{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CGKE6JJU743TLXOEPNUDLKJD5Q","short_pith_number":"pith:CGKE6JJU","schema_version":"1.0","canonical_sha256":"11944f2534ff3735ddc47b6835a923ec1e362573d333890e141c531d27eb4797","source":{"kind":"arxiv","id":"2401.00625","version":4},"attestation_state":"computed","paper":{"title":"Beyond Efficiency: A Systematic Survey of Resource-Efficient Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carl Yang, Chen Ling, Guangji Bai, Jiaying Lu, Liang Zhao, Mengdan Zhu, Nan Zhang, Shiyu Wang, Tingwei Shi, Xinyuan Song, Yifei Zhang, Yue Cheng, Zheng Chai, Ziyang Yu","submitted_at":"2024-01-01T01:12:42Z","abstract_excerpt":"The burgeoning field of Large Language Models (LLMs), exemplified by sophisticated models like OpenAI's ChatGPT, represents a significant advancement in artificial intelligence. These models, however, bring forth substantial challenges in the high consumption of computational, memory, energy, and financial resources, especially in environments with limited resource capabilities. This survey aims to systematically address these challenges by reviewing a broad spectrum of techniques designed to enhance the resource efficiency of LLMs. We categorize methods based on their optimization focus: comp"},"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":"2401.00625","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-01T01:12:42Z","cross_cats_sorted":[],"title_canon_sha256":"b9c65efc173beab86eab21ef41df90baaad3733143d86fa6269656e6010557de","abstract_canon_sha256":"56a516fdf2723f707f8249694ca73ea5622cdb8ab27b5417d6f383d3ed3a8f88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:07.751408Z","signature_b64":"VfTIBKZvUwBG1RddmbWHuhjow+YkqvlAovZ5hyhGsuZ03ZFCd3B3IE7TK/BRaOQivbRq/6g9zptqEXRXeMoTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11944f2534ff3735ddc47b6835a923ec1e362573d333890e141c531d27eb4797","last_reissued_at":"2026-07-05T09:55:07.750907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:07.750907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Efficiency: A Systematic Survey of Resource-Efficient Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carl Yang, Chen Ling, Guangji Bai, Jiaying Lu, Liang Zhao, Mengdan Zhu, Nan Zhang, Shiyu Wang, Tingwei Shi, Xinyuan Song, Yifei Zhang, Yue Cheng, Zheng Chai, Ziyang Yu","submitted_at":"2024-01-01T01:12:42Z","abstract_excerpt":"The burgeoning field of Large Language Models (LLMs), exemplified by sophisticated models like OpenAI's ChatGPT, represents a significant advancement in artificial intelligence. These models, however, bring forth substantial challenges in the high consumption of computational, memory, energy, and financial resources, especially in environments with limited resource capabilities. This survey aims to systematically address these challenges by reviewing a broad spectrum of techniques designed to enhance the resource efficiency of LLMs. We categorize methods based on their optimization focus: comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00625","kind":"arxiv","version":4},"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/2401.00625/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":"2401.00625","created_at":"2026-07-05T09:55:07.750966+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.00625v4","created_at":"2026-07-05T09:55:07.750966+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00625","created_at":"2026-07-05T09:55:07.750966+00:00"},{"alias_kind":"pith_short_12","alias_value":"CGKE6JJU743T","created_at":"2026-07-05T09:55:07.750966+00:00"},{"alias_kind":"pith_short_16","alias_value":"CGKE6JJU743TLXOE","created_at":"2026-07-05T09:55:07.750966+00:00"},{"alias_kind":"pith_short_8","alias_value":"CGKE6JJU","created_at":"2026-07-05T09:55:07.750966+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10706","citing_title":"Unifying Data, Memory, and Compute Efficiency in LLM training: A Survey","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08565","citing_title":"EinSort: Sorting is All We Need for Tensorizing LLM","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04349","citing_title":"MorphoQuant: Modality-Aware Quantization for Omni-modal Large Language Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28438","citing_title":"When AI Reviews Its Own Code: Recursive Self-Training Collapse in Code LLMs","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25098","citing_title":"Revisiting the Effectiveness of LLM Pruning for Test-Time Scaling","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2408.12935","citing_title":"AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2503.10666","citing_title":"Green Prompting: Characterizing Prompt-driven Energy Costs of LLM Inference","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15461","citing_title":"DrugSAGE:Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery","ref_index":6,"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":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25098","citing_title":"Revisiting the Effectiveness of LLM Pruning for Test-Time Scaling","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22906","citing_title":"Network Edge Inference for Large Language Models: Principles, Techniques, and Opportunities","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09048","citing_title":"Watt Counts: Energy-Aware Benchmark for Sustainable LLM Inference on Heterogeneous GPU Architectures","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21072","citing_title":"Distributed Generative Inference of LLM at Internet Scales with Multi-Dimensional Communication Optimization","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CGKE6JJU743TLXOEPNUDLKJD5Q","json":"https://pith.science/pith/CGKE6JJU743TLXOEPNUDLKJD5Q.json","graph_json":"https://pith.science/api/pith-number/CGKE6JJU743TLXOEPNUDLKJD5Q/graph.json","events_json":"https://pith.science/api/pith-number/CGKE6JJU743TLXOEPNUDLKJD5Q/events.json","paper":"https://pith.science/paper/CGKE6JJU"},"agent_actions":{"view_html":"https://pith.science/pith/CGKE6JJU743TLXOEPNUDLKJD5Q","download_json":"https://pith.science/pith/CGKE6JJU743TLXOEPNUDLKJD5Q.json","view_paper":"https://pith.science/paper/CGKE6JJU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.00625&json=true","fetch_graph":"https://pith.science/api/pith-number/CGKE6JJU743TLXOEPNUDLKJD5Q/graph.json","fetch_events":"https://pith.science/api/pith-number/CGKE6JJU743TLXOEPNUDLKJD5Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CGKE6JJU743TLXOEPNUDLKJD5Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CGKE6JJU743TLXOEPNUDLKJD5Q/action/storage_attestation","attest_author":"https://pith.science/pith/CGKE6JJU743TLXOEPNUDLKJD5Q/action/author_attestation","sign_citation":"https://pith.science/pith/CGKE6JJU743TLXOEPNUDLKJD5Q/action/citation_signature","submit_replication":"https://pith.science/pith/CGKE6JJU743TLXOEPNUDLKJD5Q/action/replication_record"}},"created_at":"2026-07-05T09:55:07.750966+00:00","updated_at":"2026-07-05T09:55:07.750966+00:00"}