{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X34UR2S3O7G56XPC3Y3VOOYZF5","short_pith_number":"pith:X34UR2S3","schema_version":"1.0","canonical_sha256":"bef948ea5b77cddf5de2de37573b192f563bc6ee0215ec250557d60228176eb9","source":{"kind":"arxiv","id":"2506.22852","version":1},"attestation_state":"computed","paper":{"title":"Knowledge Augmented Finetuning Matters in both RAG and Agent Based Dialog Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Junlan Feng, Yi Huang, Yucheng Cai, Yuxuan Wu, Zhijian Ou","submitted_at":"2025-06-28T11:26:31Z","abstract_excerpt":"Large language models (LLMs) have recently been applied to dialog systems. Despite making progress, LLMs are prone to errors in knowledge-intensive scenarios. Recently, approaches based on retrieval augmented generation (RAG) and agent have emerged to improve the factual accuracy by enhancing the LLMs with knowledge retrieved from external knowledge bases (KBs). This is mostly implemented by prompting the LLMs with instructions, examples and the retrieved knowledge. However, LLMs may have difficulty using the retrieved knowledge effectively for response generation, because they are not well tr"},"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":"2506.22852","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-28T11:26:31Z","cross_cats_sorted":[],"title_canon_sha256":"ec2f009de8d7245f8c418309cae3d87c29eca64943d5ee21b95c9dd26f9026c8","abstract_canon_sha256":"7f20334a22047f58d5b96dd58a24966fdf5b1e6f1b9a65256ca6c5bfd3e9ae32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:46.686346Z","signature_b64":"q3wyvUIdO4AFimectUo8aEP2MlW5TwlmYIG2sqzQ9BVZ19XTkYr13cqct3pX3oY+8K2H6Enl8sRyFtz/W3nuDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bef948ea5b77cddf5de2de37573b192f563bc6ee0215ec250557d60228176eb9","last_reissued_at":"2026-07-05T11:28:46.685852Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:46.685852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Augmented Finetuning Matters in both RAG and Agent Based Dialog Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Junlan Feng, Yi Huang, Yucheng Cai, Yuxuan Wu, Zhijian Ou","submitted_at":"2025-06-28T11:26:31Z","abstract_excerpt":"Large language models (LLMs) have recently been applied to dialog systems. Despite making progress, LLMs are prone to errors in knowledge-intensive scenarios. Recently, approaches based on retrieval augmented generation (RAG) and agent have emerged to improve the factual accuracy by enhancing the LLMs with knowledge retrieved from external knowledge bases (KBs). This is mostly implemented by prompting the LLMs with instructions, examples and the retrieved knowledge. However, LLMs may have difficulty using the retrieved knowledge effectively for response generation, because they are not well tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22852","kind":"arxiv","version":1},"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/2506.22852/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":"2506.22852","created_at":"2026-07-05T11:28:46.685921+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.22852v1","created_at":"2026-07-05T11:28:46.685921+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22852","created_at":"2026-07-05T11:28:46.685921+00:00"},{"alias_kind":"pith_short_12","alias_value":"X34UR2S3O7G5","created_at":"2026-07-05T11:28:46.685921+00:00"},{"alias_kind":"pith_short_16","alias_value":"X34UR2S3O7G56XPC","created_at":"2026-07-05T11:28:46.685921+00:00"},{"alias_kind":"pith_short_8","alias_value":"X34UR2S3","created_at":"2026-07-05T11:28:46.685921+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X34UR2S3O7G56XPC3Y3VOOYZF5","json":"https://pith.science/pith/X34UR2S3O7G56XPC3Y3VOOYZF5.json","graph_json":"https://pith.science/api/pith-number/X34UR2S3O7G56XPC3Y3VOOYZF5/graph.json","events_json":"https://pith.science/api/pith-number/X34UR2S3O7G56XPC3Y3VOOYZF5/events.json","paper":"https://pith.science/paper/X34UR2S3"},"agent_actions":{"view_html":"https://pith.science/pith/X34UR2S3O7G56XPC3Y3VOOYZF5","download_json":"https://pith.science/pith/X34UR2S3O7G56XPC3Y3VOOYZF5.json","view_paper":"https://pith.science/paper/X34UR2S3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.22852&json=true","fetch_graph":"https://pith.science/api/pith-number/X34UR2S3O7G56XPC3Y3VOOYZF5/graph.json","fetch_events":"https://pith.science/api/pith-number/X34UR2S3O7G56XPC3Y3VOOYZF5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X34UR2S3O7G56XPC3Y3VOOYZF5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X34UR2S3O7G56XPC3Y3VOOYZF5/action/storage_attestation","attest_author":"https://pith.science/pith/X34UR2S3O7G56XPC3Y3VOOYZF5/action/author_attestation","sign_citation":"https://pith.science/pith/X34UR2S3O7G56XPC3Y3VOOYZF5/action/citation_signature","submit_replication":"https://pith.science/pith/X34UR2S3O7G56XPC3Y3VOOYZF5/action/replication_record"}},"created_at":"2026-07-05T11:28:46.685921+00:00","updated_at":"2026-07-05T11:28:46.685921+00:00"}