{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/analyzing-compositionality-sensitivity-of-nli","title":"Analyzing Compositionality-Sensitivity of NLI Models","arxiv_id":"1811.07033","date":"2018-11-16","proceeding":null,"authors":["Yixin Nie","Yicheng Wang","Mohit Bansal"],"abstract":"Success in natural language inference (NLI) should require a model to\nunderstand both lexical and compositional semantics. However, through\nadversarial evaluation, we find that several state-of-the-art models with\ndiverse architectures are over-relying on the former and fail to use the\nlatter. Further, this compositionality unawareness is not reflected via\nstandard evaluation on current datasets. We show that removing RNNs in existing\nmodels or shuffling input words during training does not induce large\nperformance loss despite the explicit removal of compositional information.\nTherefore, we propose a compositionality-sensitivity testing setup that\nanalyzes models on natural examples from existing datasets that cannot be\nsolved via lexical features alone (i.e., on which a bag-of-words model gives a\nhigh probability to one wrong label), hence revealing the models' actual\ncompositionality awareness. We show that this setup not only highlights the\nlimited compositional ability of current NLI models, but also differentiates\nmodel performance based on design, e.g., separating shallow bag-of-words models\nfrom deeper, linguistically-grounded tree-based models. Our evaluation setup is\nan important analysis tool: complementing currently existing adversarial and\nlinguistically driven diagnostic evaluations, and exposing opportunities for\nfuture work on evaluating models' compositional understanding.","url_abs":"http://arxiv.org/abs/1811.07033v1","url_pdf":"http://arxiv.org/pdf/1811.07033v1.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":"analyzing-compositionality-sensitivity-of-nli","repo_url":"https://github.com/easonnie/analyze-compositionality-sensitivity-NLI","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diagnostic","task_name":"Diagnostic"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"sensitivity","task_name":"Sensitivity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1811.07033","atlas_url":"https://app.syntology.ai/?focus=1811.07033","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1811.07033"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1811.07033\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1811.07033"},"call":"get_concepts_for_paper(arxiv_id=\"1811.07033\")"}],"by_repo":[{"repo":"easonnie/analyze-compositionality-sensitivity-NLI","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"01ae76fcac78d8016fbef3f5bea4546e39634989b4ea33ab86279be50e6d6574","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}