@inproceedings{liu-etal-2026-exante,
title = "{E}x{A}nte: A Benchmark for Ex-Ante Inference in Large Language Models",
author = "Liu, Yachuan and
Wei, Xiaochun and
Shi, Lin and
Li, Xinnuo and
Zhang, Bohan and
Dhillon, Paramveer and
Mei, Qiaozhu",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-long.72/",
pages = "1551--1571",
ISBN = "979-8-89176-380-7",
abstract = "Large language models (LLMs) struggle with ex-ante reasoning{---}making inferences or predictions without access to future information. Even under explicit temporal cutoffs, they often rely on internalized post-cutoff knowledge. To systematically evaluate this issue, we introduce a benchmark that assesses LLMs' ex-ante inference ability across four tasks: stock prediction, question answering, Wikipedia event generation, and scientific publication generation. We quantify temporal leakage using a leakage rate metric, which measures models' reliance on future information beyond cutoff timestamps, and a quality measure that evaluates task performance. Experimental results show that LLMs frequently violate temporal constraints across tasks, revealing persistent challenges in ex-ante reasoning. Our benchmark serves as a rigorous testbed for studying temporal reasoning in time-sensitive contexts and provides complete datasets, results, and evaluation resources to support future research on improving temporal consistency in modern LLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-exante">
<titleInfo>
<title>ExAnte: A Benchmark for Ex-Ante Inference in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yachuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaochun</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lin</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinnuo</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bohan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paramveer</namePart>
<namePart type="family">Dhillon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiaozhu</namePart>
<namePart type="family">Mei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-380-7</identifier>
</relatedItem>
<abstract>Large language models (LLMs) struggle with ex-ante reasoning—making inferences or predictions without access to future information. Even under explicit temporal cutoffs, they often rely on internalized post-cutoff knowledge. To systematically evaluate this issue, we introduce a benchmark that assesses LLMs’ ex-ante inference ability across four tasks: stock prediction, question answering, Wikipedia event generation, and scientific publication generation. We quantify temporal leakage using a leakage rate metric, which measures models’ reliance on future information beyond cutoff timestamps, and a quality measure that evaluates task performance. Experimental results show that LLMs frequently violate temporal constraints across tasks, revealing persistent challenges in ex-ante reasoning. Our benchmark serves as a rigorous testbed for studying temporal reasoning in time-sensitive contexts and provides complete datasets, results, and evaluation resources to support future research on improving temporal consistency in modern LLMs.</abstract>
<identifier type="citekey">liu-etal-2026-exante</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-long.72/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>1551</start>
<end>1571</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ExAnte: A Benchmark for Ex-Ante Inference in Large Language Models
%A Liu, Yachuan
%A Wei, Xiaochun
%A Shi, Lin
%A Li, Xinnuo
%A Zhang, Bohan
%A Dhillon, Paramveer
%A Mei, Qiaozhu
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-380-7
%F liu-etal-2026-exante
%X Large language models (LLMs) struggle with ex-ante reasoning—making inferences or predictions without access to future information. Even under explicit temporal cutoffs, they often rely on internalized post-cutoff knowledge. To systematically evaluate this issue, we introduce a benchmark that assesses LLMs’ ex-ante inference ability across four tasks: stock prediction, question answering, Wikipedia event generation, and scientific publication generation. We quantify temporal leakage using a leakage rate metric, which measures models’ reliance on future information beyond cutoff timestamps, and a quality measure that evaluates task performance. Experimental results show that LLMs frequently violate temporal constraints across tasks, revealing persistent challenges in ex-ante reasoning. Our benchmark serves as a rigorous testbed for studying temporal reasoning in time-sensitive contexts and provides complete datasets, results, and evaluation resources to support future research on improving temporal consistency in modern LLMs.
%U https://aclanthology.org/2026.eacl-long.72/
%P 1551-1571
Markdown (Informal)
[ExAnte: A Benchmark for Ex-Ante Inference in Large Language Models](https://aclanthology.org/2026.eacl-long.72/) (Liu et al., EACL 2026)
ACL
- Yachuan Liu, Xiaochun Wei, Lin Shi, Xinnuo Li, Bohan Zhang, Paramveer Dhillon, and Qiaozhu Mei. 2026. ExAnte: A Benchmark for Ex-Ante Inference in Large Language Models. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1551–1571, Rabat, Morocco. Association for Computational Linguistics.