{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CHEMHGR4G7BIGQ45K37O35KK2O","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3207f7e575a88797205bf0315bc17fd0fcbfc5ffc44ab5a73568ad41f74e771b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T08:06:42Z","title_canon_sha256":"bb36a2eeed274eef7e911e6a34f3b25f7df1aae246d8df8419829ae066ceceb4"},"schema_version":"1.0","source":{"id":"2409.12545","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.12545","created_at":"2026-07-05T09:50:52Z"},{"alias_kind":"arxiv_version","alias_value":"2409.12545v2","created_at":"2026-07-05T09:50:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12545","created_at":"2026-07-05T09:50:52Z"},{"alias_kind":"pith_short_12","alias_value":"CHEMHGR4G7BI","created_at":"2026-07-05T09:50:52Z"},{"alias_kind":"pith_short_16","alias_value":"CHEMHGR4G7BIGQ45","created_at":"2026-07-05T09:50:52Z"},{"alias_kind":"pith_short_8","alias_value":"CHEMHGR4","created_at":"2026-07-05T09:50:52Z"}],"graph_snapshots":[{"event_id":"sha256:bf9c9715a000d6c40baf1f85a7038aeae6e8643672f004022d92191553288705","target":"graph","created_at":"2026-07-05T09:50:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.12545/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Knowledge distillation (KD) is an effective model compression method that can transfer the internal capabilities of large language models (LLMs) to smaller ones. However, the multi-modal probability distribution predicted by teacher LLMs causes difficulties for student models to learn. In this paper, we first demonstrate the importance of multi-modal distribution alignment with experiments and then highlight the inefficiency of existing KD approaches in learning multi-modal distributions. To address this problem, we propose Ranking Loss based Knowledge Distillation (RLKD), which encourages the","authors_text":"Jiajun Zhang, Tianyu Peng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T08:06:42Z","title":"Enhancing Knowledge Distillation of Large Language Models through Efficient Multi-Modal Distribution Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12545","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d988501b99b3acb483f179c410c6d289f251d5ad11aaf4383e3c597e8912a96a","target":"record","created_at":"2026-07-05T09:50:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3207f7e575a88797205bf0315bc17fd0fcbfc5ffc44ab5a73568ad41f74e771b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T08:06:42Z","title_canon_sha256":"bb36a2eeed274eef7e911e6a34f3b25f7df1aae246d8df8419829ae066ceceb4"},"schema_version":"1.0","source":{"id":"2409.12545","kind":"arxiv","version":2}},"canonical_sha256":"11c8c39a3c37c283439d56feedf54ad3a157a53b6dc0d32ef0c55c2f9656c8f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11c8c39a3c37c283439d56feedf54ad3a157a53b6dc0d32ef0c55c2f9656c8f3","first_computed_at":"2026-07-05T09:50:52.089856Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:52.089856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bbiuPSuCHqmznICxfTvnFMK6hbyW8t+5VQk0zPqa1PVGZ3XO+6TYOJvzGC1Xn4Q6WXAofmw/NSAaNTVkja6lDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:52.090422Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.12545","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d988501b99b3acb483f179c410c6d289f251d5ad11aaf4383e3c597e8912a96a","sha256:bf9c9715a000d6c40baf1f85a7038aeae6e8643672f004022d92191553288705"],"state_sha256":"6c0a2ecb648bb9dddd835371c6eb1ced48c2e48bb211cb96ead7e33f26e41cc6"}