{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SIYMK2U54JVKOYFNY54KB6QFNS","short_pith_number":"pith:SIYMK2U5","schema_version":"1.0","canonical_sha256":"9230c56a9de26aa760adc778a0fa056c9d36cc70b642dabc57cd5e3d744a9840","source":{"kind":"arxiv","id":"2407.04118","version":1},"attestation_state":"computed","paper":{"title":"MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bang Liu, Dayiheng Liu, Ge Fan, Wei Wu, Yanghua Xiao, Yuyan Chen, Zhengyu Chen, Zhihao Wen, Zhixu Li","submitted_at":"2024-07-04T18:39:59Z","abstract_excerpt":"Prompt engineering, as an efficient and effective way to leverage Large Language Models (LLM), has drawn a lot of attention from the research community. The existing research primarily emphasizes the importance of adapting prompts to specific tasks, rather than specific LLMs. However, a good prompt is not solely defined by its wording, but also binds to the nature of the LLM in question. In this work, we first quantitatively demonstrate that different prompts should be adapted to different LLMs to enhance their capabilities across various downstream tasks in NLP. Then we novelly propose a mode"},"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":"2407.04118","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-04T18:39:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ce40946117f17fe23f385d70bb66eb0859b46b87852b5371f0fe9674eb8308a3","abstract_canon_sha256":"75e33ac7042378feafc0968227e6b11c04c4b4ed2fe85ba1aef57077e207b3f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:28.973979Z","signature_b64":"MjLfoSbowZHbYYqh3ZQHPZbRxEujx0f7F46ZsrWVjNUY2PXBkTconnLuwmxvpMReu6ox5g/NKdpBHsp8N/HlBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9230c56a9de26aa760adc778a0fa056c9d36cc70b642dabc57cd5e3d744a9840","last_reissued_at":"2026-07-05T08:40:28.973511Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:28.973511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bang Liu, Dayiheng Liu, Ge Fan, Wei Wu, Yanghua Xiao, Yuyan Chen, Zhengyu Chen, Zhihao Wen, Zhixu Li","submitted_at":"2024-07-04T18:39:59Z","abstract_excerpt":"Prompt engineering, as an efficient and effective way to leverage Large Language Models (LLM), has drawn a lot of attention from the research community. The existing research primarily emphasizes the importance of adapting prompts to specific tasks, rather than specific LLMs. However, a good prompt is not solely defined by its wording, but also binds to the nature of the LLM in question. In this work, we first quantitatively demonstrate that different prompts should be adapted to different LLMs to enhance their capabilities across various downstream tasks in NLP. Then we novelly propose a mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04118","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/2407.04118/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":"2407.04118","created_at":"2026-07-05T08:40:28.973566+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.04118v1","created_at":"2026-07-05T08:40:28.973566+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04118","created_at":"2026-07-05T08:40:28.973566+00:00"},{"alias_kind":"pith_short_12","alias_value":"SIYMK2U54JVK","created_at":"2026-07-05T08:40:28.973566+00:00"},{"alias_kind":"pith_short_16","alias_value":"SIYMK2U54JVKOYFN","created_at":"2026-07-05T08:40:28.973566+00:00"},{"alias_kind":"pith_short_8","alias_value":"SIYMK2U5","created_at":"2026-07-05T08:40:28.973566+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.20791","citing_title":"From Cool Demos to Production-Ready FMware: Core Challenges and a Technology Roadmap","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SIYMK2U54JVKOYFNY54KB6QFNS","json":"https://pith.science/pith/SIYMK2U54JVKOYFNY54KB6QFNS.json","graph_json":"https://pith.science/api/pith-number/SIYMK2U54JVKOYFNY54KB6QFNS/graph.json","events_json":"https://pith.science/api/pith-number/SIYMK2U54JVKOYFNY54KB6QFNS/events.json","paper":"https://pith.science/paper/SIYMK2U5"},"agent_actions":{"view_html":"https://pith.science/pith/SIYMK2U54JVKOYFNY54KB6QFNS","download_json":"https://pith.science/pith/SIYMK2U54JVKOYFNY54KB6QFNS.json","view_paper":"https://pith.science/paper/SIYMK2U5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.04118&json=true","fetch_graph":"https://pith.science/api/pith-number/SIYMK2U54JVKOYFNY54KB6QFNS/graph.json","fetch_events":"https://pith.science/api/pith-number/SIYMK2U54JVKOYFNY54KB6QFNS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SIYMK2U54JVKOYFNY54KB6QFNS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SIYMK2U54JVKOYFNY54KB6QFNS/action/storage_attestation","attest_author":"https://pith.science/pith/SIYMK2U54JVKOYFNY54KB6QFNS/action/author_attestation","sign_citation":"https://pith.science/pith/SIYMK2U54JVKOYFNY54KB6QFNS/action/citation_signature","submit_replication":"https://pith.science/pith/SIYMK2U54JVKOYFNY54KB6QFNS/action/replication_record"}},"created_at":"2026-07-05T08:40:28.973566+00:00","updated_at":"2026-07-05T08:40:28.973566+00:00"}