{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LQ7O3VZPX4HW6DFY52DFNVMHPA","short_pith_number":"pith:LQ7O3VZP","schema_version":"1.0","canonical_sha256":"5c3eedd72fbf0f6f0cb8ee8656d587782196d63b46b18454ce84254fe2a84956","source":{"kind":"arxiv","id":"2310.18025","version":1},"attestation_state":"computed","paper":{"title":"Large language models for aspect-based sentiment analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Paavo Huoviala, Paul F. Simmering","submitted_at":"2023-10-27T10:03:21Z","abstract_excerpt":"Large language models (LLMs) offer unprecedented text completion capabilities. As general models, they can fulfill a wide range of roles, including those of more specialized models. We assess the performance of GPT-4 and GPT-3.5 in zero shot, few shot and fine-tuned settings on the aspect-based sentiment analysis (ABSA) task. Fine-tuned GPT-3.5 achieves a state-of-the-art F1 score of 83.8 on the joint aspect term extraction and polarity classification task of the SemEval-2014 Task 4, improving upon InstructABSA [@scaria_instructabsa_2023] by 5.7%. However, this comes at the price of 1000 times"},"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":"2310.18025","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-27T10:03:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"adbb2ad356e07b17647f4ea304eb462950100a22acb8034f7509a14e4fb5c260","abstract_canon_sha256":"aa05e05614c6c3f11015d69657227de0f3e51d4452b6fd61254def7175c5490e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:55.989305Z","signature_b64":"l2u34BcUQvxj0wVtrzydM6yLIe5SmFQ/csAA8xizM1IdMzNMNQeO2xwz6qclo2xKLUVtglbICsNdOidsJobkCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c3eedd72fbf0f6f0cb8ee8656d587782196d63b46b18454ce84254fe2a84956","last_reissued_at":"2026-07-05T07:05:55.988823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:55.988823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large language models for aspect-based sentiment analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Paavo Huoviala, Paul F. Simmering","submitted_at":"2023-10-27T10:03:21Z","abstract_excerpt":"Large language models (LLMs) offer unprecedented text completion capabilities. As general models, they can fulfill a wide range of roles, including those of more specialized models. We assess the performance of GPT-4 and GPT-3.5 in zero shot, few shot and fine-tuned settings on the aspect-based sentiment analysis (ABSA) task. Fine-tuned GPT-3.5 achieves a state-of-the-art F1 score of 83.8 on the joint aspect term extraction and polarity classification task of the SemEval-2014 Task 4, improving upon InstructABSA [@scaria_instructabsa_2023] by 5.7%. However, this comes at the price of 1000 times"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18025","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/2310.18025/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":"2310.18025","created_at":"2026-07-05T07:05:55.988878+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.18025v1","created_at":"2026-07-05T07:05:55.988878+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18025","created_at":"2026-07-05T07:05:55.988878+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQ7O3VZPX4HW","created_at":"2026-07-05T07:05:55.988878+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQ7O3VZPX4HW6DFY","created_at":"2026-07-05T07:05:55.988878+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQ7O3VZP","created_at":"2026-07-05T07:05:55.988878+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20998","citing_title":"Single-Pass, Depth-Selective Reading for Multi-Aspect Sentiment Analysis","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10417","citing_title":"LASQ: A Low-resource Aspect-based Sentiment Quadruple Extraction Dataset","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03624","citing_title":"Annotation Quality in Aspect-Based Sentiment Analysis: A Case Study Comparing Experts, Students, Crowdworkers, and Large Language Model","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LQ7O3VZPX4HW6DFY52DFNVMHPA","json":"https://pith.science/pith/LQ7O3VZPX4HW6DFY52DFNVMHPA.json","graph_json":"https://pith.science/api/pith-number/LQ7O3VZPX4HW6DFY52DFNVMHPA/graph.json","events_json":"https://pith.science/api/pith-number/LQ7O3VZPX4HW6DFY52DFNVMHPA/events.json","paper":"https://pith.science/paper/LQ7O3VZP"},"agent_actions":{"view_html":"https://pith.science/pith/LQ7O3VZPX4HW6DFY52DFNVMHPA","download_json":"https://pith.science/pith/LQ7O3VZPX4HW6DFY52DFNVMHPA.json","view_paper":"https://pith.science/paper/LQ7O3VZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.18025&json=true","fetch_graph":"https://pith.science/api/pith-number/LQ7O3VZPX4HW6DFY52DFNVMHPA/graph.json","fetch_events":"https://pith.science/api/pith-number/LQ7O3VZPX4HW6DFY52DFNVMHPA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQ7O3VZPX4HW6DFY52DFNVMHPA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQ7O3VZPX4HW6DFY52DFNVMHPA/action/storage_attestation","attest_author":"https://pith.science/pith/LQ7O3VZPX4HW6DFY52DFNVMHPA/action/author_attestation","sign_citation":"https://pith.science/pith/LQ7O3VZPX4HW6DFY52DFNVMHPA/action/citation_signature","submit_replication":"https://pith.science/pith/LQ7O3VZPX4HW6DFY52DFNVMHPA/action/replication_record"}},"created_at":"2026-07-05T07:05:55.988878+00:00","updated_at":"2026-07-05T07:05:55.988878+00:00"}