{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T5HGAX4MEJ6YGHQIH5AYVJSILJ","short_pith_number":"pith:T5HGAX4M","schema_version":"1.0","canonical_sha256":"9f4e605f8c227d831e083f418aa6485a427aea20a6925a4cb2eb1e569920d3c5","source":{"kind":"arxiv","id":"2406.01252","version":3},"attestation_state":"computed","paper":{"title":"Towards Scalable Automated Alignment of LLMs: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.CL","authors_text":"Ben He, Bowen Yu, Boxi Cao, Hao Xiang, Hongyu Lin, Jiawei Chen, Keming Lu, Le Sun, Mengjie Ren, Peilin Liu, Xianpei Han, Xinyu Lu, Yaojie Lu","submitted_at":"2024-06-03T12:10:26Z","abstract_excerpt":"Alignment is the most critical step in building large language models (LLMs) that meet human needs. With the rapid development of LLMs gradually surpassing human capabilities, traditional alignment methods based on human-annotation are increasingly unable to meet the scalability demands. Therefore, there is an urgent need to explore new sources of automated alignment signals and technical approaches. In this paper, we systematically review the recently emerging methods of automated alignment, attempting to explore how to achieve effective, scalable, automated alignment once the capabilities of"},"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":"2406.01252","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-03T12:10:26Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"332a2ef589a111b3663a4c3b312a55f76eec84275d3f2983568df3b8b01939ce","abstract_canon_sha256":"60c677508a79aac16d8cc61abe6a13156f59ded99507ff6d617850b8b036288e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:02:20.688143Z","signature_b64":"qI6aTIEa28a6uapmflodmlYoDFJiQvqpJB+yKZ0zF4e/Gz5feE1cZLHmKD5d3yXPcVl8U3mKOETkSJeL4tLYBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f4e605f8c227d831e083f418aa6485a427aea20a6925a4cb2eb1e569920d3c5","last_reissued_at":"2026-07-05T09:02:20.687649Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:02:20.687649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Scalable Automated Alignment of LLMs: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.CL","authors_text":"Ben He, Bowen Yu, Boxi Cao, Hao Xiang, Hongyu Lin, Jiawei Chen, Keming Lu, Le Sun, Mengjie Ren, Peilin Liu, Xianpei Han, Xinyu Lu, Yaojie Lu","submitted_at":"2024-06-03T12:10:26Z","abstract_excerpt":"Alignment is the most critical step in building large language models (LLMs) that meet human needs. With the rapid development of LLMs gradually surpassing human capabilities, traditional alignment methods based on human-annotation are increasingly unable to meet the scalability demands. Therefore, there is an urgent need to explore new sources of automated alignment signals and technical approaches. In this paper, we systematically review the recently emerging methods of automated alignment, attempting to explore how to achieve effective, scalable, automated alignment once the capabilities of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01252","kind":"arxiv","version":3},"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/2406.01252/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":"2406.01252","created_at":"2026-07-05T09:02:20.687714+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01252v3","created_at":"2026-07-05T09:02:20.687714+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01252","created_at":"2026-07-05T09:02:20.687714+00:00"},{"alias_kind":"pith_short_12","alias_value":"T5HGAX4MEJ6Y","created_at":"2026-07-05T09:02:20.687714+00:00"},{"alias_kind":"pith_short_16","alias_value":"T5HGAX4MEJ6YGHQI","created_at":"2026-07-05T09:02:20.687714+00:00"},{"alias_kind":"pith_short_8","alias_value":"T5HGAX4M","created_at":"2026-07-05T09:02:20.687714+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05394","citing_title":"Weak-to-Strong Generalization via Direct On-Policy Distillation","ref_index":92,"is_internal_anchor":true},{"citing_arxiv_id":"2502.07027","citing_title":"Representational Alignment with Chemical Induced Fit for Molecular Relational Learning","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2412.15115","citing_title":"Qwen2.5 Technical Report","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2502.07027","citing_title":"Representational Alignment with Chemical Induced Fit for Molecular Relational Learning","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23543","citing_title":"Pref-CTRL: Preference Driven LLM Alignment using Representation Editing","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T5HGAX4MEJ6YGHQIH5AYVJSILJ","json":"https://pith.science/pith/T5HGAX4MEJ6YGHQIH5AYVJSILJ.json","graph_json":"https://pith.science/api/pith-number/T5HGAX4MEJ6YGHQIH5AYVJSILJ/graph.json","events_json":"https://pith.science/api/pith-number/T5HGAX4MEJ6YGHQIH5AYVJSILJ/events.json","paper":"https://pith.science/paper/T5HGAX4M"},"agent_actions":{"view_html":"https://pith.science/pith/T5HGAX4MEJ6YGHQIH5AYVJSILJ","download_json":"https://pith.science/pith/T5HGAX4MEJ6YGHQIH5AYVJSILJ.json","view_paper":"https://pith.science/paper/T5HGAX4M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01252&json=true","fetch_graph":"https://pith.science/api/pith-number/T5HGAX4MEJ6YGHQIH5AYVJSILJ/graph.json","fetch_events":"https://pith.science/api/pith-number/T5HGAX4MEJ6YGHQIH5AYVJSILJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T5HGAX4MEJ6YGHQIH5AYVJSILJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T5HGAX4MEJ6YGHQIH5AYVJSILJ/action/storage_attestation","attest_author":"https://pith.science/pith/T5HGAX4MEJ6YGHQIH5AYVJSILJ/action/author_attestation","sign_citation":"https://pith.science/pith/T5HGAX4MEJ6YGHQIH5AYVJSILJ/action/citation_signature","submit_replication":"https://pith.science/pith/T5HGAX4MEJ6YGHQIH5AYVJSILJ/action/replication_record"}},"created_at":"2026-07-05T09:02:20.687714+00:00","updated_at":"2026-07-05T09:02:20.687714+00:00"}