{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3VAR6D3MA5DNE7AJ34QK6BDAT5","short_pith_number":"pith:3VAR6D3M","schema_version":"1.0","canonical_sha256":"dd411f0f6c0746d27c09df20af04609f51b1d9eb74cbacb270e1dcf846b19467","source":{"kind":"arxiv","id":"2402.01349","version":3},"attestation_state":"computed","paper":{"title":"LLMs May Perform MCQA by Selecting the Least Incorrect Option","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bing Qin, Haochun Wang, Nuwa Xi, Sendong Zhao, Ting Liu, Zewen Qiang","submitted_at":"2024-02-02T12:07:00Z","abstract_excerpt":"In the field of NLP, Large Language Models (LLMs) have markedly enhanced performance across a variety of tasks. However, the comprehensive evaluation of LLMs remains an inevitable challenge for the community. Recently, the adoption of Multiple Choice Question Answering (MCQA) as a benchmark for assessing LLMs has gained considerable traction. However, concerns regarding the robustness of this evaluative method persist. Building upon previous discussions on the issue of \\textit{variability}, we reveal an additional dimension of concern: LLMs may perform MCQA by selecting the least incorrect opt"},"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":"2402.01349","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T12:07:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"180e07bcb9bc7959d57d62f5676269ad14c26f33e746fef1f9b47819a904be5e","abstract_canon_sha256":"d6ed9dadee32e1024654bb218096e27fc4fcd21b14c283f7c6079401ca85b996"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:07.850644Z","signature_b64":"GQhicp0+wJjnVJm/bbowKj3mifBetfR2zgeHcSHTI3K55jkRhLAlp3FXGNySQIzGfEzwH1ViN+eBQz9SLeLrBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd411f0f6c0746d27c09df20af04609f51b1d9eb74cbacb270e1dcf846b19467","last_reissued_at":"2026-07-05T09:45:07.850158Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:07.850158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMs May Perform MCQA by Selecting the Least Incorrect Option","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bing Qin, Haochun Wang, Nuwa Xi, Sendong Zhao, Ting Liu, Zewen Qiang","submitted_at":"2024-02-02T12:07:00Z","abstract_excerpt":"In the field of NLP, Large Language Models (LLMs) have markedly enhanced performance across a variety of tasks. However, the comprehensive evaluation of LLMs remains an inevitable challenge for the community. Recently, the adoption of Multiple Choice Question Answering (MCQA) as a benchmark for assessing LLMs has gained considerable traction. However, concerns regarding the robustness of this evaluative method persist. Building upon previous discussions on the issue of \\textit{variability}, we reveal an additional dimension of concern: LLMs may perform MCQA by selecting the least incorrect opt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01349","kind":"arxiv","version":3},"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/2402.01349/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":"2402.01349","created_at":"2026-07-05T09:45:07.850210+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01349v3","created_at":"2026-07-05T09:45:07.850210+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01349","created_at":"2026-07-05T09:45:07.850210+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VAR6D3MA5DN","created_at":"2026-07-05T09:45:07.850210+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VAR6D3MA5DNE7AJ","created_at":"2026-07-05T09:45:07.850210+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VAR6D3M","created_at":"2026-07-05T09:45:07.850210+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00664","citing_title":"YOMI-Bench: A Benchmark for Evaluating Kanji Reading and Phonological Understanding of LLMs for Japanese","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3VAR6D3MA5DNE7AJ34QK6BDAT5","json":"https://pith.science/pith/3VAR6D3MA5DNE7AJ34QK6BDAT5.json","graph_json":"https://pith.science/api/pith-number/3VAR6D3MA5DNE7AJ34QK6BDAT5/graph.json","events_json":"https://pith.science/api/pith-number/3VAR6D3MA5DNE7AJ34QK6BDAT5/events.json","paper":"https://pith.science/paper/3VAR6D3M"},"agent_actions":{"view_html":"https://pith.science/pith/3VAR6D3MA5DNE7AJ34QK6BDAT5","download_json":"https://pith.science/pith/3VAR6D3MA5DNE7AJ34QK6BDAT5.json","view_paper":"https://pith.science/paper/3VAR6D3M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01349&json=true","fetch_graph":"https://pith.science/api/pith-number/3VAR6D3MA5DNE7AJ34QK6BDAT5/graph.json","fetch_events":"https://pith.science/api/pith-number/3VAR6D3MA5DNE7AJ34QK6BDAT5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VAR6D3MA5DNE7AJ34QK6BDAT5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VAR6D3MA5DNE7AJ34QK6BDAT5/action/storage_attestation","attest_author":"https://pith.science/pith/3VAR6D3MA5DNE7AJ34QK6BDAT5/action/author_attestation","sign_citation":"https://pith.science/pith/3VAR6D3MA5DNE7AJ34QK6BDAT5/action/citation_signature","submit_replication":"https://pith.science/pith/3VAR6D3MA5DNE7AJ34QK6BDAT5/action/replication_record"}},"created_at":"2026-07-05T09:45:07.850210+00:00","updated_at":"2026-07-05T09:45:07.850210+00:00"}