{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OP7NZ2ACN22NIYGCPQJPBFBLVV","short_pith_number":"pith:OP7NZ2AC","schema_version":"1.0","canonical_sha256":"73fedce8026eb4d460c27c12f0942bad63883cfdab4e86bee989afcabbc23e65","source":{"kind":"arxiv","id":"2305.00955","version":2},"attestation_state":"computed","paper":{"title":"Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Amanda Bertsch, Aman Madaan, Andr\\'e F. T. Martins, Ant\\'onio Farinhas, Emmy Liu, Graham Neubig, Jos\\'e G. C. de Souza, Patrick Fernandes, Pedro Henrique Martins, Shuyan Zhou, Tongshuang Wu","submitted_at":"2023-05-01T17:36:06Z","abstract_excerpt":"Many recent advances in natural language generation have been fueled by training large language models on internet-scale data. However, this paradigm can lead to models that generate toxic, inaccurate, and unhelpful content, and automatic evaluation metrics often fail to identify these behaviors. As models become more capable, human feedback is an invaluable signal for evaluating and improving models. This survey aims to provide an overview of the recent research that has leveraged human feedback to improve natural language generation. First, we introduce an encompassing formalization of feedb"},"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":"2305.00955","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-01T17:36:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c9635db8e79cc680c8a2b719df22d2642407c4867c0b43bc1638150527bc821c","abstract_canon_sha256":"b4a7a5fde37c8f17a3bfa8667728ab6b9d34470dcf84db97532ee74d861903cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:18.228524Z","signature_b64":"EzAyMnWG3zHn0AS3pJo8B0xE8gOFXYYx+nAvxrJEVXJET5Kwgh4+tnannYfx30LZq1pywmlmlAbLPsfJjuzICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73fedce8026eb4d460c27c12f0942bad63883cfdab4e86bee989afcabbc23e65","last_reissued_at":"2026-07-05T06:16:18.227999Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:18.227999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Amanda Bertsch, Aman Madaan, Andr\\'e F. T. Martins, Ant\\'onio Farinhas, Emmy Liu, Graham Neubig, Jos\\'e G. C. de Souza, Patrick Fernandes, Pedro Henrique Martins, Shuyan Zhou, Tongshuang Wu","submitted_at":"2023-05-01T17:36:06Z","abstract_excerpt":"Many recent advances in natural language generation have been fueled by training large language models on internet-scale data. However, this paradigm can lead to models that generate toxic, inaccurate, and unhelpful content, and automatic evaluation metrics often fail to identify these behaviors. As models become more capable, human feedback is an invaluable signal for evaluating and improving models. This survey aims to provide an overview of the recent research that has leveraged human feedback to improve natural language generation. First, we introduce an encompassing formalization of feedb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.00955","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/2305.00955/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":"2305.00955","created_at":"2026-07-05T06:16:18.228071+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.00955v2","created_at":"2026-07-05T06:16:18.228071+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.00955","created_at":"2026-07-05T06:16:18.228071+00:00"},{"alias_kind":"pith_short_12","alias_value":"OP7NZ2ACN22N","created_at":"2026-07-05T06:16:18.228071+00:00"},{"alias_kind":"pith_short_16","alias_value":"OP7NZ2ACN22NIYGC","created_at":"2026-07-05T06:16:18.228071+00:00"},{"alias_kind":"pith_short_8","alias_value":"OP7NZ2AC","created_at":"2026-07-05T06:16:18.228071+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2309.01219","citing_title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OP7NZ2ACN22NIYGCPQJPBFBLVV","json":"https://pith.science/pith/OP7NZ2ACN22NIYGCPQJPBFBLVV.json","graph_json":"https://pith.science/api/pith-number/OP7NZ2ACN22NIYGCPQJPBFBLVV/graph.json","events_json":"https://pith.science/api/pith-number/OP7NZ2ACN22NIYGCPQJPBFBLVV/events.json","paper":"https://pith.science/paper/OP7NZ2AC"},"agent_actions":{"view_html":"https://pith.science/pith/OP7NZ2ACN22NIYGCPQJPBFBLVV","download_json":"https://pith.science/pith/OP7NZ2ACN22NIYGCPQJPBFBLVV.json","view_paper":"https://pith.science/paper/OP7NZ2AC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.00955&json=true","fetch_graph":"https://pith.science/api/pith-number/OP7NZ2ACN22NIYGCPQJPBFBLVV/graph.json","fetch_events":"https://pith.science/api/pith-number/OP7NZ2ACN22NIYGCPQJPBFBLVV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OP7NZ2ACN22NIYGCPQJPBFBLVV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OP7NZ2ACN22NIYGCPQJPBFBLVV/action/storage_attestation","attest_author":"https://pith.science/pith/OP7NZ2ACN22NIYGCPQJPBFBLVV/action/author_attestation","sign_citation":"https://pith.science/pith/OP7NZ2ACN22NIYGCPQJPBFBLVV/action/citation_signature","submit_replication":"https://pith.science/pith/OP7NZ2ACN22NIYGCPQJPBFBLVV/action/replication_record"}},"created_at":"2026-07-05T06:16:18.228071+00:00","updated_at":"2026-07-05T06:16:18.228071+00:00"}