{"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/large-language-models-are-zero-shot-time-1","title":"Large Language Models Are Zero-Shot Time Series Forecasters","arxiv_id":"2310.07820","date":"2023-10-11","proceeding":"NeurIPS 2023 11","authors":["Nate Gruver","Marc Finzi","Shikai Qiu","Andrew Gordon Wilson"],"abstract":"By encoding time series as a string of numerical digits, we can frame time series forecasting as next-token prediction in text. Developing this approach, we find that large language models (LLMs) such as GPT-3 and LLaMA-2 can surprisingly zero-shot extrapolate time series at a level comparable to or exceeding the performance of purpose-built time series models trained on the downstream tasks. To facilitate this performance, we propose procedures for effectively tokenizing time series data and converting discrete distributions over tokens into highly flexible densities over continuous values. We argue the success of LLMs for time series stems from their ability to naturally represent multimodal distributions, in conjunction with biases for simplicity, and repetition, which align with the salient features in many time series, such as repeated seasonal trends. We also show how LLMs can naturally handle missing data without imputation through non-numerical text, accommodate textual side information, and answer questions to help explain predictions. While we find that increasing model size generally improves performance on time series, we show GPT-4 can perform worse than GPT-3 because of how it tokenizes numbers, and poor uncertainty calibration, which is likely the result of alignment interventions such as RLHF.","url_abs":"https://arxiv.org/abs/2310.07820v3","url_pdf":"https://arxiv.org/pdf/2310.07820v3.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":"large-language-models-are-zero-shot-time-1","repo_url":"https://github.com/ngruver/llmtime","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"large-language-models-are-zero-shot-time-1","repo_url":"https://github.com/junwoopark92/revisiting-llms-zeroshot-forecaster","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"imputation","task_name":"Imputation"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series-forecasting","task_name":"Time Series Forecasting"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"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":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"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":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.07820","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07820"}},"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":"deterministic:regex_extraction","url":"https://github.com/ngruver/llmtime","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/junwoopark92/revisiting-llms-zeroshot-forecaster","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":1,"unverified":6},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":6,"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":"22b1b1c4eedfe064","entry":"is_gpt","repo":"ngruver/llmtime","repo_kind":"official","path":"experiments/run_darts.py","file_url":"https://github.com/ngruver/llmtime/blob/HEAD/experiments/run_darts.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"22b1b1c4eedfe064"}},{"code_sha256_prefix":"87a2b11c5af65afe","entry":"autoregressive_inference","repo":"junwoopark92/revisiting-llms-zeroshot-forecaster","repo_kind":"listed","path":"experiments_revisiting_llm_acl25/linear_models/forecasting.py","file_url":"https://github.com/junwoopark92/revisiting-llms-zeroshot-forecaster/blob/HEAD/experiments_revisiting_llm_acl25/linear_models/forecasting.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":"87a2b11c5af65afe"}},{"code_sha256_prefix":"64d16d6e3eb94bcd","entry":"cal_metric","repo":"junwoopark92/revisiting-llms-zeroshot-forecaster","repo_kind":"listed","path":"experiments_revisiting_llm_acl25/exp_utils.py","file_url":"https://github.com/junwoopark92/revisiting-llms-zeroshot-forecaster/blob/HEAD/experiments_revisiting_llm_acl25/exp_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":"64d16d6e3eb94bcd"}},{"code_sha256_prefix":"6f226282a9ba109b","entry":"calculate_mean_confidence_interval","repo":"junwoopark92/revisiting-llms-zeroshot-forecaster","repo_kind":"listed","path":"experiments_revisiting_llm_acl25/exp_utils.py","file_url":"https://github.com/junwoopark92/revisiting-llms-zeroshot-forecaster/blob/HEAD/experiments_revisiting_llm_acl25/exp_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":"6f226282a9ba109b"}},{"code_sha256_prefix":"3b11518eaa8f914a","entry":"inference","repo":"junwoopark92/revisiting-llms-zeroshot-forecaster","repo_kind":"listed","path":"experiments_revisiting_llm_acl25/linear_models/forecasting.py","file_url":"https://github.com/junwoopark92/revisiting-llms-zeroshot-forecaster/blob/HEAD/experiments_revisiting_llm_acl25/linear_models/forecasting.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":"3b11518eaa8f914a"}},{"code_sha256_prefix":"16567b6fd5a79426","entry":"load_pickle","repo":"junwoopark92/revisiting-llms-zeroshot-forecaster","repo_kind":"listed","path":"experiments_revisiting_llm_acl25/exp_utils.py","file_url":"https://github.com/junwoopark92/revisiting-llms-zeroshot-forecaster/blob/HEAD/experiments_revisiting_llm_acl25/exp_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":"16567b6fd5a79426"}},{"code_sha256_prefix":"8d04489b831cb243","entry":"train_and_inference","repo":"junwoopark92/revisiting-llms-zeroshot-forecaster","repo_kind":"listed","path":"experiments_revisiting_llm_acl25/linear_models/forecasting.py","file_url":"https://github.com/junwoopark92/revisiting-llms-zeroshot-forecaster/blob/HEAD/experiments_revisiting_llm_acl25/linear_models/forecasting.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":"8d04489b831cb243"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}