{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:J22BAQJBUSJICYCYWVWQRQXGYG","short_pith_number":"pith:J22BAQJB","schema_version":"1.0","canonical_sha256":"4eb4104121a492816058b56d08c2e6c1902eae9ea33e13fa8e8c02f9950f9a65","source":{"kind":"arxiv","id":"2402.11260","version":1},"attestation_state":"computed","paper":{"title":"MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cheng-Long Wang, Di Wang, Lijie Hu, Muhammad Asif Ali, Shu Yang","submitted_at":"2024-02-17T12:25:31Z","abstract_excerpt":"Adapting large language models (LLMs) to new domains/tasks and enabling them to be efficient lifelong learners is a pivotal challenge. In this paper, we propose MoRAL, i.e., Mixture-of-Experts augmented Low-Rank Adaptation for Lifelong Learning. MoRAL combines the multi-tasking abilities of MoE with the fine-tuning abilities of LoRA for effective life-long learning of LLMs. In contrast to the conventional approaches that use factual triplets as inputs MoRAL relies on simple question-answer pairs, which is a more practical and effective strategy for robust and efficient learning. Owing to new d"},"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":"2402.11260","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-17T12:25:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"189be09291981f08f33408179668f2e00306964168b96867a383d7acb5944cbd","abstract_canon_sha256":"f0b8760977c999a70e38a35953f2907137c0e402394b4c42b14c803a22631007"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:36.513086Z","signature_b64":"+JNabFZqkwSpo+w546PVtwfZIVtepfMk1iba4kRtI+79+iS+yfBSfoFCZ8HxEFkeaGvEKM5h3m8BYk8GgCBIBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4eb4104121a492816058b56d08c2e6c1902eae9ea33e13fa8e8c02f9950f9a65","last_reissued_at":"2026-07-05T07:46:36.512586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:36.512586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cheng-Long Wang, Di Wang, Lijie Hu, Muhammad Asif Ali, Shu Yang","submitted_at":"2024-02-17T12:25:31Z","abstract_excerpt":"Adapting large language models (LLMs) to new domains/tasks and enabling them to be efficient lifelong learners is a pivotal challenge. In this paper, we propose MoRAL, i.e., Mixture-of-Experts augmented Low-Rank Adaptation for Lifelong Learning. MoRAL combines the multi-tasking abilities of MoE with the fine-tuning abilities of LoRA for effective life-long learning of LLMs. In contrast to the conventional approaches that use factual triplets as inputs MoRAL relies on simple question-answer pairs, which is a more practical and effective strategy for robust and efficient learning. Owing to new d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11260","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/2402.11260/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":"2402.11260","created_at":"2026-07-05T07:46:36.512661+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11260v1","created_at":"2026-07-05T07:46:36.512661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11260","created_at":"2026-07-05T07:46:36.512661+00:00"},{"alias_kind":"pith_short_12","alias_value":"J22BAQJBUSJI","created_at":"2026-07-05T07:46:36.512661+00:00"},{"alias_kind":"pith_short_16","alias_value":"J22BAQJBUSJICYCY","created_at":"2026-07-05T07:46:36.512661+00:00"},{"alias_kind":"pith_short_8","alias_value":"J22BAQJB","created_at":"2026-07-05T07:46:36.512661+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.06431","citing_title":"Functional-level Uncertainty Quantification for Calibrated Fine-tuning on LLMs","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2506.21035","citing_title":"Little by Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00029","citing_title":"LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09355","citing_title":"FLAME: Adaptive Mixture-of-Experts for Continual Multimodal Multi-Task Learning","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05732","citing_title":"CRAFT: Forgetting-Aware Intervention-Based Adaptation for Continual Learning","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04079","citing_title":"Efficient Handwriting-Based Alzheimer,s Disease Diagnosis Using a Low-Rank Mixture of Experts Deep Learning Framework","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05732","citing_title":"CRAFT: Forgetting-Aware Intervention-Based Adaptation for Continual Learning","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J22BAQJBUSJICYCYWVWQRQXGYG","json":"https://pith.science/pith/J22BAQJBUSJICYCYWVWQRQXGYG.json","graph_json":"https://pith.science/api/pith-number/J22BAQJBUSJICYCYWVWQRQXGYG/graph.json","events_json":"https://pith.science/api/pith-number/J22BAQJBUSJICYCYWVWQRQXGYG/events.json","paper":"https://pith.science/paper/J22BAQJB"},"agent_actions":{"view_html":"https://pith.science/pith/J22BAQJBUSJICYCYWVWQRQXGYG","download_json":"https://pith.science/pith/J22BAQJBUSJICYCYWVWQRQXGYG.json","view_paper":"https://pith.science/paper/J22BAQJB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11260&json=true","fetch_graph":"https://pith.science/api/pith-number/J22BAQJBUSJICYCYWVWQRQXGYG/graph.json","fetch_events":"https://pith.science/api/pith-number/J22BAQJBUSJICYCYWVWQRQXGYG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J22BAQJBUSJICYCYWVWQRQXGYG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J22BAQJBUSJICYCYWVWQRQXGYG/action/storage_attestation","attest_author":"https://pith.science/pith/J22BAQJBUSJICYCYWVWQRQXGYG/action/author_attestation","sign_citation":"https://pith.science/pith/J22BAQJBUSJICYCYWVWQRQXGYG/action/citation_signature","submit_replication":"https://pith.science/pith/J22BAQJBUSJICYCYWVWQRQXGYG/action/replication_record"}},"created_at":"2026-07-05T07:46:36.512661+00:00","updated_at":"2026-07-05T07:46:36.512661+00:00"}