{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/improving-retrieval-augmented-large-language","title":"Improving Retrieval-Augmented Large Language Models via Data Importance Learning","arxiv_id":"2307.03027","date":"2023-07-06","proceeding":null,"authors":["Xiaozhong Lyu","Stefan Grafberger","Samantha Biegel","Shaopeng Wei","Meng Cao","Sebastian Schelter","Ce Zhang"],"abstract":"Retrieval augmentation enables large language models to take advantage of external knowledge, for example on tasks like question answering and data imputation. However, the performance of such retrieval-augmented models is limited by the data quality of their underlying retrieval corpus. In this paper, we propose an algorithm based on multilinear extension for evaluating the data importance of retrieved data points. There are exponentially many terms in the multilinear extension, and one key contribution of this paper is a polynomial time algorithm that computes exactly, given a retrieval-augmented model with an additive utility function and a validation set, the data importance of data points in the retrieval corpus using the multilinear extension of the model's utility function. We further proposed an even more efficient ({\\epsilon}, {\\delta})-approximation algorithm. Our experimental results illustrate that we can enhance the performance of large language models by only pruning or reweighting the retrieval corpus, without requiring further training. For some tasks, this even allows a small model (e.g., GPT-JT), augmented with a search engine API, to outperform GPT-3.5 (without retrieval augmentation). Moreover, we show that weights based on multilinear extension can be computed efficiently in practice (e.g., in less than ten minutes for a corpus with 100 million elements).","url_abs":"https://arxiv.org/abs/2307.03027v1","url_pdf":"https://arxiv.org/pdf/2307.03027v1.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":[{"paper_slug":"improving-retrieval-augmented-large-language","repo_url":"https://github.com/amsterdata/ragbooster","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"imputation","task_name":"Imputation"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"pruning","method_name":"Pruning"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.03027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.03027"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/amsterdata/ragbooster","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2,"unverified":4},"by_repo_kind":{"official":{"samples":6,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"67d72f0dfc265400","entry":"encode_retrievals","repo":"amsterdata/ragbooster","repo_kind":"official","path":"python/ragbooster/core.py","file_url":"https://github.com/amsterdata/ragbooster/blob/HEAD/python/ragbooster/core.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"67d72f0dfc265400"}},{"code_sha256_prefix":"50ace6dde459bae7","entry":"mode","repo":"amsterdata/ragbooster","repo_kind":"official","path":"python/ragbooster/core.py","file_url":"https://github.com/amsterdata/ragbooster/blob/HEAD/python/ragbooster/core.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"50ace6dde459bae7"}},{"code_sha256_prefix":"62e55338d1f854a2","entry":"evaluate_pruned","repo":"amsterdata/ragbooster","repo_kind":"official","path":"python/ragbooster/tuning.py","file_url":"https://github.com/amsterdata/ragbooster/blob/HEAD/python/ragbooster/tuning.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"62e55338d1f854a2"}},{"code_sha256_prefix":"0d10d24118a59673","entry":"evaluate_sample_pruned","repo":"amsterdata/ragbooster","repo_kind":"official","path":"python/ragbooster/tuning.py","file_url":"https://github.com/amsterdata/ragbooster/blob/HEAD/python/ragbooster/tuning.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0d10d24118a59673"}},{"code_sha256_prefix":"cfd204a25911c17c","entry":"score","repo":"amsterdata/ragbooster","repo_kind":"official","path":"python/ragbooster/core.py","file_url":"https://github.com/amsterdata/ragbooster/blob/HEAD/python/ragbooster/core.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cfd204a25911c17c"}},{"code_sha256_prefix":"bd66dab438dac1dd","entry":"tune_pruning_threshold","repo":"amsterdata/ragbooster","repo_kind":"official","path":"python/ragbooster/tuning.py","file_url":"https://github.com/amsterdata/ragbooster/blob/HEAD/python/ragbooster/tuning.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bd66dab438dac1dd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}