{"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/are-language-models-actually-useful-for-time","title":"Are Language Models Actually Useful for Time Series Forecasting?","arxiv_id":"2406.16964","date":"2024-06-22","proceeding":null,"authors":["Mingtian Tan","Mike A. Merrill","Vinayak Gupta","Tim Althoff","Thomas Hartvigsen"],"abstract":"Large language models (LLMs) are being applied to time series forecasting. But are language models actually useful for time series? In a series of ablation studies on three recent and popular LLM-based time series forecasting methods, we find that removing the LLM component or replacing it with a basic attention layer does not degrade forecasting performance -- in most cases, the results even improve! We also find that despite their significant computational cost, pretrained LLMs do no better than models trained from scratch, do not represent the sequential dependencies in time series, and do not assist in few-shot settings. Additionally, we explore time series encoders and find that patching and attention structures perform similarly to LLM-based forecasters.","url_abs":"https://arxiv.org/abs/2406.16964v2","url_pdf":"https://arxiv.org/pdf/2406.16964v2.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":"are-language-models-actually-useful-for-time","repo_url":"https://github.com/bennytmt/llmsfortimeseries","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"are-language-models-actually-useful-for-time","repo_url":"https://github.com/bennytmt/ts_models","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"are-language-models-actually-useful-for-time","repo_url":"https://github.com/thuml/AutoTimes","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series-forecasting","task_name":"Time Series Forecasting"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"patching","method_name":"Patching"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2406.16964","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16964"}},"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/bennytmt/llmsfortimeseries","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bennytmt/ts_models","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thuml/AutoTimes","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":2},"listed":{"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":2,"samples":[{"code_sha256_prefix":"9d0ccaea639499f4","entry":"MAPE","repo":"thuml/AutoTimes","repo_kind":"listed","path":"exp/exp_in_context_forecasting.py","file_url":"https://github.com/thuml/AutoTimes/blob/HEAD/exp/exp_in_context_forecasting.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":"9d0ccaea639499f4"}},{"code_sha256_prefix":"a7f97eecdd50384f","entry":"SMAPE","repo":"thuml/AutoTimes","repo_kind":"listed","path":"exp/exp_in_context_forecasting.py","file_url":"https://github.com/thuml/AutoTimes/blob/HEAD/exp/exp_in_context_forecasting.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":"a7f97eecdd50384f"}},{"code_sha256_prefix":"3eb58dae620046d3","entry":"l2norm","repo":"bennytmt/ts_models","repo_kind":"official","path":"OFA/models/PatchTST.py","file_url":"https://github.com/bennytmt/ts_models/blob/HEAD/OFA/models/PatchTST.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3eb58dae620046d3"}},{"code_sha256_prefix":"25a40de96ff65a01","entry":"url_file_name","repo":"thuml/AutoTimes","repo_kind":"listed","path":"data_provider/m4.py","file_url":"https://github.com/thuml/AutoTimes/blob/HEAD/data_provider/m4.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":"25a40de96ff65a01"}},{"code_sha256_prefix":"bdc787c888ab83a2","entry":"divide_no_nan","repo":"bennytmt/llmsfortimeseries","repo_kind":"official","path":"CALF/utils/losses.py","file_url":"https://github.com/bennytmt/llmsfortimeseries/blob/HEAD/CALF/utils/losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bdc787c888ab83a2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}