{"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/llm-stability-a-detailed-analysis-with-some","title":"Non-Determinism of \"Deterministic\" LLM Settings","arxiv_id":"2408.04667","date":"2024-08-06","proceeding":null,"authors":["Berk Atıl","Sarp Aykent","Alexa Chittams","Lisheng Fu","Rebecca J. Passonneau","Evan Radcliffe","Guru Rajan Rajagopal","Adam Sloan","Tomasz Tudrej","Ferhan Ture","Zhe Wu","Lixinyu Xu","Breck Baldwin"],"abstract":"LLM (large language model) practitioners commonly notice that outputs can vary for the same inputs under settings expected to be deterministic. Yet the questions of how pervasive this is, and with what impact on results, have not to our knowledge been systematically investigated. We investigate non-determinism in five LLMs configured to be deterministic when applied to eight common tasks in across 10 runs, in both zero-shot and few-shot settings. We see accuracy variations up to 15% across naturally occurring runs with a gap of best possible performance to worst possible performance up to 70%. In fact, none of the LLMs consistently delivers repeatable accuracy across all tasks, much less identical output strings. Sharing preliminary results with insiders has revealed that non-determinism perhaps essential to the efficient use of compute resources via co-mingled data in input buffers so this issue is not going away anytime soon. To better quantify our observations, we introduce metrics focused on quantifying determinism, TARr@N for the total agreement rate at N runs over raw output, and TARa@N for total agreement rate of parsed-out answers. Our code and data are publicly available at https://github.com/breckbaldwin/llm-stability.","url_abs":"https://arxiv.org/abs/2408.04667v5","url_pdf":"https://arxiv.org/pdf/2408.04667v5.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":"llm-stability-a-detailed-analysis-with-some","repo_url":"https://github.com/breckbaldwin/llm-stability","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"llm-stability-a-detailed-analysis-with-some","repo_url":"https://github.com/Comcast/llm-stability","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2408.04667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04667"}},"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/Comcast/llm-stability","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/breckbaldwin/llm-stability","reach":null}],"summary":{"ran_draft_wrong":4,"unverified":2},"by_repo_kind":{"official":{"samples":6,"ran":4,"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":0,"samples":[{"code_sha256_prefix":"76cadee5f7964ff8","entry":"check_hand_annotated_cache","repo":"Comcast/llm-stability","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/Comcast/llm-stability/blob/HEAD/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"76cadee5f7964ff8"}},{"code_sha256_prefix":"59024a627e4343c6","entry":"get_experiment_configs","repo":"Comcast/llm-stability","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/Comcast/llm-stability/blob/HEAD/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"59024a627e4343c6"}},{"code_sha256_prefix":"151e9739708eb70c","entry":"load_runs","repo":"Comcast/llm-stability","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/Comcast/llm-stability/blob/HEAD/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"151e9739708eb70c"}},{"code_sha256_prefix":"48505ee862750c1e","entry":"run_model","repo":"breckbaldwin/llm-stability","repo_kind":"official","path":"run_experiment.py","file_url":"https://github.com/breckbaldwin/llm-stability/blob/HEAD/run_experiment.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"48505ee862750c1e"}},{"code_sha256_prefix":"2aa869fcf2a593c3","entry":"load_runs","repo":"breckbaldwin/llm-stability","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/breckbaldwin/llm-stability/blob/HEAD/evaluate.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":"2aa869fcf2a593c3"}},{"code_sha256_prefix":"0e000ac3dfcc1171","entry":"run","repo":"breckbaldwin/llm-stability","repo_kind":"official","path":"run_experiment.py","file_url":"https://github.com/breckbaldwin/llm-stability/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":"0e000ac3dfcc1171"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}