@inproceedings{tan-etal-2026-inferring,
title = "Inferring Events from Time Series using Language Models",
author = "Tan, Mingtian and
Merrill, Mike A and
Gottesman, Zachary and
Althoff, Tim and
Evans, David and
Hartvigsen, Thomas",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.157/",
pages = "3469--3490",
ISBN = "979-8-89176-390-6",
abstract = "A common goal in analyzing time series data is to understand how events cause observed variations. We study whether Large Language Models (LLMs) can infer natural language events associated with time series data.We introduce an automated method for generating tasks that test a model{'}s ability to reason about events associated with time series data based on sports data, and develop a new benchmarking method. In experiments spanning 18 LLMs, we prompt LLMs to infer unobserved events given time series data and observe surprising successes, even when providing minimal context. We then show that combining distillation with Reinforcement Learning (RL) can improve the performance for small language models to approach that of large proprietary reasoning models. All resources needed to reproduce our work are available: https://github.com/hartvigsen-group/GAMETime."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tan-etal-2026-inferring">
<titleInfo>
<title>Inferring Events from Time Series using Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mingtian</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Merrill</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zachary</namePart>
<namePart type="family">Gottesman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Althoff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Evans</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Hartvigsen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>A common goal in analyzing time series data is to understand how events cause observed variations. We study whether Large Language Models (LLMs) can infer natural language events associated with time series data.We introduce an automated method for generating tasks that test a model’s ability to reason about events associated with time series data based on sports data, and develop a new benchmarking method. In experiments spanning 18 LLMs, we prompt LLMs to infer unobserved events given time series data and observe surprising successes, even when providing minimal context. We then show that combining distillation with Reinforcement Learning (RL) can improve the performance for small language models to approach that of large proprietary reasoning models. All resources needed to reproduce our work are available: https://github.com/hartvigsen-group/GAMETime.</abstract>
<identifier type="citekey">tan-etal-2026-inferring</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.157/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>3469</start>
<end>3490</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Inferring Events from Time Series using Language Models
%A Tan, Mingtian
%A Merrill, Mike A.
%A Gottesman, Zachary
%A Althoff, Tim
%A Evans, David
%A Hartvigsen, Thomas
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F tan-etal-2026-inferring
%X A common goal in analyzing time series data is to understand how events cause observed variations. We study whether Large Language Models (LLMs) can infer natural language events associated with time series data.We introduce an automated method for generating tasks that test a model’s ability to reason about events associated with time series data based on sports data, and develop a new benchmarking method. In experiments spanning 18 LLMs, we prompt LLMs to infer unobserved events given time series data and observe surprising successes, even when providing minimal context. We then show that combining distillation with Reinforcement Learning (RL) can improve the performance for small language models to approach that of large proprietary reasoning models. All resources needed to reproduce our work are available: https://github.com/hartvigsen-group/GAMETime.
%U https://aclanthology.org/2026.acl-long.157/
%P 3469-3490
Markdown (Informal)
[Inferring Events from Time Series using Language Models](https://aclanthology.org/2026.acl-long.157/) (Tan et al., ACL 2026)
ACL
- Mingtian Tan, Mike A Merrill, Zachary Gottesman, Tim Althoff, David Evans, and Thomas Hartvigsen. 2026. Inferring Events from Time Series using Language Models. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3469–3490, San Diego, California, United States. Association for Computational Linguistics.