{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:35RB3H23RUUHIKL3SNAEOT44ZH","short_pith_number":"pith:35RB3H23","schema_version":"1.0","canonical_sha256":"df621d9f5b8d2874297b9340474f9cc9e2e23c18452f80c0dbd20f09c350287e","source":{"kind":"arxiv","id":"2305.16633","version":1},"attestation_state":"computed","paper":{"title":"Zero is Not Hero Yet: Benchmarking Zero-Shot Performance of LLMs for Financial Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-fin.GN"],"primary_cat":"cs.CL","authors_text":"Agam Shah, Sudheer Chava","submitted_at":"2023-05-26T05:13:01Z","abstract_excerpt":"Recently large language models (LLMs) like ChatGPT have shown impressive performance on many natural language processing tasks with zero-shot. In this paper, we investigate the effectiveness of zero-shot LLMs in the financial domain. We compare the performance of ChatGPT along with some open-source generative LLMs in zero-shot mode with RoBERTa fine-tuned on annotated data. We address three inter-related research questions on data annotation, performance gaps, and the feasibility of employing generative models in the finance domain. Our findings demonstrate that ChatGPT performs well even with"},"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":"2305.16633","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T05:13:01Z","cross_cats_sorted":["q-fin.GN"],"title_canon_sha256":"73e0761d792d814b38ca41d6dbd2b9a788f5795a830cd516938498082085cbeb","abstract_canon_sha256":"aec3ecd23ac907665013914e9621710e1eba2ef33a052b0f864d722a7d01dc0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:15.313145Z","signature_b64":"gc4HIpzfIBxbARBhL/y/3LOpkxUljaZ2dBUC0Dk/yIuAXMGs8wK4ybpiJOc2ZsGwWkiGRGUut7nzP+UKNWV1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df621d9f5b8d2874297b9340474f9cc9e2e23c18452f80c0dbd20f09c350287e","last_reissued_at":"2026-07-05T06:14:15.312668Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:15.312668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero is Not Hero Yet: Benchmarking Zero-Shot Performance of LLMs for Financial Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-fin.GN"],"primary_cat":"cs.CL","authors_text":"Agam Shah, Sudheer Chava","submitted_at":"2023-05-26T05:13:01Z","abstract_excerpt":"Recently large language models (LLMs) like ChatGPT have shown impressive performance on many natural language processing tasks with zero-shot. In this paper, we investigate the effectiveness of zero-shot LLMs in the financial domain. We compare the performance of ChatGPT along with some open-source generative LLMs in zero-shot mode with RoBERTa fine-tuned on annotated data. We address three inter-related research questions on data annotation, performance gaps, and the feasibility of employing generative models in the finance domain. Our findings demonstrate that ChatGPT performs well even with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16633","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/2305.16633/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":"2305.16633","created_at":"2026-07-05T06:14:15.312722+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.16633v1","created_at":"2026-07-05T06:14:15.312722+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16633","created_at":"2026-07-05T06:14:15.312722+00:00"},{"alias_kind":"pith_short_12","alias_value":"35RB3H23RUUH","created_at":"2026-07-05T06:14:15.312722+00:00"},{"alias_kind":"pith_short_16","alias_value":"35RB3H23RUUHIKL3","created_at":"2026-07-05T06:14:15.312722+00:00"},{"alias_kind":"pith_short_8","alias_value":"35RB3H23","created_at":"2026-07-05T06:14:15.312722+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19675","citing_title":"Calibrating Pre-trained Language Classifiers on LLM-generated Noisy Labels via Iterative Refinement","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/35RB3H23RUUHIKL3SNAEOT44ZH","json":"https://pith.science/pith/35RB3H23RUUHIKL3SNAEOT44ZH.json","graph_json":"https://pith.science/api/pith-number/35RB3H23RUUHIKL3SNAEOT44ZH/graph.json","events_json":"https://pith.science/api/pith-number/35RB3H23RUUHIKL3SNAEOT44ZH/events.json","paper":"https://pith.science/paper/35RB3H23"},"agent_actions":{"view_html":"https://pith.science/pith/35RB3H23RUUHIKL3SNAEOT44ZH","download_json":"https://pith.science/pith/35RB3H23RUUHIKL3SNAEOT44ZH.json","view_paper":"https://pith.science/paper/35RB3H23","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.16633&json=true","fetch_graph":"https://pith.science/api/pith-number/35RB3H23RUUHIKL3SNAEOT44ZH/graph.json","fetch_events":"https://pith.science/api/pith-number/35RB3H23RUUHIKL3SNAEOT44ZH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/35RB3H23RUUHIKL3SNAEOT44ZH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/35RB3H23RUUHIKL3SNAEOT44ZH/action/storage_attestation","attest_author":"https://pith.science/pith/35RB3H23RUUHIKL3SNAEOT44ZH/action/author_attestation","sign_citation":"https://pith.science/pith/35RB3H23RUUHIKL3SNAEOT44ZH/action/citation_signature","submit_replication":"https://pith.science/pith/35RB3H23RUUHIKL3SNAEOT44ZH/action/replication_record"}},"created_at":"2026-07-05T06:14:15.312722+00:00","updated_at":"2026-07-05T06:14:15.312722+00:00"}