{"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/the-locality-and-symmetry-of-positional","title":"The Locality and Symmetry of Positional Encodings","arxiv_id":"2310.12864","date":"2023-10-19","proceeding":null,"authors":["Lihu Chen","Gaël Varoquaux","Fabian M. Suchanek"],"abstract":"Positional Encodings (PEs) are used to inject word-order information into transformer-based language models. While they can significantly enhance the quality of sentence representations, their specific contribution to language models is not fully understood, especially given recent findings that various positional encodings are insensitive to word order. In this work, we conduct a systematic study of positional encodings in \\textbf{Bidirectional Masked Language Models} (BERT-style) , which complements existing work in three aspects: (1) We uncover the core function of PEs by identifying two common properties, Locality and Symmetry; (2) We show that the two properties are closely correlated with the performances of downstream tasks; (3) We quantify the weakness of current PEs by introducing two new probing tasks, on which current PEs perform poorly. We believe that these results are the basis for developing better PEs for transformer-based language models. The code is available at \\faGithub~ \\url{https://github.com/tigerchen52/locality\\_symmetry}","url_abs":"https://arxiv.org/abs/2310.12864v1","url_pdf":"https://arxiv.org/pdf/2310.12864v1.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":"the-locality-and-symmetry-of-positional","repo_url":"https://github.com/tigerchen52/locality_symmetry","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"CC0-1.0"}}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.12864","atlas_url":"https://app.syntology.ai/?focus=2310.12864","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12864"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/tigerchen52/locality_symmetry","reach":{"status":"ok","spdx":"CC0-1.0"}}],"summary":{"ran":9,"ran_honours":1},"by_repo_kind":{"official":{"samples":10,"ran":10,"repositories":1}},"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":0,"samples":[{"code_sha256_prefix":"de2ce5172b3752be","entry":"cal_matrix_symmetry","repo":"tigerchen52/locality_symmetry","repo_kind":"official","path":"locality_symmetry/calculate.py","file_url":"https://github.com/tigerchen52/locality_symmetry/blob/HEAD/locality_symmetry/calculate.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"de2ce5172b3752be"}},{"code_sha256_prefix":"476bd54c93ccef10","entry":"cal_pos_att","repo":"tigerchen52/locality_symmetry","repo_kind":"official","path":"experiments/model/bert.py","file_url":"https://github.com/tigerchen52/locality_symmetry/blob/HEAD/experiments/model/bert.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"476bd54c93ccef10"}},{"code_sha256_prefix":"762b5659955a9e61","entry":"dataset_class","repo":"tigerchen52/locality_symmetry","repo_kind":"official","path":"experiments/classify.py","file_url":"https://github.com/tigerchen52/locality_symmetry/blob/HEAD/experiments/classify.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"762b5659955a9e61"}},{"code_sha256_prefix":"62e7409a816626ac","entry":"gelu","repo":"tigerchen52/locality_symmetry","repo_kind":"official","path":"experiments/model/attenuated.py","file_url":"https://github.com/tigerchen52/locality_symmetry/blob/HEAD/experiments/model/attenuated.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"62e7409a816626ac"}},{"code_sha256_prefix":"d91346a6487413c0","entry":"get_pos_endcode","repo":"tigerchen52/locality_symmetry","repo_kind":"official","path":"experiments/model/attenuated.py","file_url":"https://github.com/tigerchen52/locality_symmetry/blob/HEAD/experiments/model/attenuated.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d91346a6487413c0"}},{"code_sha256_prefix":"022d46a269f1cc32","entry":"get_pre_cal_pa","repo":"tigerchen52/locality_symmetry","repo_kind":"official","path":"experiments/model/attenuated.py","file_url":"https://github.com/tigerchen52/locality_symmetry/blob/HEAD/experiments/model/attenuated.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"022d46a269f1cc32"}},{"code_sha256_prefix":"8bd3f7334af5c7b2","entry":"get_pre_cal_pa","repo":"tigerchen52/locality_symmetry","repo_kind":"official","path":"experiments/model/attenuated_l.py","file_url":"https://github.com/tigerchen52/locality_symmetry/blob/HEAD/experiments/model/attenuated_l.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8bd3f7334af5c7b2"}},{"code_sha256_prefix":"e945316d27e8b1b2","entry":"get_pre_cal_pa","repo":"tigerchen52/locality_symmetry","repo_kind":"official","path":"experiments/model/bert.py","file_url":"https://github.com/tigerchen52/locality_symmetry/blob/HEAD/experiments/model/bert.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e945316d27e8b1b2"}},{"code_sha256_prefix":"dc5a80cd186eef64","entry":"matrix_locality","repo":"tigerchen52/locality_symmetry","repo_kind":"official","path":"locality_symmetry/calculate.py","file_url":"https://github.com/tigerchen52/locality_symmetry/blob/HEAD/locality_symmetry/calculate.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dc5a80cd186eef64"}},{"code_sha256_prefix":"732b9918ceb2ca06","entry":"score_func","repo":"tigerchen52/locality_symmetry","repo_kind":"official","path":"experiments/classify.py","file_url":"https://github.com/tigerchen52/locality_symmetry/blob/HEAD/experiments/classify.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"732b9918ceb2ca06"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}