{"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/obtaining-faithful-interpretations-from","title":"Obtaining Faithful Interpretations from Compositional Neural Networks","arxiv_id":"2005.00724","date":"2020-05-02","proceeding":"ACL 2020 6","authors":["Sanjay Subramanian","Ben Bogin","Nitish Gupta","Tomer Wolfson","Sameer Singh","Jonathan Berant","Matt Gardner"],"abstract":"Neural module networks (NMNs) are a popular approach for modeling compositionality: they achieve high accuracy when applied to problems in language and vision, while reflecting the compositional structure of the problem in the network architecture. However, prior work implicitly assumed that the structure of the network modules, describing the abstract reasoning process, provides a faithful explanation of the model's reasoning; that is, that all modules perform their intended behaviour. In this work, we propose and conduct a systematic evaluation of the intermediate outputs of NMNs on NLVR2 and DROP, two datasets which require composing multiple reasoning steps. We find that the intermediate outputs differ from the expected output, illustrating that the network structure does not provide a faithful explanation of model behaviour. To remedy that, we train the model with auxiliary supervision and propose particular choices for module architecture that yield much better faithfulness, at a minimal cost to accuracy.","url_abs":"https://arxiv.org/abs/2005.00724v2","url_pdf":"https://arxiv.org/pdf/2005.00724v2.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":"obtaining-faithful-interpretations-from","repo_url":"https://github.com/allenai/faithful-nmn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2005.00724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00724"}},"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/allenai/faithful-nmn","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"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":"c91ead5152ed16e3","entry":"annotation_to_lisp_exp","repo":"allenai/faithful-nmn","repo_kind":"official","path":"lib/dataset_readers/reader_utils.py","file_url":"https://github.com/allenai/faithful-nmn/blob/HEAD/lib/dataset_readers/reader_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c91ead5152ed16e3"}},{"code_sha256_prefix":"bd302aafd64b392f","entry":"annotation_to_module_attention","repo":"allenai/faithful-nmn","repo_kind":"official","path":"lib/dataset_readers/reader_utils.py","file_url":"https://github.com/allenai/faithful-nmn/blob/HEAD/lib/dataset_readers/reader_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bd302aafd64b392f"}},{"code_sha256_prefix":"4321df4fa827e85b","entry":"target_sequence_to_target_boxes","repo":"allenai/faithful-nmn","repo_kind":"official","path":"lib/dataset_readers/reader_utils.py","file_url":"https://github.com/allenai/faithful-nmn/blob/HEAD/lib/dataset_readers/reader_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4321df4fa827e85b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}