{"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/calibrated-interpretation-confidence","title":"Calibrated Interpretation: Confidence Estimation in Semantic Parsing","arxiv_id":"2211.07443","date":"2022-11-14","proceeding":null,"authors":["Elias Stengel-Eskin","Benjamin Van Durme"],"abstract":"Sequence generation models are increasingly being used to translate natural language into programs, i.e. to perform executable semantic parsing. The fact that semantic parsing aims to predict programs that can lead to executed actions in the real world motivates developing safe systems. This in turn makes measuring calibration -- a central component to safety -- particularly important. We investigate the calibration of popular generation models across four popular semantic parsing datasets, finding that it varies across models and datasets. We then analyze factors associated with calibration error and release new confidence-based challenge splits of two parsing datasets. To facilitate the inclusion of calibration in semantic parsing evaluations, we release a library for computing calibration metrics.","url_abs":"https://arxiv.org/abs/2211.07443v6","url_pdf":"https://arxiv.org/pdf/2211.07443v6.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":"calibrated-interpretation-confidence","repo_url":"https://github.com/esteng/calibration_metric","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"calibrated-interpretation-confidence","repo_url":"https://github.com/esteng/calibration_miso","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"}],"methods":[{"method_slug":null,"method_name":"Library"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.07443","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.07443"}},"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/esteng/calibration_metric","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/esteng/calibration_miso","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"unverified":8},"by_repo_kind":{"official":{"samples":9,"ran":1,"repositories":2}},"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":1,"samples":[{"code_sha256_prefix":"d2a31edb99a4fdfa","entry":"plot_df","repo":"esteng/calibration_metric","repo_kind":"official","path":"calibration_metric/vis/calibration_plot.py","file_url":"https://github.com/esteng/calibration_metric/blob/HEAD/calibration_metric/vis/calibration_plot.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d2a31edb99a4fdfa"}},{"code_sha256_prefix":"326bcd08f41f0633","entry":"get_and_tokenize","repo":"esteng/calibration_miso","repo_kind":"official","path":"analysis/calibration_sql_lm.py","file_url":"https://github.com/esteng/calibration_miso/blob/HEAD/analysis/calibration_sql_lm.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":"326bcd08f41f0633"}},{"code_sha256_prefix":"7136734fee77a93e","entry":"get_dataloader","repo":"esteng/calibration_miso","repo_kind":"official","path":"analysis/calibration_sql_lstm_lm.py","file_url":"https://github.com/esteng/calibration_miso/blob/HEAD/analysis/calibration_sql_lstm_lm.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":"7136734fee77a93e"}},{"code_sha256_prefix":"3b28e76018403525","entry":"get_low_prob","repo":"esteng/calibration_miso","repo_kind":"official","path":"analysis/calibration_ensemble.py","file_url":"https://github.com/esteng/calibration_miso/blob/HEAD/analysis/calibration_ensemble.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":"3b28e76018403525"}},{"code_sha256_prefix":"292f09d035dd264e","entry":"get_low_prob","repo":"esteng/calibration_miso","repo_kind":"official","path":"analysis/calibration_make_data_splits.py","file_url":"https://github.com/esteng/calibration_miso/blob/HEAD/analysis/calibration_make_data_splits.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":"292f09d035dd264e"}},{"code_sha256_prefix":"3c84fab5b11ff0ff","entry":"get_low_prob_idxs","repo":"esteng/calibration_miso","repo_kind":"official","path":"analysis/calibration_make_data_splits.py","file_url":"https://github.com/esteng/calibration_miso/blob/HEAD/analysis/calibration_make_data_splits.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":"3c84fab5b11ff0ff"}},{"code_sha256_prefix":"679c1b4f3abe2d88","entry":"get_ppl","repo":"esteng/calibration_miso","repo_kind":"official","path":"analysis/calibration_sql_lstm_lm.py","file_url":"https://github.com/esteng/calibration_miso/blob/HEAD/analysis/calibration_sql_lstm_lm.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":"679c1b4f3abe2d88"}},{"code_sha256_prefix":"162f3413a0413984","entry":"read_data","repo":"esteng/calibration_miso","repo_kind":"official","path":"analysis/calibration_sql_lm.py","file_url":"https://github.com/esteng/calibration_miso/blob/HEAD/analysis/calibration_sql_lm.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":"162f3413a0413984"}},{"code_sha256_prefix":"fb231fe58ed02d5a","entry":"read_test_data","repo":"esteng/calibration_miso","repo_kind":"official","path":"analysis/calibration_sql_lm.py","file_url":"https://github.com/esteng/calibration_miso/blob/HEAD/analysis/calibration_sql_lm.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":"fb231fe58ed02d5a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}