{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MXJ3RDBLVC5EL2ZMGUZXGFVME7","short_pith_number":"pith:MXJ3RDBL","schema_version":"1.0","canonical_sha256":"65d3b88c2ba8ba45eb2c35337316ac27cf27dca80fc6276a0d0592f13bdc6821","source":{"kind":"arxiv","id":"2410.14635","version":2},"attestation_state":"computed","paper":{"title":"GenEOL: Harnessing the Generative Power of LLMs for Training-Free Sentence Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bhuwan Dhingra, Raghuveer Thirukovalluru","submitted_at":"2024-10-18T17:36:53Z","abstract_excerpt":"Training-free embedding methods directly leverage pretrained large language models (LLMs) to embed text, bypassing the costly and complex procedure of contrastive learning. Previous training-free embedding methods have mainly focused on optimizing embedding prompts and have overlooked the benefits of utilizing the generative abilities of LLMs. We propose a novel method, GenEOL, which uses LLMs to generate diverse transformations of a sentence that preserve its meaning, and aggregates the resulting embeddings of these transformations to enhance the overall sentence embedding. GenEOL significant"},"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":"2410.14635","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-18T17:36:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5182fd396af7dfb3d33efbfe58636ef4f38693c156b12075303a4e52f68396e3","abstract_canon_sha256":"b0ca496fcaa70447d8267b05c547d36a341f981c1ebf20f652e32aa4faf68225"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:26.646338Z","signature_b64":"ayPVcXj7KwicLOcQ+gDswegbnfHv87lxl4PPExvaDWIPmTx+I80aE4tUIqtSkiuRxUKRXYw2sSM+keq/0NKkCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65d3b88c2ba8ba45eb2c35337316ac27cf27dca80fc6276a0d0592f13bdc6821","last_reissued_at":"2026-07-05T10:11:26.645819Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:26.645819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GenEOL: Harnessing the Generative Power of LLMs for Training-Free Sentence Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bhuwan Dhingra, Raghuveer Thirukovalluru","submitted_at":"2024-10-18T17:36:53Z","abstract_excerpt":"Training-free embedding methods directly leverage pretrained large language models (LLMs) to embed text, bypassing the costly and complex procedure of contrastive learning. Previous training-free embedding methods have mainly focused on optimizing embedding prompts and have overlooked the benefits of utilizing the generative abilities of LLMs. We propose a novel method, GenEOL, which uses LLMs to generate diverse transformations of a sentence that preserve its meaning, and aggregates the resulting embeddings of these transformations to enhance the overall sentence embedding. GenEOL significant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14635","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/2410.14635/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":"2410.14635","created_at":"2026-07-05T10:11:26.645882+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.14635v2","created_at":"2026-07-05T10:11:26.645882+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14635","created_at":"2026-07-05T10:11:26.645882+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXJ3RDBLVC5E","created_at":"2026-07-05T10:11:26.645882+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXJ3RDBLVC5EL2ZM","created_at":"2026-07-05T10:11:26.645882+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXJ3RDBL","created_at":"2026-07-05T10:11:26.645882+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30027","citing_title":"DocRetriever: A Plug-and-Play Framework for Multimodal Document Retrieval with Comprehensive Benchmark","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24621","citing_title":"FreeRet: MLLMs as Training-Free Retrievers","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17054","citing_title":"mEOL: Training-Free Instruction-Guided Multimodal Embedder for Vector Graphics and Image Retrieval","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MXJ3RDBLVC5EL2ZMGUZXGFVME7","json":"https://pith.science/pith/MXJ3RDBLVC5EL2ZMGUZXGFVME7.json","graph_json":"https://pith.science/api/pith-number/MXJ3RDBLVC5EL2ZMGUZXGFVME7/graph.json","events_json":"https://pith.science/api/pith-number/MXJ3RDBLVC5EL2ZMGUZXGFVME7/events.json","paper":"https://pith.science/paper/MXJ3RDBL"},"agent_actions":{"view_html":"https://pith.science/pith/MXJ3RDBLVC5EL2ZMGUZXGFVME7","download_json":"https://pith.science/pith/MXJ3RDBLVC5EL2ZMGUZXGFVME7.json","view_paper":"https://pith.science/paper/MXJ3RDBL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.14635&json=true","fetch_graph":"https://pith.science/api/pith-number/MXJ3RDBLVC5EL2ZMGUZXGFVME7/graph.json","fetch_events":"https://pith.science/api/pith-number/MXJ3RDBLVC5EL2ZMGUZXGFVME7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXJ3RDBLVC5EL2ZMGUZXGFVME7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXJ3RDBLVC5EL2ZMGUZXGFVME7/action/storage_attestation","attest_author":"https://pith.science/pith/MXJ3RDBLVC5EL2ZMGUZXGFVME7/action/author_attestation","sign_citation":"https://pith.science/pith/MXJ3RDBLVC5EL2ZMGUZXGFVME7/action/citation_signature","submit_replication":"https://pith.science/pith/MXJ3RDBLVC5EL2ZMGUZXGFVME7/action/replication_record"}},"created_at":"2026-07-05T10:11:26.645882+00:00","updated_at":"2026-07-05T10:11:26.645882+00:00"}