Papers › Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilities

Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilities

16 Feb 2024arXiv:2402.10835archive 2025-07-28

Hua Tang, Chong Zhang, Mingyu Jin, Qinkai Yu, Zhenting Wang, Xiaobo Jin, Yongfeng Zhang, Mengnan Du

Large language models (LLMs) have been applied in many fields and have developed rapidly in recent years. As a classic machine learning task, time series forecasting has recently been boosted by LLMs. Recent works treat large language models as zero-shot time series reasoners without further fine-tuning, which achieves remarkable performance. However, there are some unexplored research problems when applying LLMs for time series forecasting under the zero-shot setting. For instance, the LLMs' preferences for the input time series are less understood. In this paper, by comparing LLMs with traditional time series forecasting models, we observe many interesting properties of LLMs in the context of time series forecasting. First, our study shows that LLMs perform well in predicting time series with clear patterns and trends, but face challenges with datasets lacking periodicity. This observation can be explained by the ability of LLMs to recognize the underlying period within datasets, which is supported by our experiments. In addition, the input strategy is investigated, and it is found that incorporating external knowledge and adopting natural language paraphrases substantially improve the predictive performance of LLMs for time series. Overall, our study contributes insight into LLMs' advantages and limitations in time series forecasting under different conditions.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 22 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 12 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 22 samples from 1 repository, 10 ran (7 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

mingyuj666/time-series-forecasting-with-llms officialmentioned in paperjaxSyntology: 22 samples, 10 ran (3 instrument-failed) · 12 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

22 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 12 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
1ran; the contract check could not run
7ran
12unverified

Licence: 22 of the 22 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from mingyuj666/time-series-forecasting-with-llms. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

mingyuj666/time-series-forecasting-with-llms official repository 22 samples, 10 ran (3 instrument-failed) · 12 unverified
get_avg_tokens_per_step models/promptcast.py ran no licence file found · pointer only · a43c0e795f42a4e4 · report fixture: signature input_str:str/0/str, settings:Settings/0/? · returned float · level recorded 2026-09-24
get_chunked_AR_likelihoods models/darts.py ran no licence file found · pointer only · f9f0267039a3e10c · report fixture: signature model:callable/0/?, scaled_series:ndarray/2/float, trainsize:int/0/int, in_len:int/0/int, out_len:int/0/int, scaler:MockScaler/0/? · returned float · level recorded 2026-09-24
get_gp_predictions_data models/gaussian_process.py ran no licence file found · pointer only · c9d4277557a5ad48 · report fixture: signature train:ndarray/1/float, test:ndarray/1/float, epochs:int/0/int, lr:float/0/float, num_samples:int/0/int · returned dict · level recorded 2026-09-24
get_scaler in 7 papers models/llmtime.py ran; the contract check could not run (RAISES) no licence file found · pointer only · ddf3ae386381837b · report fixture: signature history:ndarray/1/float, alpha:float/0/float, beta:float/0/float, basic:bool/0/bool · returned Scaler · level recorded 2026-09-24
handle_prediction models/llmtime.py ran no licence file found · pointer only · e2334c5cdd64f02f · report fixture: signature pred:ndarray/1/float, expected_length:int/0/int, strict:bool/0/bool · returned ndarray · level recorded 2026-09-24
llama2_model_string models/llama.py ran · our draft was wrong fingerprinted no licence file found · pointer only · ea3f2a9058322ab1 · report fixture: signature model_size:str/0/str, chat:bool/0/bool · returned str · level recorded 2026-09-24
metrics_used utils_others.py ran no licence file found · pointer only · c0e90befe3def690 · report fixture: signature test:ndarray/1/float, dataset_name:str/0/str, original_pred:dict/0/?, num_samples:int/0/int · returned tuple · level recorded 2026-09-24
paraphrase_seq2lan utils_paragraph.py ran no licence file found · pointer only · 1584833dcf9cb539 · report fixture: signature seq:Series/1/float, desp:str/0/str · returned str · level recorded 2026-09-24
test_gp models/gaussian_process.py ran no licence file found · pointer only · a944775a44d34a92 · report fixture: signature model:callable/0/?, likelihood:callable/0/?, test_x:list/1/list, test_y:list/1/float · returned tuple · level recorded 2026-09-24
unflatten in 15 papers models/utils.py ran · our draft was wrong no licence file found · pointer only · fbf4f5f91d7ae546 · report fixture: signature d:dict/0/?, sep:str/0/str · returned dict · level recorded 2026-09-24
describe_change utils_paragraph.py unverified no licence file found · pointer only · 697cdd488db56658 · report
evaluate_hyper models/validation_likelihood_tuning.py unverified no licence file found · pointer only · 2a86130b6c290600 · report
flatten in 178 papers
census: 4 implementations from 7 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
models/utils.py unverified no licence file found · pointer only · 4d2db8ac4af8bffc · report
get_allowed_ids models/gpt.py unverified no licence file found · pointer only · 07a1ec7a6c69ed48 · report
get_model_and_tokenizer in 15 papers models/llama.py unverified no licence file found · pointer only · 42592f351c8e9f61 · report
get_token_ids in 5 papers models/promptcast.py unverified no licence file found · pointer only · 013b729b67771afc · report
get_tokenizer in 156 papers models/llama.py unverified no licence file found · pointer only · cfe13ed62ca54e83 · report
make_validation_dataset models/validation_likelihood_tuning.py unverified no licence file found · pointer only · 3ead7ce217600482 · report
paraphrase_initial utils_paragraph.py unverified no licence file found · pointer only · 7c64b8e59c3fb35b · report
sample_config models/utils.py unverified no licence file found · pointer only · 3aae9ed7e6ed94d4 · report
tokenize_fn in 9 papers models/gpt.py unverified no licence file found · pointer only · 0974c070244bffa0 · report
train_gp models/gaussian_process.py unverified no licence file found · pointer only · 76c5dcef347a5103 · report

Tasks

Time SeriesTime Series ForecastingTime Series Prediction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections