{"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/testing-the-ability-of-language-models-to-1","title":"Testing the Ability of Language Models to Interpret Figurative Language","arxiv_id":"2204.12632","date":"2022-04-26","proceeding":"NAACL 2022 7","authors":["Emmy Liu","Chen Cui","Kenneth Zheng","Graham Neubig"],"abstract":"Figurative and metaphorical language are commonplace in discourse, and figurative expressions play an important role in communication and cognition. However, figurative language has been a relatively under-studied area in NLP, and it remains an open question to what extent modern language models can interpret nonliteral phrases. To address this question, we introduce Fig-QA, a Winograd-style nonliteral language understanding task consisting of correctly interpreting paired figurative phrases with divergent meanings. We evaluate the performance of several state-of-the-art language models on this task, and find that although language models achieve performance significantly over chance, they still fall short of human performance, particularly in zero- or few-shot settings. This suggests that further work is needed to improve the nonliteral reasoning capabilities of language models.","url_abs":"https://arxiv.org/abs/2204.12632v2","url_pdf":"https://arxiv.org/pdf/2204.12632v2.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":"testing-the-ability-of-language-models-to-1","repo_url":"https://github.com/nightingal3/fig-qa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"testing-the-ability-of-language-models-to-1","repo_url":"https://github.com/simran-khanuja/multilingual-fig-qa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"open-question","task_name":"Open-Ended Question Answering"}],"methods":[],"datasets_introduced":[{"slug":"fig-qa","name":"Fig-QA","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2204.12632","atlas_url":"https://app.syntology.ai/?focus=2204.12632","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.12632"}},"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/nightingal3/fig-qa","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/simran-khanuja/multilingual-fig-qa","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"ran_draft_wrong":1,"unverified":9},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":1},"listed":{"samples":12,"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":"31e5d4061c0165ee","entry":"eval_model","repo":"simran-khanuja/multilingual-fig-qa","repo_kind":"listed","path":"run_baselines.py","file_url":"https://github.com/simran-khanuja/multilingual-fig-qa/blob/HEAD/run_baselines.py","link_basis":"harvester_set","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":"31e5d4061c0165ee"}},{"code_sha256_prefix":"2a5615f598f3af2b","entry":"evaluate_model","repo":"nightingal3/fig-qa","repo_kind":"official","path":"src/models/gpt_score.py","file_url":"https://github.com/nightingal3/fig-qa/blob/HEAD/src/models/gpt_score.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2a5615f598f3af2b"}},{"code_sha256_prefix":"21007e567ee7726b","entry":"is_subarray","repo":"simran-khanuja/multilingual-fig-qa","repo_kind":"listed","path":"get_syntax_chunks.py","file_url":"https://github.com/simran-khanuja/multilingual-fig-qa/blob/HEAD/get_syntax_chunks.py","link_basis":"harvester_set","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":"21007e567ee7726b"}},{"code_sha256_prefix":"454507be28be36dd","entry":"main_train_loop","repo":"simran-khanuja/multilingual-fig-qa","repo_kind":"listed","path":"run_baselines.py","file_url":"https://github.com/simran-khanuja/multilingual-fig-qa/blob/HEAD/run_baselines.py","link_basis":"harvester_set","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":"454507be28be36dd"}},{"code_sha256_prefix":"62a67c92331edd10","entry":"substring_between","repo":"simran-khanuja/multilingual-fig-qa","repo_kind":"listed","path":"get_syntax_chunks.py","file_url":"https://github.com/simran-khanuja/multilingual-fig-qa/blob/HEAD/get_syntax_chunks.py","link_basis":"harvester_set","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":"62a67c92331edd10"}},{"code_sha256_prefix":"4f74b4458496f1dc","entry":"convert_examples_to_features","repo":"simran-khanuja/multilingual-fig-qa","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/simran-khanuja/multilingual-fig-qa/blob/HEAD/utils.py","link_basis":"harvester_set","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":"4f74b4458496f1dc"}},{"code_sha256_prefix":"a7ffc645f7b1c747","entry":"convert_multiple_choice_examples_to_features","repo":"simran-khanuja/multilingual-fig-qa","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/simran-khanuja/multilingual-fig-qa/blob/HEAD/utils.py","link_basis":"harvester_set","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":"a7ffc645f7b1c747"}},{"code_sha256_prefix":"10b84b6e2e00afe1","entry":"get_hypernyms","repo":"simran-khanuja/multilingual-fig-qa","repo_kind":"listed","path":"plot_parsed_data.py","file_url":"https://github.com/simran-khanuja/multilingual-fig-qa/blob/HEAD/plot_parsed_data.py","link_basis":"harvester_set","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":"10b84b6e2e00afe1"}},{"code_sha256_prefix":"16090c8ed2178c61","entry":"get_pos_tags","repo":"simran-khanuja/multilingual-fig-qa","repo_kind":"listed","path":"plot_parsed_data.py","file_url":"https://github.com/simran-khanuja/multilingual-fig-qa/blob/HEAD/plot_parsed_data.py","link_basis":"harvester_set","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":"16090c8ed2178c61"}},{"code_sha256_prefix":"792128008f28fb12","entry":"lemmatize_words","repo":"simran-khanuja/multilingual-fig-qa","repo_kind":"listed","path":"plot_parsed_data.py","file_url":"https://github.com/simran-khanuja/multilingual-fig-qa/blob/HEAD/plot_parsed_data.py","link_basis":"harvester_set","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":"792128008f28fb12"}},{"code_sha256_prefix":"581a4523d21cb660","entry":"remove_substrings","repo":"simran-khanuja/multilingual-fig-qa","repo_kind":"listed","path":"get_syntax_chunks.py","file_url":"https://github.com/simran-khanuja/multilingual-fig-qa/blob/HEAD/get_syntax_chunks.py","link_basis":"harvester_set","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":"581a4523d21cb660"}},{"code_sha256_prefix":"39cf438241a8d1dd","entry":"sent_scoring","repo":"nightingal3/fig-qa","repo_kind":"official","path":"src/models/gpt_score.py","file_url":"https://github.com/nightingal3/fig-qa/blob/HEAD/src/models/gpt_score.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":"39cf438241a8d1dd"}},{"code_sha256_prefix":"3c241ecfe3749a6d","entry":"simple_accuracy","repo":"simran-khanuja/multilingual-fig-qa","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/simran-khanuja/multilingual-fig-qa/blob/HEAD/utils.py","link_basis":"harvester_set","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":"3c241ecfe3749a6d"}},{"code_sha256_prefix":"e7b3e41b3b961fb4","entry":"train_model","repo":"simran-khanuja/multilingual-fig-qa","repo_kind":"listed","path":"run_baselines.py","file_url":"https://github.com/simran-khanuja/multilingual-fig-qa/blob/HEAD/run_baselines.py","link_basis":"harvester_set","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":"e7b3e41b3b961fb4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}