{"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/iterated-decomposition-improving-science-q-a","title":"Iterated Decomposition: Improving Science Q&A by Supervising Reasoning Processes","arxiv_id":"2301.01751","date":"2023-01-04","proceeding":null,"authors":["Justin Reppert","Ben Rachbach","Charlie George","Luke Stebbing","Jungwon Byun","Maggie Appleton","Andreas Stuhlmüller"],"abstract":"Language models (LMs) can perform complex reasoning either end-to-end, with hidden latent state, or compositionally, with transparent intermediate state. Composition offers benefits for interpretability and safety, but may need workflow support and infrastructure to remain competitive. We describe iterated decomposition, a human-in-the-loop workflow for developing and refining compositional LM programs. We improve the performance of compositions by zooming in on failing components and refining them through decomposition, additional context, chain of thought, etc. To support this workflow, we develop ICE, an open-source tool for visualizing the execution traces of LM programs. We apply iterated decomposition to three real-world tasks and improve the accuracy of LM programs over less compositional baselines: describing the placebo used in a randomized controlled trial (25% to 65%), evaluating participant adherence to a medical intervention (53% to 70%), and answering NLP questions on the Qasper dataset (38% to 69%). These applications serve as case studies for a workflow that, if automated, could keep ML systems interpretable and safe even as they scale to increasingly complex tasks.","url_abs":"https://arxiv.org/abs/2301.01751v2","url_pdf":"https://arxiv.org/pdf/2301.01751v2.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":"iterated-decomposition-improving-science-q-a","repo_url":"https://github.com/oughtinc/ice","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2301.01751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.01751"}},"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/oughtinc/ice","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"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":"cb9dce8ee95dfdfe","entry":"get_full_document_id","repo":"oughtinc/ice","repo_kind":"official","path":"ice/paper.py","file_url":"https://github.com/oughtinc/ice/blob/HEAD/ice/paper.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":"cb9dce8ee95dfdfe"}},{"code_sha256_prefix":"0bdb3c07ace9e389","entry":"get_paper_paths","repo":"oughtinc/ice","repo_kind":"official","path":"ice/paper.py","file_url":"https://github.com/oughtinc/ice/blob/HEAD/ice/paper.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":"0bdb3c07ace9e389"}},{"code_sha256_prefix":"2f56ff4dbb1ca003","entry":"is_filename","repo":"oughtinc/ice","repo_kind":"official","path":"ice/cli_utils.py","file_url":"https://github.com/oughtinc/ice/blob/HEAD/ice/cli_utils.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":"2f56ff4dbb1ca003"}},{"code_sha256_prefix":"fe5c837ecad2eece","entry":"starts_with_number","repo":"oughtinc/ice","repo_kind":"official","path":"ice/paper.py","file_url":"https://github.com/oughtinc/ice/blob/HEAD/ice/paper.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":"fe5c837ecad2eece"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}