{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6YRZ3FFNFTA2RIGEIL7UACU2UP","short_pith_number":"pith:6YRZ3FFN","schema_version":"1.0","canonical_sha256":"f6239d94ad2cc1a8a0c442ff400a9aa3c77627cfc37c768418255783d421ea53","source":{"kind":"arxiv","id":"2403.00236","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking zero-shot stance detection with FlanT5-XXL: Insights from training data, prompting, and decoding strategies into its near-SoTA performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Haewoon Kwak, Jisun An, Rachith Aiyappa, Shruthi Senthilmani, Yong-Yeol Ahn","submitted_at":"2024-03-01T02:33:26Z","abstract_excerpt":"We investigate the performance of LLM-based zero-shot stance detection on tweets. Using FlanT5-XXL, an instruction-tuned open-source LLM, with the SemEval 2016 Tasks 6A, 6B, and P-Stance datasets, we study the performance and its variations under different prompts and decoding strategies, as well as the potential biases of the model. We show that the zero-shot approach can match or outperform state-of-the-art benchmarks, including fine-tuned models. We provide various insights into its performance including the sensitivity to instructions and prompts, the decoding strategies, the perplexity of"},"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":"2403.00236","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-01T02:33:26Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1556293ea5e849035faeb3da4e57e93ccc51d1d353786c478cd8d27eac2170c1","abstract_canon_sha256":"793a6433bd96630081d4fd56f5aa524d2d06edfbe31b26b49826d9c003a2828e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:01.062202Z","signature_b64":"k/1MzQOPFA/JhM0VSzGQbbTeuWGNRaSLyFqNFDuuJ4GV2ay+du/V+cwGj+rSqhyRz7dzeEljAeDrqc/4hW1cBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6239d94ad2cc1a8a0c442ff400a9aa3c77627cfc37c768418255783d421ea53","last_reissued_at":"2026-07-05T07:51:01.061724Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:01.061724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking zero-shot stance detection with FlanT5-XXL: Insights from training data, prompting, and decoding strategies into its near-SoTA performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Haewoon Kwak, Jisun An, Rachith Aiyappa, Shruthi Senthilmani, Yong-Yeol Ahn","submitted_at":"2024-03-01T02:33:26Z","abstract_excerpt":"We investigate the performance of LLM-based zero-shot stance detection on tweets. Using FlanT5-XXL, an instruction-tuned open-source LLM, with the SemEval 2016 Tasks 6A, 6B, and P-Stance datasets, we study the performance and its variations under different prompts and decoding strategies, as well as the potential biases of the model. We show that the zero-shot approach can match or outperform state-of-the-art benchmarks, including fine-tuned models. We provide various insights into its performance including the sensitivity to instructions and prompts, the decoding strategies, the perplexity of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00236","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/2403.00236/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":"2403.00236","created_at":"2026-07-05T07:51:01.061780+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.00236v1","created_at":"2026-07-05T07:51:01.061780+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00236","created_at":"2026-07-05T07:51:01.061780+00:00"},{"alias_kind":"pith_short_12","alias_value":"6YRZ3FFNFTA2","created_at":"2026-07-05T07:51:01.061780+00:00"},{"alias_kind":"pith_short_16","alias_value":"6YRZ3FFNFTA2RIGE","created_at":"2026-07-05T07:51:01.061780+00:00"},{"alias_kind":"pith_short_8","alias_value":"6YRZ3FFN","created_at":"2026-07-05T07:51:01.061780+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26571","citing_title":"Zero-shot Tweet-Level Stance Detection Enhanced by External Knowledge and Reflective Chain-of-Thought Reasoning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20457","citing_title":"The Structure and Dynamics of the Online MAHA-sphere","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6YRZ3FFNFTA2RIGEIL7UACU2UP","json":"https://pith.science/pith/6YRZ3FFNFTA2RIGEIL7UACU2UP.json","graph_json":"https://pith.science/api/pith-number/6YRZ3FFNFTA2RIGEIL7UACU2UP/graph.json","events_json":"https://pith.science/api/pith-number/6YRZ3FFNFTA2RIGEIL7UACU2UP/events.json","paper":"https://pith.science/paper/6YRZ3FFN"},"agent_actions":{"view_html":"https://pith.science/pith/6YRZ3FFNFTA2RIGEIL7UACU2UP","download_json":"https://pith.science/pith/6YRZ3FFNFTA2RIGEIL7UACU2UP.json","view_paper":"https://pith.science/paper/6YRZ3FFN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.00236&json=true","fetch_graph":"https://pith.science/api/pith-number/6YRZ3FFNFTA2RIGEIL7UACU2UP/graph.json","fetch_events":"https://pith.science/api/pith-number/6YRZ3FFNFTA2RIGEIL7UACU2UP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6YRZ3FFNFTA2RIGEIL7UACU2UP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6YRZ3FFNFTA2RIGEIL7UACU2UP/action/storage_attestation","attest_author":"https://pith.science/pith/6YRZ3FFNFTA2RIGEIL7UACU2UP/action/author_attestation","sign_citation":"https://pith.science/pith/6YRZ3FFNFTA2RIGEIL7UACU2UP/action/citation_signature","submit_replication":"https://pith.science/pith/6YRZ3FFNFTA2RIGEIL7UACU2UP/action/replication_record"}},"created_at":"2026-07-05T07:51:01.061780+00:00","updated_at":"2026-07-05T07:51:01.061780+00:00"}