407.02485v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"answer-generation","task_name":"Answer Generation"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"rag","task_name":"RAG"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"retrieval-augmented-generation","task_name":"Retrieval-augmented Generation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bart","method_name":"BART"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"rag","method_name":"RAG"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-natural-questions","task":"Question Answering","dataset":"Natural Questions","model":"RankRAG-llama3-70b (Zero-Shot, KILT)","rank_in_archive_order":8,"of":47,"metrics":{"EM":"54.2"},"uses_additional_data":true},{"leaderboard":"/sota/question-answering-on-natural-questions","task":"Question Answering","dataset":"Natural Questions","model":"RankRAG-llama3-8b (Zero-Shot, KILT)","rank_in_archive_order":11,"of":47,"metrics":{"EM":"50.6"},"uses_additional_data":true},{"leaderboard":"/sota/question-answering-on-natural-questions","task":"Question Answering","dataset":"Natural Questions","model":"RankRAG-llama3-70b (Zero-Shot, DPR)","rank_in_archive_order":12,"of":47,"metrics":{"EM":"50.0"},"uses_additional_data":true},{"leaderboard":"/sota/question-answering-on-natural-questions","task":"Question Answering","dataset":"Natural Questions","model":"RankRAG-llama3-8b (Zero-Shot, DPR)","rank_in_archive_order":14,"of":47,"metrics":{"EM":"46.1"},"uses_additional_data":true},{"leaderboard":"/sota/question-answering-on-pubmedqa","task":"Question Answering","dataset":"PubMedQA","model":"RankRAG-llama3-70B (Zero-Shot)","rank_in_archive_order":3,"of":30,"metrics":{"Accuracy":"79.8"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-triviaqa","task":"Question Answering","dataset":"TriviaQA","model":"RankRAG-llama3-70b (Zero-Shot, KILT)","rank_in_archive_order":4,"of":56,"metrics":{"EM":"86.5"},"uses_additional_data":true},{"leaderboard":"/sota/question-answering-on-triviaqa","task":"Question Answering","dataset":"TriviaQA","model":"RankRAG-llama3-8b (Zero-Shot, KILT)","rank_in_archive_order":9,"of":56,"metrics":{"EM":"82.9"},"uses_additional_data":true},{"leaderboard":"/sota/question-answering-on-triviaqa","task":"Question Answering","dataset":"TriviaQA","model":"RankRAG-llama3-70b (Zero-Shot, DPR)","rank_in_archive_order":26,"of":56,"metrics":{"EM":"72.6"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.02485","atlas_url":"https://app.syntology.ai/?focus=2407.02485","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2407.02485"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2407.02485\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2407.02485"},"call":"get_concepts_for_paper(arxiv_id=\"2407.02485\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"140e8aa5588dcbb6d17df8d2a76a43e87bebebd7b59d4b070b944d6b67657a44","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}