{"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/can-large-language-model-comprehend-ancient","title":"Can Large Language Model Comprehend Ancient Chinese? A Preliminary Test on ACLUE","arxiv_id":"2310.09550","date":"2023-10-14","proceeding":null,"authors":["Yixuan Zhang","Haonan Li"],"abstract":"Large language models (LLMs) have showcased remarkable capabilities in understanding and generating language. However, their ability in comprehending ancient languages, particularly ancient Chinese, remains largely unexplored. To bridge this gap, we present ACLUE, an evaluation benchmark designed to assess the capability of language models in comprehending ancient Chinese. ACLUE consists of 15 tasks cover a range of skills, spanning phonetic, lexical, syntactic, semantic, inference and knowledge. Through the evaluation of eight state-of-the-art LLMs, we observed a noticeable disparity in their performance between modern Chinese and ancient Chinese. Among the assessed models, ChatGLM2 demonstrates the most remarkable performance, achieving an average score of 37.4%. We have made our code and data public available.","url_abs":"https://arxiv.org/abs/2310.09550v1","url_pdf":"https://arxiv.org/pdf/2310.09550v1.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":"can-large-language-model-comprehend-ancient","repo_url":"https://github.com/isen-zhang/aclue","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[],"datasets_introduced":[{"slug":"aclue","name":"ACLUE","full_name":"Ancient Chinese Language Understanding Evaluation"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.09550","atlas_url":"https://app.syntology.ai/?focus=2310.09550","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.09550"}},"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/isen-zhang/aclue","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"ran":3,"unverified":1},"by_repo_kind":{"official":{"samples":5,"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":"19f01570b0a18e2b","entry":"softmax","repo":"isen-zhang/aclue","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/isen-zhang/aclue/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"19f01570b0a18e2b"}},{"code_sha256_prefix":"c7ad8ee11528e78b","entry":"format_example","repo":"isen-zhang/aclue","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/isen-zhang/aclue/blob/HEAD/src/utils.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":"c7ad8ee11528e78b"}},{"code_sha256_prefix":"9cbcb7e3d68900c3","entry":"gen_prompt","repo":"isen-zhang/aclue","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/isen-zhang/aclue/blob/HEAD/src/utils.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":"9cbcb7e3d68900c3"}},{"code_sha256_prefix":"0df614fff2114f23","entry":"get_response","repo":"isen-zhang/aclue","repo_kind":"official","path":"src/chatgpt.py","file_url":"https://github.com/isen-zhang/aclue/blob/HEAD/src/chatgpt.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":"0df614fff2114f23"}},{"code_sha256_prefix":"d0da2ec45f606dab","entry":"get_response","repo":"isen-zhang/aclue","repo_kind":"official","path":"src/gpt4.py","file_url":"https://github.com/isen-zhang/aclue/blob/HEAD/src/gpt4.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d0da2ec45f606dab"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}