{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LBMHD7JPMXJOC45DV4KHTDSS2S","short_pith_number":"pith:LBMHD7JP","schema_version":"1.0","canonical_sha256":"585871fd2f65d2e173a3af14798e52d4a3d6b972480f08702d858c99f35edd28","source":{"kind":"arxiv","id":"2402.10083","version":1},"attestation_state":"computed","paper":{"title":"Fine-tuning Large Language Model (LLM) Artificial Intelligence Chatbots in Ophthalmology and LLM-based evaluation using GPT-4","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Daniel Lim, Daniel Shu Wei Ting, Joshua Lim, Kabilan Elangovan, Li Yong, Liyuan Jin, Nan Liu, Stanley Poh, Ting Fang Tan, Wei Yan Ng, Yao Jie, Yuhe Ke","submitted_at":"2024-02-15T16:43:41Z","abstract_excerpt":"Purpose: To assess the alignment of GPT-4-based evaluation to human clinician experts, for the evaluation of responses to ophthalmology-related patient queries generated by fine-tuned LLM chatbots. Methods: 400 ophthalmology questions and paired answers were created by ophthalmologists to represent commonly asked patient questions, divided into fine-tuning (368; 92%), and testing (40; 8%). We find-tuned 5 different LLMs, including LLAMA2-7b, LLAMA2-7b-Chat, LLAMA2-13b, and LLAMA2-13b-Chat. For the testing dataset, additional 8 glaucoma QnA pairs were included. 200 responses to the testing data"},"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":"2402.10083","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-15T16:43:41Z","cross_cats_sorted":[],"title_canon_sha256":"e0e79bda013a70a05ef5352d253c078c8fd13cabced2b3bacec2ddebae89211e","abstract_canon_sha256":"6ca37d46debeee6a596665148f9a10fdb8b72d672cae445ccbb2d6dd2635626d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:41.203829Z","signature_b64":"xHaVNWJcfa5fp6Xdapv8sjOVJAxigN+JlTsoUubDOkDXs6p2LzFkvjljbJh5K2nQzn0B9e+wSvlQAVY2TElMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"585871fd2f65d2e173a3af14798e52d4a3d6b972480f08702d858c99f35edd28","last_reissued_at":"2026-07-05T07:45:41.203403Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:41.203403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-tuning Large Language Model (LLM) Artificial Intelligence Chatbots in Ophthalmology and LLM-based evaluation using GPT-4","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Daniel Lim, Daniel Shu Wei Ting, Joshua Lim, Kabilan Elangovan, Li Yong, Liyuan Jin, Nan Liu, Stanley Poh, Ting Fang Tan, Wei Yan Ng, Yao Jie, Yuhe Ke","submitted_at":"2024-02-15T16:43:41Z","abstract_excerpt":"Purpose: To assess the alignment of GPT-4-based evaluation to human clinician experts, for the evaluation of responses to ophthalmology-related patient queries generated by fine-tuned LLM chatbots. Methods: 400 ophthalmology questions and paired answers were created by ophthalmologists to represent commonly asked patient questions, divided into fine-tuning (368; 92%), and testing (40; 8%). We find-tuned 5 different LLMs, including LLAMA2-7b, LLAMA2-7b-Chat, LLAMA2-13b, and LLAMA2-13b-Chat. For the testing dataset, additional 8 glaucoma QnA pairs were included. 200 responses to the testing data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10083","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/2402.10083/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":"2402.10083","created_at":"2026-07-05T07:45:41.203460+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.10083v1","created_at":"2026-07-05T07:45:41.203460+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10083","created_at":"2026-07-05T07:45:41.203460+00:00"},{"alias_kind":"pith_short_12","alias_value":"LBMHD7JPMXJO","created_at":"2026-07-05T07:45:41.203460+00:00"},{"alias_kind":"pith_short_16","alias_value":"LBMHD7JPMXJOC45D","created_at":"2026-07-05T07:45:41.203460+00:00"},{"alias_kind":"pith_short_8","alias_value":"LBMHD7JP","created_at":"2026-07-05T07:45:41.203460+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19776","citing_title":"Development and Preliminary Evaluation of a Domain-Specific Large Language Model for Tuberculosis Care in South Africa","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LBMHD7JPMXJOC45DV4KHTDSS2S","json":"https://pith.science/pith/LBMHD7JPMXJOC45DV4KHTDSS2S.json","graph_json":"https://pith.science/api/pith-number/LBMHD7JPMXJOC45DV4KHTDSS2S/graph.json","events_json":"https://pith.science/api/pith-number/LBMHD7JPMXJOC45DV4KHTDSS2S/events.json","paper":"https://pith.science/paper/LBMHD7JP"},"agent_actions":{"view_html":"https://pith.science/pith/LBMHD7JPMXJOC45DV4KHTDSS2S","download_json":"https://pith.science/pith/LBMHD7JPMXJOC45DV4KHTDSS2S.json","view_paper":"https://pith.science/paper/LBMHD7JP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.10083&json=true","fetch_graph":"https://pith.science/api/pith-number/LBMHD7JPMXJOC45DV4KHTDSS2S/graph.json","fetch_events":"https://pith.science/api/pith-number/LBMHD7JPMXJOC45DV4KHTDSS2S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LBMHD7JPMXJOC45DV4KHTDSS2S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LBMHD7JPMXJOC45DV4KHTDSS2S/action/storage_attestation","attest_author":"https://pith.science/pith/LBMHD7JPMXJOC45DV4KHTDSS2S/action/author_attestation","sign_citation":"https://pith.science/pith/LBMHD7JPMXJOC45DV4KHTDSS2S/action/citation_signature","submit_replication":"https://pith.science/pith/LBMHD7JPMXJOC45DV4KHTDSS2S/action/replication_record"}},"created_at":"2026-07-05T07:45:41.203460+00:00","updated_at":"2026-07-05T07:45:41.203460+00:00"}