{"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/stress-test-evaluation-for-natural-language","title":"Stress Test Evaluation for Natural Language Inference","arxiv_id":"1806.00692","date":"2018-06-02","proceeding":"COLING 2018 8","authors":["Aakanksha Naik","Abhilasha Ravichander","Norman Sadeh","Carolyn Rose","Graham Neubig"],"abstract":"Natural language inference (NLI) is the task of determining if a natural\nlanguage hypothesis can be inferred from a given premise in a justifiable\nmanner. NLI was proposed as a benchmark task for natural language\nunderstanding. Existing models perform well at standard datasets for NLI,\nachieving impressive results across different genres of text. However, the\nextent to which these models understand the semantic content of sentences is\nunclear. In this work, we propose an evaluation methodology consisting of\nautomatically constructed \"stress tests\" that allow us to examine whether\nsystems have the ability to make real inferential decisions. Our evaluation of\nsix sentence-encoder models on these stress tests reveals strengths and\nweaknesses of these models with respect to challenging linguistic phenomena,\nand suggests important directions for future work in this area.","url_abs":"http://arxiv.org/abs/1806.00692v3","url_pdf":"http://arxiv.org/pdf/1806.00692v3.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":"stress-test-evaluation-for-natural-language","repo_url":"https://github.com/AbhilashaRavichander/NLI_StressTest","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.00692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.00692"}},"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/AbhilashaRavichander/NLI_StressTest","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"listed":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"e8a668be25c1be3f","entry":"get_contradictory_hypothesis","repo":"AbhilashaRavichander/NLI_StressTest","repo_kind":"listed","path":"quant_example_gen.py","file_url":"https://github.com/AbhilashaRavichander/NLI_StressTest/blob/HEAD/quant_example_gen.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e8a668be25c1be3f"}},{"code_sha256_prefix":"e96492d019d70e2c","entry":"get_entailed_hypothesis","repo":"AbhilashaRavichander/NLI_StressTest","repo_kind":"listed","path":"quant_example_gen.py","file_url":"https://github.com/AbhilashaRavichander/NLI_StressTest/blob/HEAD/quant_example_gen.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e96492d019d70e2c"}},{"code_sha256_prefix":"5e57b85ad9e2d8ee","entry":"tokenize","repo":"AbhilashaRavichander/NLI_StressTest","repo_kind":"listed","path":"gen_num_test.py","file_url":"https://github.com/AbhilashaRavichander/NLI_StressTest/blob/HEAD/gen_num_test.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5e57b85ad9e2d8ee"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}