{"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/llmstep-llm-proofstep-suggestions-in-lean","title":"LLMSTEP: LLM proofstep suggestions in Lean","arxiv_id":"2310.18457","date":"2023-10-27","proceeding":null,"authors":["Sean Welleck","Rahul Saha"],"abstract":"We present LLMSTEP, a tool for integrating a language model into the Lean proof assistant. LLMSTEP is a Lean 4 tactic that sends a user's proof state to a server hosting a language model. The language model generates suggestions, which are checked in Lean and displayed to a user in their development environment. We provide a baseline language model, along with code for fine-tuning and evaluation to support further development. We provide server implementations that run on CPU, a CUDA GPU, or a Google Colab notebook, as a step towards fast, effective language model suggestions for any user.","url_abs":"https://arxiv.org/abs/2310.18457v1","url_pdf":"https://arxiv.org/pdf/2310.18457v1.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":"llmstep-llm-proofstep-suggestions-in-lean","repo_url":"https://github.com/wellecks/llmstep","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.18457","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.18457"}},"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/wellecks/llmstep","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":9,"unverified":2},"by_repo_kind":{"official":{"samples":11,"ran":9,"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":"ef2fe3849acf24b8","entry":"fmt_proofstep","repo":"wellecks/llmstep","repo_kind":"official","path":"python/train/data.py","file_url":"https://github.com/wellecks/llmstep/blob/HEAD/python/train/data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ef2fe3849acf24b8"}},{"code_sha256_prefix":"ba10a72407a0401c","entry":"hf_encdec_generate","repo":"wellecks/llmstep","repo_kind":"official","path":"python/server_encdec.py","file_url":"https://github.com/wellecks/llmstep/blob/HEAD/python/server_encdec.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ba10a72407a0401c"}},{"code_sha256_prefix":"95146b04fb52c3d1","entry":"llmstep_prompt","repo":"wellecks/llmstep","repo_kind":"official","path":"python/server.py","file_url":"https://github.com/wellecks/llmstep/blob/HEAD/python/server.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"95146b04fb52c3d1"}},{"code_sha256_prefix":"f9d677d82616a315","entry":"llmstep_prompt1","repo":"wellecks/llmstep","repo_kind":"official","path":"python/server_llemma.py","file_url":"https://github.com/wellecks/llmstep/blob/HEAD/python/server_llemma.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f9d677d82616a315"}},{"code_sha256_prefix":"d0a79e9af1754b83","entry":"load_hf","repo":"wellecks/llmstep","repo_kind":"official","path":"python/server.py","file_url":"https://github.com/wellecks/llmstep/blob/HEAD/python/server.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d0a79e9af1754b83"}},{"code_sha256_prefix":"80ae9da2d8d17562","entry":"load_hf_encdec","repo":"wellecks/llmstep","repo_kind":"official","path":"python/server_encdec.py","file_url":"https://github.com/wellecks/llmstep/blob/HEAD/python/server_encdec.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"80ae9da2d8d17562"}},{"code_sha256_prefix":"0260b6a8ebc40a5f","entry":"preprocess","repo":"wellecks/llmstep","repo_kind":"official","path":"python/train/tune.py","file_url":"https://github.com/wellecks/llmstep/blob/HEAD/python/train/tune.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0260b6a8ebc40a5f"}},{"code_sha256_prefix":"652c32004f36cbf1","entry":"proofstep","repo":"wellecks/llmstep","repo_kind":"official","path":"python/train/data.py","file_url":"https://github.com/wellecks/llmstep/blob/HEAD/python/train/data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"652c32004f36cbf1"}},{"code_sha256_prefix":"9a02d31cabf99be9","entry":"reprover_prompt","repo":"wellecks/llmstep","repo_kind":"official","path":"python/server_encdec.py","file_url":"https://github.com/wellecks/llmstep/blob/HEAD/python/server_encdec.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9a02d31cabf99be9"}},{"code_sha256_prefix":"9f6ffd840464d935","entry":"hf_generate","repo":"wellecks/llmstep","repo_kind":"official","path":"python/server.py","file_url":"https://github.com/wellecks/llmstep/blob/HEAD/python/server.py","link_basis":"first_harvest_node","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":"9f6ffd840464d935"}},{"code_sha256_prefix":"f227a3efda0fb0e6","entry":"resume_from","repo":"wellecks/llmstep","repo_kind":"official","path":"python/benchmarking/proofsearch/proofsearch.py","file_url":"https://github.com/wellecks/llmstep/blob/HEAD/python/benchmarking/proofsearch/proofsearch.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":"f227a3efda0fb0e6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}