{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AUQ4UNVAIQL4AKBRNJN7QAXFOO","short_pith_number":"pith:AUQ4UNVA","schema_version":"1.0","canonical_sha256":"0521ca36a04417c028316a5bf802e573a32c34d74dba93abd92b549f7a55d64c","source":{"kind":"arxiv","id":"2405.14862","version":2},"attestation_state":"computed","paper":{"title":"Bitune: Leveraging Bidirectional Attention to Improve Decoder-Only LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dawid J. Kopiczko, Tijmen Blankevoort, Yuki M. Asano","submitted_at":"2024-05-23T17:59:22Z","abstract_excerpt":"Decoder-only large language models typically rely solely on masked causal attention, which limits their expressiveness by restricting information flow to one direction. We propose Bitune, a method that enhances pretrained decoder-only LLMs by incorporating bidirectional attention into prompt processing. We evaluate Bitune in instruction-tuning and question-answering settings, showing significant improvements in performance on commonsense reasoning, arithmetic, and language understanding tasks. Furthermore, extensive ablation studies validate the role of each component of the method, and demons"},"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":"2405.14862","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-23T17:59:22Z","cross_cats_sorted":[],"title_canon_sha256":"021154e8b920940ac27eff50ede483bd6b637fc56df3ad72386f9013fad40370","abstract_canon_sha256":"105efd2e3707a301ac569f3c54976c2bc7ca6a5efe8c2d8e1a30325fd33ff75e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:42.882787Z","signature_b64":"sWEus/7iipmHfhg0pLH4769bPt6o3J7TCcjlFZCRglkhd28xgdoFS0rBRs67BIqgJP5gQhmERuRomXypku2XCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0521ca36a04417c028316a5bf802e573a32c34d74dba93abd92b549f7a55d64c","last_reissued_at":"2026-07-05T12:00:42.882344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:42.882344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bitune: Leveraging Bidirectional Attention to Improve Decoder-Only LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dawid J. Kopiczko, Tijmen Blankevoort, Yuki M. Asano","submitted_at":"2024-05-23T17:59:22Z","abstract_excerpt":"Decoder-only large language models typically rely solely on masked causal attention, which limits their expressiveness by restricting information flow to one direction. We propose Bitune, a method that enhances pretrained decoder-only LLMs by incorporating bidirectional attention into prompt processing. We evaluate Bitune in instruction-tuning and question-answering settings, showing significant improvements in performance on commonsense reasoning, arithmetic, and language understanding tasks. Furthermore, extensive ablation studies validate the role of each component of the method, and demons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14862","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/2405.14862/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":"2405.14862","created_at":"2026-07-05T12:00:42.882412+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.14862v2","created_at":"2026-07-05T12:00:42.882412+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14862","created_at":"2026-07-05T12:00:42.882412+00:00"},{"alias_kind":"pith_short_12","alias_value":"AUQ4UNVAIQL4","created_at":"2026-07-05T12:00:42.882412+00:00"},{"alias_kind":"pith_short_16","alias_value":"AUQ4UNVAIQL4AKBR","created_at":"2026-07-05T12:00:42.882412+00:00"},{"alias_kind":"pith_short_8","alias_value":"AUQ4UNVA","created_at":"2026-07-05T12:00:42.882412+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.15433","citing_title":"Set-LLM: A Permutation-Invariant LLM","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AUQ4UNVAIQL4AKBRNJN7QAXFOO","json":"https://pith.science/pith/AUQ4UNVAIQL4AKBRNJN7QAXFOO.json","graph_json":"https://pith.science/api/pith-number/AUQ4UNVAIQL4AKBRNJN7QAXFOO/graph.json","events_json":"https://pith.science/api/pith-number/AUQ4UNVAIQL4AKBRNJN7QAXFOO/events.json","paper":"https://pith.science/paper/AUQ4UNVA"},"agent_actions":{"view_html":"https://pith.science/pith/AUQ4UNVAIQL4AKBRNJN7QAXFOO","download_json":"https://pith.science/pith/AUQ4UNVAIQL4AKBRNJN7QAXFOO.json","view_paper":"https://pith.science/paper/AUQ4UNVA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.14862&json=true","fetch_graph":"https://pith.science/api/pith-number/AUQ4UNVAIQL4AKBRNJN7QAXFOO/graph.json","fetch_events":"https://pith.science/api/pith-number/AUQ4UNVAIQL4AKBRNJN7QAXFOO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AUQ4UNVAIQL4AKBRNJN7QAXFOO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AUQ4UNVAIQL4AKBRNJN7QAXFOO/action/storage_attestation","attest_author":"https://pith.science/pith/AUQ4UNVAIQL4AKBRNJN7QAXFOO/action/author_attestation","sign_citation":"https://pith.science/pith/AUQ4UNVAIQL4AKBRNJN7QAXFOO/action/citation_signature","submit_replication":"https://pith.science/pith/AUQ4UNVAIQL4AKBRNJN7QAXFOO/action/replication_record"}},"created_at":"2026-07-05T12:00:42.882412+00:00","updated_at":"2026-07-05T12:00:42.882412+00:00"}