{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ODXWRQYNXKOR3ZX6FVYSFXZLUC","short_pith_number":"pith:ODXWRQYN","schema_version":"1.0","canonical_sha256":"70ef68c30dba9d1de6fe2d7122df2ba0b9441751d771fab7e32eafc994127e60","source":{"kind":"arxiv","id":"2402.13116","version":4},"attestation_state":"computed","paper":{"title":"A Survey on Knowledge Distillation of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Knowledge distillation transfers advanced capabilities from proprietary LLMs like GPT-4 to open-source models such as LLaMA and Mistral.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Can Xu, Chongyang Tao, Dacheng Tao, Jinyang Li, Ming Li, Reynold Cheng, Tao Shen, Tianyi Zhou, Xiaohan Xu","submitted_at":"2024-02-20T16:17:37Z","abstract_excerpt":"In the era of Large Language Models (LLMs), Knowledge Distillation (KD) emerges as a pivotal methodology for transferring advanced capabilities from leading proprietary LLMs, such as GPT-4, to their open-source counterparts like LLaMA and Mistral. Additionally, as open-source LLMs flourish, KD plays a crucial role in both compressing these models, and facilitating their self-improvement by employing themselves as teachers. This paper presents a comprehensive survey of KD's role within the realm of LLM, highlighting its critical function in imparting advanced knowledge to smaller models and its"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2402.13116","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T16:17:37Z","cross_cats_sorted":[],"title_canon_sha256":"12f954505e87a6800491342b9b9738cfea9318a753e579e6b7d8f80c95b99e9c","abstract_canon_sha256":"d3883b76b02e2cc11bb101e4b4b99096c4653e9dddd62c8cc77bd4da17007bbb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:37:42.481483Z","signature_b64":"wEcu2611nmi9Jfj0Tt7tMsbDgTH8hYmgJh+500Gp/LqzmqRVgrfwOnLL45qpeEHs8KlKFzRLd+v4hmBjChEADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70ef68c30dba9d1de6fe2d7122df2ba0b9441751d771fab7e32eafc994127e60","last_reissued_at":"2026-05-17T23:37:42.480803Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:37:42.480803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Knowledge Distillation of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Knowledge distillation transfers advanced capabilities from proprietary LLMs like GPT-4 to open-source models such as LLaMA and Mistral.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Can Xu, Chongyang Tao, Dacheng Tao, Jinyang Li, Ming Li, Reynold Cheng, Tao Shen, Tianyi Zhou, Xiaohan Xu","submitted_at":"2024-02-20T16:17:37Z","abstract_excerpt":"In the era of Large Language Models (LLMs), Knowledge Distillation (KD) emerges as a pivotal methodology for transferring advanced capabilities from leading proprietary LLMs, such as GPT-4, to their open-source counterparts like LLaMA and Mistral. Additionally, as open-source LLMs flourish, KD plays a crucial role in both compressing these models, and facilitating their self-improvement by employing themselves as teachers. This paper presents a comprehensive survey of KD's role within the realm of LLM, highlighting its critical function in imparting advanced knowledge to smaller models and its"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"KD emerges as a pivotal methodology for transferring advanced capabilities from leading proprietary LLMs, such as GPT-4, to their open-source counterparts like LLaMA and Mistral, while also enabling model compression and self-improvement.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That data augmentation within the KD framework can reliably enable open-source models to approximate the contextual adeptness, ethical alignment, and deep semantic insights of proprietary models.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A comprehensive survey of knowledge distillation for LLMs structured around algorithms, skill enhancement, and vertical applications, highlighting data augmentation as a key enabler.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Knowledge distillation transfers advanced capabilities from proprietary LLMs like GPT-4 to open-source models such as LLaMA and Mistral.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e3b88ff0303c0d4d2e95c70c9ed3150d2102ed0863b08d9400bc05dadafabdf4"},"source":{"id":"2402.13116","kind":"arxiv","version":4},"verdict":{"id":"c8c748e0-8724-479c-9fec-65c18e1c3267","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T23:27:17.705659Z","strongest_claim":"KD emerges as a pivotal methodology for transferring advanced capabilities from leading proprietary LLMs, such as GPT-4, to their open-source counterparts like LLaMA and Mistral, while also enabling model compression and self-improvement.","one_line_summary":"A comprehensive survey of knowledge distillation for LLMs structured around algorithms, skill enhancement, and vertical applications, highlighting data augmentation as a key enabler.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That data augmentation within the KD framework can reliably enable open-source models to approximate the contextual adeptness, ethical alignment, and deep semantic insights of proprietary models.","pith_extraction_headline":"Knowledge distillation transfers advanced capabilities from proprietary LLMs like GPT-4 to open-source models such as LLaMA and Mistral."},"references":{"count":300,"sample":[{"doi":"","year":null,"title":"Advances in Neural Information Processing Systems , volume=","work_id":"c2cc414b-17c6-4006-b389-f3ec0bf8141b","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"arXiv preprint arXiv:2304.14233 , year=","work_id":"6ee50a7d-801e-4444-93a9-5496cce785bd","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"arXiv preprint arXiv:2305.07402 , year=","work_id":"5ead8756-3597-48cb-afe3-a2ec06e20dbf","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"arXiv preprint arXiv:2212.10192 , year=","work_id":"e82d7266-b4ea-4926-b70c-0833cea400f0","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"The Eleventh International Conference on Learning Representations , year=","work_id":"49c26f65-5708-4074-91fa-3703224fe0a9","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":300,"snapshot_sha256":"e603a99c43e130929671350775832f5916ccf292fb130c9e311d07ebe0688d0f","internal_anchors":25},"formal_canon":{"evidence_count":3,"snapshot_sha256":"daf0e6e47c588826aa57be3413278158443d5742bee93599f2d5c63c4dc5478e"},"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":"2402.13116","created_at":"2026-05-17T23:37:42.480891+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.13116v4","created_at":"2026-05-17T23:37:42.480891+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13116","created_at":"2026-05-17T23:37:42.480891+00:00"},{"alias_kind":"pith_short_12","alias_value":"ODXWRQYNXKOR","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"ODXWRQYNXKOR3ZX6","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"ODXWRQYN","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":22,"sample":[{"citing_arxiv_id":"2510.18471","citing_title":"CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2502.21074","citing_title":"CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation","ref_index":130,"is_internal_anchor":true},{"citing_arxiv_id":"2601.20375","citing_title":"LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02753","citing_title":"DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12652","citing_title":"Multi-Rollout On-Policy Distillation via Peer Successes and Failures","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06387","citing_title":"Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02753","citing_title":"DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03841","citing_title":"Training a Student Expert via Semi-Supervised Foundation Model Distillation","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11290","citing_title":"ReAD: Reinforcement-Guided Capability Distillation for Large Language Models","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08873","citing_title":"CoDistill-GRPO: A Co-Distillation Recipe for Efficient Group Relative Policy Optimization","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08568","citing_title":"Different Prompts, Different Ranks: Prompt-aware Dynamic Rank Selection for SVD-based LLM Compression","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25110","citing_title":"Knowledge Distillation Must Account for What It Loses","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25110","citing_title":"Knowledge Distillation Must Account for What It Loses","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06597","citing_title":"UniSD: Towards a Unified Self-Distillation Framework for Large Language Models","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05893","citing_title":"Logic-Regularized Verifier Elicits Reasoning from LLMs","ref_index":91,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06387","citing_title":"Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06387","citing_title":"Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07725","citing_title":"SOD: Step-wise On-policy Distillation for Small Language Model Agents","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07783","citing_title":"Chain-based Distillation for Effective Initialization of Variable-Sized Small Language Models","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07711","citing_title":"SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07941","citing_title":"Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19144","citing_title":"ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine Translation","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":3,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ODXWRQYNXKOR3ZX6FVYSFXZLUC","json":"https://pith.science/pith/ODXWRQYNXKOR3ZX6FVYSFXZLUC.json","graph_json":"https://pith.science/api/pith-number/ODXWRQYNXKOR3ZX6FVYSFXZLUC/graph.json","events_json":"https://pith.science/api/pith-number/ODXWRQYNXKOR3ZX6FVYSFXZLUC/events.json","paper":"https://pith.science/paper/ODXWRQYN"},"agent_actions":{"view_html":"https://pith.science/pith/ODXWRQYNXKOR3ZX6FVYSFXZLUC","download_json":"https://pith.science/pith/ODXWRQYNXKOR3ZX6FVYSFXZLUC.json","view_paper":"https://pith.science/paper/ODXWRQYN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.13116&json=true","fetch_graph":"https://pith.science/api/pith-number/ODXWRQYNXKOR3ZX6FVYSFXZLUC/graph.json","fetch_events":"https://pith.science/api/pith-number/ODXWRQYNXKOR3ZX6FVYSFXZLUC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ODXWRQYNXKOR3ZX6FVYSFXZLUC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ODXWRQYNXKOR3ZX6FVYSFXZLUC/action/storage_attestation","attest_author":"https://pith.science/pith/ODXWRQYNXKOR3ZX6FVYSFXZLUC/action/author_attestation","sign_citation":"https://pith.science/pith/ODXWRQYNXKOR3ZX6FVYSFXZLUC/action/citation_signature","submit_replication":"https://pith.science/pith/ODXWRQYNXKOR3ZX6FVYSFXZLUC/action/replication_record"}},"created_at":"2026-05-17T23:37:42.480891+00:00","updated_at":"2026-05-17T23:37:42.480891+00:00"}