{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QG2SAPON27JVEYC43WF7D6FBVW","short_pith_number":"pith:QG2SAPON","schema_version":"1.0","canonical_sha256":"81b5203dcdd7d352605cdd8bf1f8a1adb638c84af569e52efa7c6342a98a1d36","source":{"kind":"arxiv","id":"2410.13339","version":2},"attestation_state":"computed","paper":{"title":"Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Byeongjeong Kim, Hwan Chang, Hwanhee Lee, Ingeol Baek, Jimin Lee","submitted_at":"2024-10-17T08:48:54Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) enhances language models by retrieving and incorporating relevant external knowledge. However, traditional retrieve-and-generate processes may not be optimized for real-world scenarios, where queries might require multiple retrieval steps or none at all. In this paper, we propose a Probing-RAG, which utilizes the hidden state representations from the intermediate layers of language models to adaptively determine the necessity of additional retrievals for a given query. By employing a pre-trained prober, Probing-RAG effectively captures the model's internal "},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.13339","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-17T08:48:54Z","cross_cats_sorted":[],"title_canon_sha256":"3d74f14d04562321d09a69d3c1e309aaf993d25682430edaf20d9177094a7354","abstract_canon_sha256":"16771fa379988565e282acc32e44a67d108d7092cec07f5cd5e6b1163e881956"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:04.944472Z","signature_b64":"He9IhcWqzeYaRvt+tVad4K2IwE9II4AK9hSUfN+3dvgIveE0nZzdWL9PPyqcHfL0HzgdxED64CHQhuu0F7L/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81b5203dcdd7d352605cdd8bf1f8a1adb638c84af569e52efa7c6342a98a1d36","last_reissued_at":"2026-07-05T10:21:04.943861Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:04.943861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Byeongjeong Kim, Hwan Chang, Hwanhee Lee, Ingeol Baek, Jimin Lee","submitted_at":"2024-10-17T08:48:54Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) enhances language models by retrieving and incorporating relevant external knowledge. However, traditional retrieve-and-generate processes may not be optimized for real-world scenarios, where queries might require multiple retrieval steps or none at all. In this paper, we propose a Probing-RAG, which utilizes the hidden state representations from the intermediate layers of language models to adaptively determine the necessity of additional retrievals for a given query. By employing a pre-trained prober, Probing-RAG effectively captures the model's internal "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13339","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.13339/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"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":"2410.13339","created_at":"2026-07-05T10:21:04.943942+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13339v2","created_at":"2026-07-05T10:21:04.943942+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13339","created_at":"2026-07-05T10:21:04.943942+00:00"},{"alias_kind":"pith_short_12","alias_value":"QG2SAPON27JV","created_at":"2026-07-05T10:21:04.943942+00:00"},{"alias_kind":"pith_short_16","alias_value":"QG2SAPON27JVEYC4","created_at":"2026-07-05T10:21:04.943942+00:00"},{"alias_kind":"pith_short_8","alias_value":"QG2SAPON","created_at":"2026-07-05T10:21:04.943942+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.17862","citing_title":"Retrieval Feedback Memory Enhancement Large Model Retrieval Generation Method","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QG2SAPON27JVEYC43WF7D6FBVW","json":"https://pith.science/pith/QG2SAPON27JVEYC43WF7D6FBVW.json","graph_json":"https://pith.science/api/pith-number/QG2SAPON27JVEYC43WF7D6FBVW/graph.json","events_json":"https://pith.science/api/pith-number/QG2SAPON27JVEYC43WF7D6FBVW/events.json","paper":"https://pith.science/paper/QG2SAPON"},"agent_actions":{"view_html":"https://pith.science/pith/QG2SAPON27JVEYC43WF7D6FBVW","download_json":"https://pith.science/pith/QG2SAPON27JVEYC43WF7D6FBVW.json","view_paper":"https://pith.science/paper/QG2SAPON","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13339&json=true","fetch_graph":"https://pith.science/api/pith-number/QG2SAPON27JVEYC43WF7D6FBVW/graph.json","fetch_events":"https://pith.science/api/pith-number/QG2SAPON27JVEYC43WF7D6FBVW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QG2SAPON27JVEYC43WF7D6FBVW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QG2SAPON27JVEYC43WF7D6FBVW/action/storage_attestation","attest_author":"https://pith.science/pith/QG2SAPON27JVEYC43WF7D6FBVW/action/author_attestation","sign_citation":"https://pith.science/pith/QG2SAPON27JVEYC43WF7D6FBVW/action/citation_signature","submit_replication":"https://pith.science/pith/QG2SAPON27JVEYC43WF7D6FBVW/action/replication_record"}},"created_at":"2026-07-05T10:21:04.943942+00:00","updated_at":"2026-07-05T10:21:04.943942+00:00"}