{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3PC66H3MJEEVBLJYC3VTVMHJRF","short_pith_number":"pith:3PC66H3M","schema_version":"1.0","canonical_sha256":"dbc5ef1f6c490950ad3816eb3ab0e9894fd3b008590382a7ae351c342f5cc606","source":{"kind":"arxiv","id":"2307.12966","version":1},"attestation_state":"computed","paper":{"title":"Aligning Large Language Models with Human: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fei Mi, Liangyou Li, Lifeng Shang, Qun Liu, Wanjun Zhong, Wenyong Huang, Xingshan Zeng, Xin Jiang, Yufei Wang","submitted_at":"2023-07-24T17:44:58Z","abstract_excerpt":"Large Language Models (LLMs) trained on extensive textual corpora have emerged as leading solutions for a broad array of Natural Language Processing (NLP) tasks. Despite their notable performance, these models are prone to certain limitations such as misunderstanding human instructions, generating potentially biased content, or factually incorrect (hallucinated) information. Hence, aligning LLMs with human expectations has become an active area of interest within the research community. This survey presents a comprehensive overview of these alignment technologies, including the following aspec"},"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":"2307.12966","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-24T17:44:58Z","cross_cats_sorted":[],"title_canon_sha256":"5ac795711df76a4250b84df6105212b81dd64526add5ddc5de6b9b1e69684183","abstract_canon_sha256":"2ce49dd4e03e7d9f66a9ef0560ebb2df51ac58792c9ef0ef29a5be2ccef8e6c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:34:00.743134Z","signature_b64":"DDzZLmhGdKkIA/mvE8ZRtqmJCcSJdi+CvJCghmLoIGLxwZsmdJJgH4QNz1Tg9Z0WPegJRld7XmmBjVcK0PBnDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbc5ef1f6c490950ad3816eb3ab0e9894fd3b008590382a7ae351c342f5cc606","last_reissued_at":"2026-07-05T06:34:00.742651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:34:00.742651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aligning Large Language Models with Human: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fei Mi, Liangyou Li, Lifeng Shang, Qun Liu, Wanjun Zhong, Wenyong Huang, Xingshan Zeng, Xin Jiang, Yufei Wang","submitted_at":"2023-07-24T17:44:58Z","abstract_excerpt":"Large Language Models (LLMs) trained on extensive textual corpora have emerged as leading solutions for a broad array of Natural Language Processing (NLP) tasks. Despite their notable performance, these models are prone to certain limitations such as misunderstanding human instructions, generating potentially biased content, or factually incorrect (hallucinated) information. Hence, aligning LLMs with human expectations has become an active area of interest within the research community. This survey presents a comprehensive overview of these alignment technologies, including the following aspec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12966","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/2307.12966/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":"2307.12966","created_at":"2026-07-05T06:34:00.742713+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.12966v1","created_at":"2026-07-05T06:34:00.742713+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12966","created_at":"2026-07-05T06:34:00.742713+00:00"},{"alias_kind":"pith_short_12","alias_value":"3PC66H3MJEEV","created_at":"2026-07-05T06:34:00.742713+00:00"},{"alias_kind":"pith_short_16","alias_value":"3PC66H3MJEEVBLJY","created_at":"2026-07-05T06:34:00.742713+00:00"},{"alias_kind":"pith_short_8","alias_value":"3PC66H3M","created_at":"2026-07-05T06:34:00.742713+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":27,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20258","citing_title":"Editorial Alignment: A Participatory Approach to Engaging Editorial Expertise in LLM-mediated Knowledge Dissemination","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01392","citing_title":"Multi-Objective Exploration and Preference Optimization via Mutual Information","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10078","citing_title":"Mult-DPO: Multinomial Direct Preference Optimization for Recommender Systems","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09068","citing_title":"Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09013","citing_title":"Beyond Averages: Evaluating LLMs on Human Survey Replication at the Distributional Level","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03376","citing_title":"P$^2$-DPO: Grounding Hallucination in Perceptual Processing via Calibration Direct Preference Optimization","ref_index":106,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28707","citing_title":"BV-Blend: Uncertainty-Weighted Historical Baselines for Stable Critic-Free RL with Verifiable Rewards","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30454","citing_title":"Collective cooperation without individual fidelity in LLM agents","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30323","citing_title":"In-Context Reward Adaptation for Robust Preference Modeling","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2309.10305","citing_title":"Baichuan 2: Open Large-scale Language Models","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18018","citing_title":"See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19228","citing_title":"Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2307.06435","citing_title":"A Comprehensive Overview of Large Language Models","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":268,"is_internal_anchor":false},{"citing_arxiv_id":"2509.15336","citing_title":"Knowledge-Driven Hallucination in Large Language Models: An Empirical Study on Process Modeling","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2510.04465","citing_title":"Autonomy Reshapes How Personalization Affects Privacy Concerns and Trust in LLM Agents","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2510.17881","citing_title":"POPI: Personalizing LLMs via Optimized Natural Language Preference Inference","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2402.13116","citing_title":"A Survey on Knowledge Distillation of Large Language Models","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15336","citing_title":"Facial-Expression-Aware Prompting for Empathetic LLM Tutoring","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2404.13501","citing_title":"A Survey on the Memory Mechanism of Large Language Model based Agents","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2308.11432","citing_title":"A Survey on Large Language Model based Autonomous Agents","ref_index":177,"is_internal_anchor":false},{"citing_arxiv_id":"2406.00515","citing_title":"A Survey on Large Language Models for Code Generation","ref_index":279,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25175","citing_title":"Indirect reciprocity beyond pairwise interactions","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01123","citing_title":"PERSA: Reinforcement Learning for Professor-Style Personalized Feedback with LLMs","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06987","citing_title":"Response Time Enhances Alignment with Heterogeneous Preferences","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3PC66H3MJEEVBLJYC3VTVMHJRF","json":"https://pith.science/pith/3PC66H3MJEEVBLJYC3VTVMHJRF.json","graph_json":"https://pith.science/api/pith-number/3PC66H3MJEEVBLJYC3VTVMHJRF/graph.json","events_json":"https://pith.science/api/pith-number/3PC66H3MJEEVBLJYC3VTVMHJRF/events.json","paper":"https://pith.science/paper/3PC66H3M"},"agent_actions":{"view_html":"https://pith.science/pith/3PC66H3MJEEVBLJYC3VTVMHJRF","download_json":"https://pith.science/pith/3PC66H3MJEEVBLJYC3VTVMHJRF.json","view_paper":"https://pith.science/paper/3PC66H3M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.12966&json=true","fetch_graph":"https://pith.science/api/pith-number/3PC66H3MJEEVBLJYC3VTVMHJRF/graph.json","fetch_events":"https://pith.science/api/pith-number/3PC66H3MJEEVBLJYC3VTVMHJRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3PC66H3MJEEVBLJYC3VTVMHJRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3PC66H3MJEEVBLJYC3VTVMHJRF/action/storage_attestation","attest_author":"https://pith.science/pith/3PC66H3MJEEVBLJYC3VTVMHJRF/action/author_attestation","sign_citation":"https://pith.science/pith/3PC66H3MJEEVBLJYC3VTVMHJRF/action/citation_signature","submit_replication":"https://pith.science/pith/3PC66H3MJEEVBLJYC3VTVMHJRF/action/replication_record"}},"created_at":"2026-07-05T06:34:00.742713+00:00","updated_at":"2026-07-05T06:34:00.742713+00:00"}