{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RVEGLZANKI644B5S6KQWWJ4CS2","short_pith_number":"pith:RVEGLZAN","schema_version":"1.0","canonical_sha256":"8d4865e40d523dce07b2f2a16b278296831b63d83cd1db13309f32fdc1c25136","source":{"kind":"arxiv","id":"2412.12591","version":2},"attestation_state":"computed","paper":{"title":"LLMs are Also Effective Embedding Models: An In-depth Overview","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chongyang Tao, JunShuo Zhang, Kai Hua, Shen Gao, Shuai Ma, Tao Shen, Wenpeng Hu, Zhengwei Tao, Zhen Li","submitted_at":"2024-12-17T06:48:24Z","abstract_excerpt":"Large language models (LLMs) have revolutionized natural language processing by achieving state-of-the-art performance across various tasks. Recently, their effectiveness as embedding models has gained attention, marking a paradigm shift from traditional encoder-only models like ELMo and BERT to decoder-only, large-scale LLMs such as GPT, LLaMA, and Mistral. This survey provides an in-depth overview of this transition, beginning with foundational techniques before the LLM era, followed by LLM-based embedding models through two main strategies to derive embeddings from LLMs. 1) Direct prompting"},"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":"2412.12591","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T06:48:24Z","cross_cats_sorted":[],"title_canon_sha256":"9d135089de9b195ce612160eaa12bd47e4c547c721a890467a47c7d5453b6537","abstract_canon_sha256":"f9fdcc6a65593a3cae9ab9d3bcb4b7f72b9a0409cdcca57b8d80a6ef6f033528"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:08.667590Z","signature_b64":"R5Fzg8WRglOcaFMSarVZHE6YUcEpMGoVdrSI6Q7kIxi+44I7upvO+kidpC7hiH1sv68UtZOWiuQUrFPrRIq4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d4865e40d523dce07b2f2a16b278296831b63d83cd1db13309f32fdc1c25136","last_reissued_at":"2026-07-05T11:43:08.667134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:08.667134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMs are Also Effective Embedding Models: An In-depth Overview","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chongyang Tao, JunShuo Zhang, Kai Hua, Shen Gao, Shuai Ma, Tao Shen, Wenpeng Hu, Zhengwei Tao, Zhen Li","submitted_at":"2024-12-17T06:48:24Z","abstract_excerpt":"Large language models (LLMs) have revolutionized natural language processing by achieving state-of-the-art performance across various tasks. Recently, their effectiveness as embedding models has gained attention, marking a paradigm shift from traditional encoder-only models like ELMo and BERT to decoder-only, large-scale LLMs such as GPT, LLaMA, and Mistral. This survey provides an in-depth overview of this transition, beginning with foundational techniques before the LLM era, followed by LLM-based embedding models through two main strategies to derive embeddings from LLMs. 1) Direct prompting"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12591","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/2412.12591/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":"2412.12591","created_at":"2026-07-05T11:43:08.667189+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.12591v2","created_at":"2026-07-05T11:43:08.667189+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12591","created_at":"2026-07-05T11:43:08.667189+00:00"},{"alias_kind":"pith_short_12","alias_value":"RVEGLZANKI64","created_at":"2026-07-05T11:43:08.667189+00:00"},{"alias_kind":"pith_short_16","alias_value":"RVEGLZANKI644B5S","created_at":"2026-07-05T11:43:08.667189+00:00"},{"alias_kind":"pith_short_8","alias_value":"RVEGLZAN","created_at":"2026-07-05T11:43:08.667189+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25674","citing_title":"BitNet Text Embeddings","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30027","citing_title":"DocRetriever: A Plug-and-Play Framework for Multimodal Document Retrieval with Comprehensive Benchmark","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08809","citing_title":"SimReg: Achieving Higher Performance in the Pretraining via Embedding Similarity Regularization","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24374","citing_title":"MIPIC: Matryoshka Representation Learning via Self-Distilled Intra-Relational and Progressive Information Chaining","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07775","citing_title":"POETS: Uncertainty-Aware LLM Optimization via Compute-Efficient Policy Ensembles","ref_index":112,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17778","citing_title":"TeleEmbedBench: A Multi-Corpus Embedding Benchmark for RAG in Telecommunications","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RVEGLZANKI644B5S6KQWWJ4CS2","json":"https://pith.science/pith/RVEGLZANKI644B5S6KQWWJ4CS2.json","graph_json":"https://pith.science/api/pith-number/RVEGLZANKI644B5S6KQWWJ4CS2/graph.json","events_json":"https://pith.science/api/pith-number/RVEGLZANKI644B5S6KQWWJ4CS2/events.json","paper":"https://pith.science/paper/RVEGLZAN"},"agent_actions":{"view_html":"https://pith.science/pith/RVEGLZANKI644B5S6KQWWJ4CS2","download_json":"https://pith.science/pith/RVEGLZANKI644B5S6KQWWJ4CS2.json","view_paper":"https://pith.science/paper/RVEGLZAN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.12591&json=true","fetch_graph":"https://pith.science/api/pith-number/RVEGLZANKI644B5S6KQWWJ4CS2/graph.json","fetch_events":"https://pith.science/api/pith-number/RVEGLZANKI644B5S6KQWWJ4CS2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RVEGLZANKI644B5S6KQWWJ4CS2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RVEGLZANKI644B5S6KQWWJ4CS2/action/storage_attestation","attest_author":"https://pith.science/pith/RVEGLZANKI644B5S6KQWWJ4CS2/action/author_attestation","sign_citation":"https://pith.science/pith/RVEGLZANKI644B5S6KQWWJ4CS2/action/citation_signature","submit_replication":"https://pith.science/pith/RVEGLZANKI644B5S6KQWWJ4CS2/action/replication_record"}},"created_at":"2026-07-05T11:43:08.667189+00:00","updated_at":"2026-07-05T11:43:08.667189+00:00"}