{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YB5G57BPAJS4YTYVUJOR7MNPRO","short_pith_number":"pith:YB5G57BP","schema_version":"1.0","canonical_sha256":"c07a6efc2f0265cc4f15a25d1fb1af8ba0a4cd9d8dd26a8bba03cfc407907903","source":{"kind":"arxiv","id":"2402.11597","version":2},"attestation_state":"computed","paper":{"title":"Multi-Task Inference: Can Large Language Models Follow Multiple Instructions at Once?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guijin Son, Ilgyun Jeong, Sangdae Nam, Sangwon Baek, Seungone Kim","submitted_at":"2024-02-18T14:25:19Z","abstract_excerpt":"Large language models (LLMs) are typically prompted to follow a single instruction per inference call. In this work, we analyze whether LLMs also hold the capability to handle multiple instructions simultaneously, denoted as Multi-Task Inference. For this purpose, we introduce the MTI Bench(Multi-Task Inference Benchmark), a comprehensive evaluation benchmark encompassing 5,000 instances across 25 tasks. Each task in the MTI Bench involves 2 to 3 sub-tasks. As expected, we first demonstrate that Multi-Task Inference reduces the total inference time by 1.46 times in average since it does not re"},"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":"2402.11597","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T14:25:19Z","cross_cats_sorted":[],"title_canon_sha256":"347e67cccf0ffedfdbef7c1379fac53a67853b9601fbe49434f81213e3b8ea5e","abstract_canon_sha256":"f2a30183d1115aea0d092d921bcce131c260fa9e2297e969f451fbc1bf33df16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:06.292478Z","signature_b64":"XTg13tAPuEE7XJvlh5YNdh1sdB2Px40kyCcwyOxllxF9STNVBPm5OJVRltpBwfnTrNlCSMxjR8ExRTIHrlP7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c07a6efc2f0265cc4f15a25d1fb1af8ba0a4cd9d8dd26a8bba03cfc407907903","last_reissued_at":"2026-07-05T08:28:06.292059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:06.292059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Task Inference: Can Large Language Models Follow Multiple Instructions at Once?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guijin Son, Ilgyun Jeong, Sangdae Nam, Sangwon Baek, Seungone Kim","submitted_at":"2024-02-18T14:25:19Z","abstract_excerpt":"Large language models (LLMs) are typically prompted to follow a single instruction per inference call. In this work, we analyze whether LLMs also hold the capability to handle multiple instructions simultaneously, denoted as Multi-Task Inference. For this purpose, we introduce the MTI Bench(Multi-Task Inference Benchmark), a comprehensive evaluation benchmark encompassing 5,000 instances across 25 tasks. Each task in the MTI Bench involves 2 to 3 sub-tasks. As expected, we first demonstrate that Multi-Task Inference reduces the total inference time by 1.46 times in average since it does not re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11597","kind":"arxiv","version":2},"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/2402.11597/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":"2402.11597","created_at":"2026-07-05T08:28:06.292114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11597v2","created_at":"2026-07-05T08:28:06.292114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11597","created_at":"2026-07-05T08:28:06.292114+00:00"},{"alias_kind":"pith_short_12","alias_value":"YB5G57BPAJS4","created_at":"2026-07-05T08:28:06.292114+00:00"},{"alias_kind":"pith_short_16","alias_value":"YB5G57BPAJS4YTYV","created_at":"2026-07-05T08:28:06.292114+00:00"},{"alias_kind":"pith_short_8","alias_value":"YB5G57BP","created_at":"2026-07-05T08:28:06.292114+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YB5G57BPAJS4YTYVUJOR7MNPRO","json":"https://pith.science/pith/YB5G57BPAJS4YTYVUJOR7MNPRO.json","graph_json":"https://pith.science/api/pith-number/YB5G57BPAJS4YTYVUJOR7MNPRO/graph.json","events_json":"https://pith.science/api/pith-number/YB5G57BPAJS4YTYVUJOR7MNPRO/events.json","paper":"https://pith.science/paper/YB5G57BP"},"agent_actions":{"view_html":"https://pith.science/pith/YB5G57BPAJS4YTYVUJOR7MNPRO","download_json":"https://pith.science/pith/YB5G57BPAJS4YTYVUJOR7MNPRO.json","view_paper":"https://pith.science/paper/YB5G57BP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11597&json=true","fetch_graph":"https://pith.science/api/pith-number/YB5G57BPAJS4YTYVUJOR7MNPRO/graph.json","fetch_events":"https://pith.science/api/pith-number/YB5G57BPAJS4YTYVUJOR7MNPRO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YB5G57BPAJS4YTYVUJOR7MNPRO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YB5G57BPAJS4YTYVUJOR7MNPRO/action/storage_attestation","attest_author":"https://pith.science/pith/YB5G57BPAJS4YTYVUJOR7MNPRO/action/author_attestation","sign_citation":"https://pith.science/pith/YB5G57BPAJS4YTYVUJOR7MNPRO/action/citation_signature","submit_replication":"https://pith.science/pith/YB5G57BPAJS4YTYVUJOR7MNPRO/action/replication_record"}},"created_at":"2026-07-05T08:28:06.292114+00:00","updated_at":"2026-07-05T08:28:06.292114+00:00"}