{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TOWXDDJWQSC2EPTIXWHQYSZV5P","short_pith_number":"pith:TOWXDDJW","schema_version":"1.0","canonical_sha256":"9bad718d368485a23e68bd8f0c4b35ebf7fe612a69c5579e3ba4838f495dc45e","source":{"kind":"arxiv","id":"2002.08909","version":1},"attestation_state":"computed","paper":{"title":"REALM: Retrieval-Augmented Language Model Pre-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Language models pre-trained with an integrated retriever over a document corpus outperform prior methods on open-domain question answering by 4 to 16 percent.","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Kelvin Guu, Kenton Lee, Ming-Wei Chang, Panupong Pasupat, Zora Tung","submitted_at":"2020-02-10T18:40:59Z","abstract_excerpt":"Language model pre-training has been shown to capture a surprising amount of world knowledge, crucial for NLP tasks such as question answering. However, this knowledge is stored implicitly in the parameters of a neural network, requiring ever-larger networks to cover more facts.\n  To capture knowledge in a more modular and interpretable way, we augment language model pre-training with a latent knowledge retriever, which allows the model to retrieve and attend over documents from a large corpus such as Wikipedia, used during pre-training, fine-tuning and inference. For the first time, we show h"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2002.08909","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-10T18:40:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4cc1d8fa32eb3843fc491ea769947edd01955ffa807b5f78126a614095724e51","abstract_canon_sha256":"a232dfc972dce5d964abce327735d56ef564c47b6287fe4dc0ed536c127173cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:52.830061Z","signature_b64":"QyWzjAl+tc7l6pvFXoGlXs8eGo/gUbsVDYcY0kkKMf4yaMDEdzt2R2xuMgj2uW+w4JHd5hG9pcx14jEuYcnODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bad718d368485a23e68bd8f0c4b35ebf7fe612a69c5579e3ba4838f495dc45e","last_reissued_at":"2026-05-17T23:38:52.829438Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:52.829438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"REALM: Retrieval-Augmented Language Model Pre-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Language models pre-trained with an integrated retriever over a document corpus outperform prior methods on open-domain question answering by 4 to 16 percent.","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Kelvin Guu, Kenton Lee, Ming-Wei Chang, Panupong Pasupat, Zora Tung","submitted_at":"2020-02-10T18:40:59Z","abstract_excerpt":"Language model pre-training has been shown to capture a surprising amount of world knowledge, crucial for NLP tasks such as question answering. However, this knowledge is stored implicitly in the parameters of a neural network, requiring ever-larger networks to cover more facts.\n  To capture knowledge in a more modular and interpretable way, we augment language model pre-training with a latent knowledge retriever, which allows the model to retrieve and attend over documents from a large corpus such as Wikipedia, used during pre-training, fine-tuning and inference. For the first time, we show h"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We demonstrate the effectiveness of Retrieval-Augmented Language Model pre-training (REALM) by fine-tuning on the challenging task of Open-domain Question Answering (Open-QA). We compare against state-of-the-art models for both explicit and implicit knowledge storage on three popular Open-QA benchmarks, and find that we outperform all previous methods by a significant margin (4-16% absolute accuracy).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That back-propagation through a retrieval step over millions of documents is numerically stable and provides a useful unsupervised learning signal for the retriever parameters.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"REALM augments language-model pre-training with an unsupervised retriever over Wikipedia documents and reports 4-16% absolute gains on open-domain QA benchmarks over prior implicit and explicit knowledge methods.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Language models pre-trained with an integrated retriever over a document corpus outperform prior methods on open-domain question answering by 4 to 16 percent.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"fd05d3e400545758fdf5d7a79da9bff47de60a2fdeaaa7ce976fb7785f375b58"},"source":{"id":"2002.08909","kind":"arxiv","version":1},"verdict":{"id":"0496c68e-e097-4692-837a-27d9f626107a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T09:52:42.388463Z","strongest_claim":"We demonstrate the effectiveness of Retrieval-Augmented Language Model pre-training (REALM) by fine-tuning on the challenging task of Open-domain Question Answering (Open-QA). We compare against state-of-the-art models for both explicit and implicit knowledge storage on three popular Open-QA benchmarks, and find that we outperform all previous methods by a significant margin (4-16% absolute accuracy).","one_line_summary":"REALM augments language-model pre-training with an unsupervised retriever over Wikipedia documents and reports 4-16% absolute gains on open-domain QA benchmarks over prior implicit and explicit knowledge methods.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That back-propagation through a retrieval step over millions of documents is numerically stable and provides a useful unsupervised learning signal for the retriever parameters.","pith_extraction_headline":"Language models pre-trained with an integrated retriever over a document corpus outperform prior methods on open-domain question answering by 4 to 16 percent."},"references":{"count":20,"sample":[{"doi":"","year":1911,"title":"arXiv preprint arXiv:1911.10470 , year=","work_id":"bba0e5b4-dccd-4c07-86fb-2dae46efdce9","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Neural Machine Translation by Jointly Learning to Align and Translate","work_id":"d831e763-d530-4029-a65c-ac595d82cb2a","ref_index":2,"cited_arxiv_id":"1409.0473","is_internal_anchor":true},{"doi":"","year":2013,"title":"Semantic parsing on freebase from question-answer pairs","work_id":"55a52a96-0321-4fc0-a8f5-eccec466bc2d","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","work_id":"ed240a10-5b19-406c-baa5-30803f465785","ref_index":4,"cited_arxiv_id":"1810.04805","is_internal_anchor":true},{"doi":"","year":null,"title":"Neural Turing Machines","work_id":"0a5ce53c-9670-42b9-8be5-386de7eed50c","ref_index":5,"cited_arxiv_id":"1410.5401","is_internal_anchor":true}],"resolved_work":20,"snapshot_sha256":"217ebf269247a333e779ed5dbbf87e45e2bf0a2c4d5f6cbb1950fc955a6166ce","internal_anchors":11},"formal_canon":{"evidence_count":3,"snapshot_sha256":"921de4a55a8393b7609ce9eec082d809fbe45062a568b445ccd3f0a7c006572d"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2002.08909","created_at":"2026-05-17T23:38:52.829538+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.08909v1","created_at":"2026-05-17T23:38:52.829538+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.08909","created_at":"2026-05-17T23:38:52.829538+00:00"},{"alias_kind":"pith_short_12","alias_value":"TOWXDDJWQSC2","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"TOWXDDJWQSC2EPTI","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"TOWXDDJW","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":29,"internal_anchor_count":29,"sample":[{"citing_arxiv_id":"2110.01552","citing_title":"Perhaps PTLMs Should Go to School -- A Task to Assess Open Book and Closed Book QA","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2408.12935","citing_title":"AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions","ref_index":283,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22203","citing_title":"Evaluation of Chunking Strategies for Effective Text Embedding in Low-Resource Language on Agricultural Documents","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16347","citing_title":"HPC-LLM: Practical Domain Adaptation and Retrieval-Augmented Generation for HPC Support","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2502.03387","citing_title":"LIMO: Less is More for Reasoning","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2208.03299","citing_title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","ref_index":194,"is_internal_anchor":true},{"citing_arxiv_id":"2309.16671","citing_title":"Demystifying CLIP Data","ref_index":100,"is_internal_anchor":true},{"citing_arxiv_id":"2004.04906","citing_title":"Dense Passage Retrieval for Open-Domain Question Answering","ref_index":78,"is_internal_anchor":true},{"citing_arxiv_id":"2201.10005","citing_title":"Text and Code Embeddings by Contrastive Pre-Training","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2401.18059","citing_title":"RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2002.08910","citing_title":"How Much Knowledge Can You Pack Into the Parameters of a Language Model?","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12813","citing_title":"REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations","ref_index":122,"is_internal_anchor":true},{"citing_arxiv_id":"2604.01348","citing_title":"Procedural Knowledge at Scale Improves Reasoning","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2101.03961","citing_title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2202.08906","citing_title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","ref_index":75,"is_internal_anchor":true},{"citing_arxiv_id":"2112.09118","citing_title":"Unsupervised Dense Information Retrieval with Contrastive Learning","ref_index":134,"is_internal_anchor":true},{"citing_arxiv_id":"2201.08239","citing_title":"LaMDA: Language Models for Dialog Applications","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2305.14325","citing_title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24334","citing_title":"Reducing Redundancy in Retrieval-Augmented Generation through Chunk Filtering","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22261","citing_title":"Bridging the Long-Tail Gap: Robust Retrieval-Augmented Relation Completion via Multi-Stage Paraphrase Infusion","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2310.03714","citing_title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05287","citing_title":"Securing the Agent: Vendor-Neutral, Multitenant Enterprise Retrieval and Tool Use","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2206.07682","citing_title":"Emergent Abilities of Large Language Models","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07274","citing_title":"A Systematic Study of Retrieval Pipeline Design for Retrieval-Augmented Medical Question Answering","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2005.11401","citing_title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":3,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TOWXDDJWQSC2EPTIXWHQYSZV5P","json":"https://pith.science/pith/TOWXDDJWQSC2EPTIXWHQYSZV5P.json","graph_json":"https://pith.science/api/pith-number/TOWXDDJWQSC2EPTIXWHQYSZV5P/graph.json","events_json":"https://pith.science/api/pith-number/TOWXDDJWQSC2EPTIXWHQYSZV5P/events.json","paper":"https://pith.science/paper/TOWXDDJW"},"agent_actions":{"view_html":"https://pith.science/pith/TOWXDDJWQSC2EPTIXWHQYSZV5P","download_json":"https://pith.science/pith/TOWXDDJWQSC2EPTIXWHQYSZV5P.json","view_paper":"https://pith.science/paper/TOWXDDJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.08909&json=true","fetch_graph":"https://pith.science/api/pith-number/TOWXDDJWQSC2EPTIXWHQYSZV5P/graph.json","fetch_events":"https://pith.science/api/pith-number/TOWXDDJWQSC2EPTIXWHQYSZV5P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TOWXDDJWQSC2EPTIXWHQYSZV5P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TOWXDDJWQSC2EPTIXWHQYSZV5P/action/storage_attestation","attest_author":"https://pith.science/pith/TOWXDDJWQSC2EPTIXWHQYSZV5P/action/author_attestation","sign_citation":"https://pith.science/pith/TOWXDDJWQSC2EPTIXWHQYSZV5P/action/citation_signature","submit_replication":"https://pith.science/pith/TOWXDDJWQSC2EPTIXWHQYSZV5P/action/replication_record"}},"created_at":"2026-05-17T23:38:52.829538+00:00","updated_at":"2026-05-17T23:38:52.829538+00:00"}