{"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/probing-language-models-for-understanding-of","title":"Probing Language Models for Understanding of Temporal Expressions","arxiv_id":"2110.01113","date":"2021-10-03","proceeding":"EMNLP (BlackboxNLP) 2021 11","authors":["Shivin Thukral","Kunal Kukreja","Christian Kavouras"],"abstract":"We present three Natural Language Inference (NLI) challenge sets that can evaluate NLI models on their understanding of temporal expressions. More specifically, we probe these models for three temporal properties: (a) the order between points in time, (b) the duration between two points in time, (c) the relation between the magnitude of times specified in different units. We find that although large language models fine-tuned on MNLI have some basic perception of the order between points in time, at large, these models do not have a thorough understanding of the relation between temporal expressions.","url_abs":"https://arxiv.org/abs/2110.01113v1","url_pdf":"https://arxiv.org/pdf/2110.01113v1.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":"probing-language-models-for-understanding-of","repo_url":"https://github.com/kunalkukreja21/temporal-expressions-evaluation-lm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"probing-language-models","task_name":"Probing Language Models"},{"task_slug":null,"task_name":"Relation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.01113","atlas_url":"https://app.syntology.ai/?focus=2110.01113","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.01113"}},"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/kunalkukreja21/temporal-expressions-evaluation-lm","reach":null}],"summary":{"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":"23ef2be8fb64aa1b","entry":"genOrderingPairList","repo":"kunalkukreja21/temporal-expressions-evaluation-lm","repo_kind":"official","path":"code/cs1.py","file_url":"https://github.com/kunalkukreja21/temporal-expressions-evaluation-lm/blob/HEAD/code/cs1.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"23ef2be8fb64aa1b"}},{"code_sha256_prefix":"4c61b4909935abbc","entry":"relationString","repo":"kunalkukreja21/temporal-expressions-evaluation-lm","repo_kind":"official","path":"code/cs1.py","file_url":"https://github.com/kunalkukreja21/temporal-expressions-evaluation-lm/blob/HEAD/code/cs1.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4c61b4909935abbc"}},{"code_sha256_prefix":"5ae7314659068802","entry":"genOrderingDatePairs","repo":"kunalkukreja21/temporal-expressions-evaluation-lm","repo_kind":"official","path":"code/cs1.py","file_url":"https://github.com/kunalkukreja21/temporal-expressions-evaluation-lm/blob/HEAD/code/cs1.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5ae7314659068802"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}