{"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/faithfulness-tests-for-natural-language","title":"Faithfulness Tests for Natural Language Explanations","arxiv_id":"2305.18029","date":"2023-05-29","proceeding":null,"authors":["Pepa Atanasova","Oana-Maria Camburu","Christina Lioma","Thomas Lukasiewicz","Jakob Grue Simonsen","Isabelle Augenstein"],"abstract":"Explanations of neural models aim to reveal a model's decision-making process for its predictions. However, recent work shows that current methods giving explanations such as saliency maps or counterfactuals can be misleading, as they are prone to present reasons that are unfaithful to the model's inner workings. This work explores the challenging question of evaluating the faithfulness of natural language explanations (NLEs). To this end, we present two tests. First, we propose a counterfactual input editor for inserting reasons that lead to counterfactual predictions but are not reflected by the NLEs. Second, we reconstruct inputs from the reasons stated in the generated NLEs and check how often they lead to the same predictions. Our tests can evaluate emerging NLE models, proving a fundamental tool in the development of faithful NLEs.","url_abs":"https://arxiv.org/abs/2305.18029v2","url_pdf":"https://arxiv.org/pdf/2305.18029v2.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":"faithfulness-tests-for-natural-language","repo_url":"https://github.com/copenlu/nle_faithfulness","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":null,"task_name":"counterfactual"}],"methods":[{"method_slug":"counterfactuals","method_name":"Counterfactuals"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.18029","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18029"}},"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/copenlu/nle_faithfulness","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":3,"samples":[{"code_sha256_prefix":"58dd46c259689999","entry":"T5_sample","repo":"copenlu/nle_faithfulness","repo_kind":"official","path":"LAS-NL-Explanations/sim_experiments/counterfactual/counterfactual_editor.py","file_url":"https://github.com/copenlu/nle_faithfulness/blob/HEAD/LAS-NL-Explanations/sim_experiments/counterfactual/counterfactual_editor.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"58dd46c259689999"}},{"code_sha256_prefix":"fb9f7f202818de15","entry":"detok_batch","repo":"copenlu/nle_faithfulness","repo_kind":"official","path":"LAS-NL-Explanations/sim_experiments/counterfactual/counterfactual_editor.py","file_url":"https://github.com/copenlu/nle_faithfulness/blob/HEAD/LAS-NL-Explanations/sim_experiments/counterfactual/counterfactual_editor.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fb9f7f202818de15"}},{"code_sha256_prefix":"862656102baa4813","entry":"eval_examples","repo":"copenlu/nle_faithfulness","repo_kind":"official","path":"LAS-NL-Explanations/sim_experiments/counterfactual/counterfactual_editor.py","file_url":"https://github.com/copenlu/nle_faithfulness/blob/HEAD/LAS-NL-Explanations/sim_experiments/counterfactual/counterfactual_editor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"862656102baa4813"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}