{"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/language-models-are-greedy-reasoners-a","title":"Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought","arxiv_id":"2210.01240","date":"2022-10-03","proceeding":null,"authors":["Abulhair Saparov","He He"],"abstract":"Large language models (LLMs) have shown remarkable reasoning capabilities given chain-of-thought prompts (examples with intermediate reasoning steps). Existing benchmarks measure reasoning ability indirectly, by evaluating accuracy on downstream tasks such as mathematical reasoning. However, it is unclear how these models obtain the answers and whether they rely on simple heuristics rather than the generated chain-of-thought. To enable systematic exploration of the reasoning ability of LLMs, we present a new synthetic question-answering dataset called PrOntoQA, where each example is generated from a synthetic world model represented in first-order logic. This allows us to parse the generated chain-of-thought into symbolic proofs for formal analysis. Our analysis on InstructGPT and GPT-3 shows that LLMs are quite capable of making correct individual deduction steps, and so are generally capable of reasoning, even in fictional contexts. However, they have difficulty with proof planning: When multiple valid deduction steps are available, they are not able to systematically explore the different options.","url_abs":"https://arxiv.org/abs/2210.01240v4","url_pdf":"https://arxiv.org/pdf/2210.01240v4.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":"language-models-are-greedy-reasoners-a","repo_url":"https://github.com/asaparov/prontoqa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"language-models-are-greedy-reasoners-a","repo_url":"https://github.com/facebookresearch/coconut","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"mathematical-reasoning","task_name":"Mathematical Reasoning"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":null,"task_name":"valid"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[{"slug":"prontoqa","name":"PrOntoQA","full_name":"Proof and Ontology-Generated Question-Answering"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.01240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.01240"}},"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/asaparov/prontoqa","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/coconut","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"ran_honours":1,"ran_draft_wrong":1,"ran_violates":1,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":"1d11c551594f3298","entry":"get_count","repo":"asaparov/prontoqa","repo_kind":"official","path":"analyze_results.py","file_url":"https://github.com/asaparov/prontoqa/blob/HEAD/analyze_results.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1d11c551594f3298"}},{"code_sha256_prefix":"94b21ef3a27e0a02","entry":"lighten_color","repo":"asaparov/prontoqa","repo_kind":"official","path":"analyze_results.py","file_url":"https://github.com/asaparov/prontoqa/blob/HEAD/analyze_results.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"94b21ef3a27e0a02"}},{"code_sha256_prefix":"63403bf63d6ded29","entry":"rindex","repo":"asaparov/prontoqa","repo_kind":"official","path":"run_experiment.py","file_url":"https://github.com/asaparov/prontoqa/blob/HEAD/run_experiment.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"63403bf63d6ded29"}},{"code_sha256_prefix":"f24ebcccb5b1d226","entry":"wilson_conf_interval","repo":"asaparov/prontoqa","repo_kind":"official","path":"analyze_results.py","file_url":"https://github.com/asaparov/prontoqa/blob/HEAD/analyze_results.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f24ebcccb5b1d226"}},{"code_sha256_prefix":"0408f2ab52da6612","entry":"is_antecedent_provable","repo":"asaparov/prontoqa","repo_kind":"official","path":"run_experiment.py","file_url":"https://github.com/asaparov/prontoqa/blob/HEAD/run_experiment.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":"0408f2ab52da6612"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}