{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/angle-optimized-text-embeddings","title":"AnglE-optimized Text Embeddings","arxiv_id":"2309.12871","date":"2023-09-22","proceeding":null,"authors":["Xianming Li","Jing Li"],"abstract":"High-quality text embedding is pivotal in improving semantic textual similarity (STS) tasks, which are crucial components in Large Language Model (LLM) applications. However, a common challenge existing text embedding models face is the problem of vanishing gradients, primarily due to their reliance on the cosine function in the optimization objective, which has saturation zones. To address this issue, this paper proposes a novel angle-optimized text embedding model called AnglE. The core idea of AnglE is to introduce angle optimization in a complex space. This novel approach effectively mitigates the adverse effects of the saturation zone in the cosine function, which can impede gradient and hinder optimization processes. To set up a comprehensive STS evaluation, we experimented on existing short-text STS datasets and a newly collected long-text STS dataset from GitHub Issues. Furthermore, we examine domain-specific STS scenarios with limited labeled data and explore how AnglE works with LLM-annotated data. Extensive experiments were conducted on various tasks including short-text STS, long-text STS, and domain-specific STS tasks. The results show that AnglE outperforms the state-of-the-art (SOTA) STS models that ignore the cosine saturation zone. These findings demonstrate the ability of AnglE to generate high-quality text embeddings and the usefulness of angle optimization in STS.","url_abs":"https://arxiv.org/abs/2309.12871v9","url_pdf":"https://arxiv.org/pdf/2309.12871v9.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":"angle-optimized-text-embeddings","repo_url":"https://github.com/SeanLee97/AnglE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"angle-optimized-text-embeddings","repo_url":"https://github.com/4ai/bellm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"sts","task_name":"STS"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[],"datasets_introduced":[{"slug":"gis","name":"GIS","full_name":"Github Issue Similarity"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-textual-similarity-on-mteb","task":"Semantic Textual Similarity","dataset":"MTEB","model":"AnglE-UAE","rank_in_archive_order":1,"of":30,"metrics":{"Spearman Correlation":"84.54"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sick-r-1","task":"Semantic Textual Similarity","dataset":"SICK-R","model":"AnglE-LLaMA-7B","rank_in_archive_order":1,"of":2,"metrics":{"Spearman Correlation":"0.8094"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sick-r-1","task":"Semantic Textual Similarity","dataset":"SICK-R","model":"AnglE-LLaMA-13B","rank_in_archive_order":2,"of":2,"metrics":{"Spearman Correlation":"0. 8132"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts-benchmark","task":"Semantic Textual Similarity","dataset":"STS Benchmark","model":"AnglE-LLaMA-13B","rank_in_archive_order":30,"of":66,"metrics":{"Spearman Correlation":"0.8969"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts-benchmark","task":"Semantic Textual Similarity","dataset":"STS Benchmark","model":"AnglE-LLaMA-7B","rank_in_archive_order":33,"of":66,"metrics":{"Spearman Correlation":"0.8897"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts-benchmark","task":"Semantic Textual Similarity","dataset":"STS Benchmark","model":"AnglE-LLaMA-7B-v2","rank_in_archive_order":34,"of":66,"metrics":{"Spearman Correlation":"0.8897"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts12","task":"Semantic Textual Similarity","dataset":"STS12","model":"AnglE-LLaMA-7B","rank_in_archive_order":5,"of":20,"metrics":{"Spearman Correlation":"0.7868"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts12","task":"Semantic Textual Similarity","dataset":"STS12","model":"AnglE-LLaMA-13B","rank_in_archive_order":6,"of":20,"metrics":{"Spearman Correlation":"0.7868"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts13","task":"Semantic Textual Similarity","dataset":"STS13","model":"AnglE-LLaMA-7B","rank_in_archive_order":1,"of":22,"metrics":{"Spearman Correlation":"0.9058"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts13","task":"Semantic Textual Similarity","dataset":"STS13","model":"AnglE-LLaMA-7B-v2","rank_in_archive_order":2,"of":22,"metrics":{"Spearman Correlation":"0.9056"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts14","task":"Semantic Textual Similarity","dataset":"STS14","model":"AnglE-LLaMA-13B","rank_in_archive_order":1,"of":21,"metrics":{"Spearman Correlation":"0.8689"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts14","task":"Semantic Textual Similarity","dataset":"STS14","model":"AnglE-LLaMA-7B-v2","rank_in_archive_order":3,"of":21,"metrics":{"Spearman Correlation":"0.8579"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts14","task":"Semantic Textual Similarity","dataset":"STS14","model":"AnglE-LLaMA-7B","rank_in_archive_order":4,"of":21,"metrics":{"Spearman Correlation":"0.8549"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts15","task":"Semantic Textual Similarity","dataset":"STS15","model":"AnglE-LLaMA-13B","rank_in_archive_order":2,"of":20,"metrics":{"Spearman Correlation":"0.8956"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts15","task":"Semantic Textual Similarity","dataset":"STS15","model":"AnglE-LLaMA-7B-v2","rank_in_archive_order":5,"of":20,"metrics":{"Spearman Correlation":"0.8943"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts16","task":"Semantic Textual Similarity","dataset":"STS16","model":"AnglE-LLaMA-7B-v2","rank_in_archive_order":1,"of":20,"metrics":{"Spearman Correlation":"0.8700"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts16","task":"Semantic Textual Similarity","dataset":"STS16","model":"AnglE-LLaMA-13B","rank_in_archive_order":2,"of":20,"metrics":{"Spearman Correlation":"0.8700"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts16","task":"Semantic Textual Similarity","dataset":"STS16","model":"AnglE-LLaMA-7B","rank_in_archive_order":3,"of":20,"metrics":{"Spearman Correlation":"0.8691"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-cr","task":"Sentiment Analysis","dataset":"CR","model":"AnglE-LLaMA-7B","rank_in_archive_order":1,"of":9,"metrics":{"Accuracy":"93.54"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-mr","task":"Sentiment Analysis","dataset":"MR","model":"AnglE-LLaMA-7B","rank_in_archive_order":3,"of":19,"metrics":{"Accuracy":"91.09"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2309.12871","atlas_url":"https://app.syntology.ai/?focus=2309.12871","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2309.12871"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2309.12871\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2309.12871"},"call":"get_concepts_for_paper(arxiv_id=\"2309.12871\")"}],"by_repo":[{"repo":"SeanLee97/AnglE","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2311.05296"],"harvested_for_calls":[{"arxiv_id":"2311.05296","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2311.05296"},"call":"get_harvested_code_for_paper(arxiv_id=\"2311.05296\")"}]},{"repo":"4ai/bellm","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"eda6af48bf918886e69230cafdc665653a1703f2a141430c8f3669d2f3358d63","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}