{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/repetition-improves-language-model-embeddings","title":"Repetition Improves Language Model Embeddings","arxiv_id":"2402.15449","date":"2024-02-23","proceeding":null,"authors":["Jacob Mitchell Springer","Suhas Kotha","Daniel Fried","Graham Neubig","aditi raghunathan"],"abstract":"Recent approaches to improving the extraction of text embeddings from autoregressive large language models (LLMs) have largely focused on improvements to data, backbone pretrained language models, or improving task-differentiation via instructions. In this work, we address an architectural limitation of autoregressive models: token embeddings cannot contain information from tokens that appear later in the input. To address this limitation, we propose a simple approach, \"echo embeddings,\" in which we repeat the input twice in context and extract embeddings from the second occurrence. We show that echo embeddings of early tokens can encode information about later tokens, allowing us to maximally leverage high-quality LLMs for embeddings. On the MTEB leaderboard, echo embeddings improve over classical embeddings by over 9% zero-shot and by around 0.7% when fine-tuned. Echo embeddings with a Mistral-7B model achieve state-of-the-art compared to prior open source models that do not leverage synthetic fine-tuning data.","url_abs":"https://arxiv.org/abs/2402.15449v1","url_pdf":"https://arxiv.org/pdf/2402.15449v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"repetition-improves-language-model-embeddings","repo_url":"https://github.com/jakespringer/echo-embeddings","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"repetition-improves-language-model-embeddings","repo_url":"https://github.com/mcgill-nlp/llm2vec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"repetition-improves-language-model-embeddings","repo_url":"https://github.com/neuir/llm-qe","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"repetition-improves-language-model-embeddings","repo_url":"https://github.com/openbmb/debater","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2402.15449","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15449"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/openbmb/debater","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mcgill-nlp/llm2vec","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jakespringer/echo-embeddings","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/neuir/llm-qe","reach":null}],"summary":{"ran":2,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":2,"ran":1,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"d764b2d25ca4c5ef","entry":"EchoEmbeddingsMistral","repo":"jakespringer/echo-embeddings","repo_kind":"official","path":"echo_embeddings.py","file_url":"https://github.com/jakespringer/echo-embeddings/blob/HEAD/echo_embeddings.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d764b2d25ca4c5ef"}},{"code_sha256_prefix":"54cf155a7282e094","entry":"LLM2Vec","repo":"openbmb/debater","repo_kind":"listed","path":"llm2vec/llm2vec.py","file_url":"https://github.com/openbmb/debater/blob/HEAD/llm2vec/llm2vec.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"54cf155a7282e094"}},{"code_sha256_prefix":"74b280cb6a91117e","entry":"batch_to_device","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"74b280cb6a91117e"}},{"code_sha256_prefix":"8773b7cc3b3fff25","entry":"FlagModel","repo":"neuir/llm-qe","repo_kind":"listed","path":"src/flagmodel.py","file_url":"https://github.com/neuir/llm-qe/blob/HEAD/src/flagmodel.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8773b7cc3b3fff25"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}