{"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/cute-measuring-llms-understanding-of-their","title":"CUTE: Measuring LLMs' Understanding of Their Tokens","arxiv_id":"2409.15452","date":"2024-09-23","proceeding":null,"authors":["Lukas Edman","Helmut Schmid","Alexander Fraser"],"abstract":"Large Language Models (LLMs) show remarkable performance on a wide variety of tasks. Most LLMs split text into multi-character tokens and process them as atomic units without direct access to individual characters. This raises the question: To what extent can LLMs learn orthographic information? To answer this, we propose a new benchmark, CUTE, which features a collection of tasks designed to test the orthographic knowledge of LLMs. We evaluate popular LLMs on CUTE, finding that most of them seem to know the spelling of their tokens, yet fail to use this information effectively to manipulate text, calling into question how much of this knowledge is generalizable.","url_abs":"https://arxiv.org/abs/2409.15452v2","url_pdf":"https://arxiv.org/pdf/2409.15452v2.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":"cute-measuring-llms-understanding-of-their","repo_url":"https://github.com/leukas/cute","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.15452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.15452"}},"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/leukas/cute","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":"1ef70d8be309684d","entry":"gen_random","repo":"leukas/cute","repo_kind":"official","path":"data_gen/gen_char_tasks.py","file_url":"https://github.com/leukas/cute/blob/HEAD/data_gen/gen_char_tasks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1ef70d8be309684d"}},{"code_sha256_prefix":"05b0af049f82ce2c","entry":"get_and_sort_near_spells","repo":"leukas/cute","repo_kind":"official","path":"data_gen/gen_sem_orth.py","file_url":"https://github.com/leukas/cute/blob/HEAD/data_gen/gen_sem_orth.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"05b0af049f82ce2c"}},{"code_sha256_prefix":"4b2c2cdfe762b8ed","entry":"load_fasttext","repo":"leukas/cute","repo_kind":"official","path":"data_gen/gen_sem_orth.py","file_url":"https://github.com/leukas/cute/blob/HEAD/data_gen/gen_sem_orth.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4b2c2cdfe762b8ed"}},{"code_sha256_prefix":"88f4097fd3667925","entry":"replace_plus_one","repo":"leukas/cute","repo_kind":"official","path":"data_gen/gen_char_tasks.py","file_url":"https://github.com/leukas/cute/blob/HEAD/data_gen/gen_char_tasks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"88f4097fd3667925"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}