@inproceedings{diskind-etal-2026-cross,
title = "Cross-Lingual Exploration for Parametric Knowledge",
author = "Diskind, Elisha and
Trainin, Itamar and
Shaham, Uri and
Choshen, Leshem and
Szpektor, Idan and
Abend, Omri",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.2443/",
pages = "52429--52466",
ISBN = "979-8-89176-462-0",
abstract = "Parametric knowledge in Large Language Models is not equally accessible across languages. As a result, standard inference techniques often struggle to surface localized facts, leading to failures in cross-lingual knowledge transfer and consistency. In this work, we investigate techniques for accessing hidden factual knowledge by exploring the prompted questions across languages. We identify four inherent dimensions of cross-lingual exploration that directly govern parametric knowledge retrieval and evaluate them on multilingual factual benchmarks covering 17 typologically diverse languages. Our results demonstrate that cross-lingual exploration significantly improves knowledge transfer and factual recall, representing a more efficient compute Pareto frontier than native-language scaling. Furthermore, we report similar performance improvement in cross-lingual consistency, exceeding what can be explained by accuracy gains alone. Overall, our work demonstrates the potential of multilingual exploration to improve parametric knowledge recall."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="diskind-etal-2026-cross">
<titleInfo>
<title>Cross-Lingual Exploration for Parametric Knowledge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elisha</namePart>
<namePart type="family">Diskind</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Itamar</namePart>
<namePart type="family">Trainin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uri</namePart>
<namePart type="family">Shaham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leshem</namePart>
<namePart type="family">Choshen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Idan</namePart>
<namePart type="family">Szpektor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omri</namePart>
<namePart type="family">Abend</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Parametric knowledge in Large Language Models is not equally accessible across languages. As a result, standard inference techniques often struggle to surface localized facts, leading to failures in cross-lingual knowledge transfer and consistency. In this work, we investigate techniques for accessing hidden factual knowledge by exploring the prompted questions across languages. We identify four inherent dimensions of cross-lingual exploration that directly govern parametric knowledge retrieval and evaluate them on multilingual factual benchmarks covering 17 typologically diverse languages. Our results demonstrate that cross-lingual exploration significantly improves knowledge transfer and factual recall, representing a more efficient compute Pareto frontier than native-language scaling. Furthermore, we report similar performance improvement in cross-lingual consistency, exceeding what can be explained by accuracy gains alone. Overall, our work demonstrates the potential of multilingual exploration to improve parametric knowledge recall.</abstract>
<identifier type="citekey">diskind-etal-2026-cross</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2443/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>52429</start>
<end>52466</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-Lingual Exploration for Parametric Knowledge
%A Diskind, Elisha
%A Trainin, Itamar
%A Shaham, Uri
%A Choshen, Leshem
%A Szpektor, Idan
%A Abend, Omri
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F diskind-etal-2026-cross
%X Parametric knowledge in Large Language Models is not equally accessible across languages. As a result, standard inference techniques often struggle to surface localized facts, leading to failures in cross-lingual knowledge transfer and consistency. In this work, we investigate techniques for accessing hidden factual knowledge by exploring the prompted questions across languages. We identify four inherent dimensions of cross-lingual exploration that directly govern parametric knowledge retrieval and evaluate them on multilingual factual benchmarks covering 17 typologically diverse languages. Our results demonstrate that cross-lingual exploration significantly improves knowledge transfer and factual recall, representing a more efficient compute Pareto frontier than native-language scaling. Furthermore, we report similar performance improvement in cross-lingual consistency, exceeding what can be explained by accuracy gains alone. Overall, our work demonstrates the potential of multilingual exploration to improve parametric knowledge recall.
%U https://aclanthology.org/2026.findings-emnlp.2443/
%P 52429-52466
Markdown (Informal)
[Cross-Lingual Exploration for Parametric Knowledge](https://aclanthology.org/2026.findings-emnlp.2443/) (Diskind et al., Findings 2026)
ACL
- Elisha Diskind, Itamar Trainin, Uri Shaham, Leshem Choshen, Idan Szpektor, and Omri Abend. 2026. Cross-Lingual Exploration for Parametric Knowledge. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 52429–52466, Budapest, Hungary. Association for Computational Linguistics.