{"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/phenomenal-yet-puzzling-testing-inductive","title":"Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement","arxiv_id":"2310.08559","date":"2023-10-12","proceeding":null,"authors":["Linlu Qiu","Liwei Jiang","Ximing Lu","Melanie Sclar","Valentina Pyatkin","Chandra Bhagavatula","Bailin Wang","Yoon Kim","Yejin Choi","Nouha Dziri","Xiang Ren"],"abstract":"The ability to derive underlying principles from a handful of observations and then generalize to novel situations -- known as inductive reasoning -- is central to human intelligence. Prior work suggests that language models (LMs) often fall short on inductive reasoning, despite achieving impressive success on research benchmarks. In this work, we conduct a systematic study of the inductive reasoning capabilities of LMs through iterative hypothesis refinement, a technique that more closely mirrors the human inductive process than standard input-output prompting. Iterative hypothesis refinement employs a three-step process: proposing, selecting, and refining hypotheses in the form of textual rules. By examining the intermediate rules, we observe that LMs are phenomenal hypothesis proposers (i.e., generating candidate rules), and when coupled with a (task-specific) symbolic interpreter that is able to systematically filter the proposed set of rules, this hybrid approach achieves strong results across inductive reasoning benchmarks that require inducing causal relations, language-like instructions, and symbolic concepts. However, they also behave as puzzling inductive reasoners, showing notable performance gaps between rule induction (i.e., identifying plausible rules) and rule application (i.e., applying proposed rules to instances), suggesting that LMs are proposing hypotheses without being able to actually apply the rules. Through empirical and human analyses, we further reveal several discrepancies between the inductive reasoning processes of LMs and humans, shedding light on both the potentials and limitations of using LMs in inductive reasoning tasks.","url_abs":"https://arxiv.org/abs/2310.08559v4","url_pdf":"https://arxiv.org/pdf/2310.08559v4.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":"phenomenal-yet-puzzling-testing-inductive","repo_url":"https://github.com/linlu-qiu/lm-inductive-reasoning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.08559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.08559"}},"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/linlu-qiu/lm-inductive-reasoning","reach":{"status":"ok"}}],"summary":{"ran":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"ed6531c664d2cd2e","entry":"format_grid","repo":"linlu-qiu/lm-inductive-reasoning","repo_kind":"official","path":"utils/format_utils.py","file_url":"https://github.com/linlu-qiu/lm-inductive-reasoning/blob/HEAD/utils/format_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ed6531c664d2cd2e"}},{"code_sha256_prefix":"a5051431b312aaed","entry":"format_list","repo":"linlu-qiu/lm-inductive-reasoning","repo_kind":"official","path":"utils/format_utils.py","file_url":"https://github.com/linlu-qiu/lm-inductive-reasoning/blob/HEAD/utils/format_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a5051431b312aaed"}},{"code_sha256_prefix":"e3fe161fa1685957","entry":"unformat_grid","repo":"linlu-qiu/lm-inductive-reasoning","repo_kind":"official","path":"utils/format_utils.py","file_url":"https://github.com/linlu-qiu/lm-inductive-reasoning/blob/HEAD/utils/format_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e3fe161fa1685957"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}