@inproceedings{bafna-etal-2026-rashid,
title = "Rashid: A Cipher-Based Framework for Exploring In-Context Language Learning",
author = "Bafna, Niyati and
Shim, Ryan Soh-Eun and
Plank, Barbara and
Yarowsky, David and
Sirin, Hale",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1743/",
pages = "39746--39783",
ISBN = "979-8-89176-459-0",
abstract = "While there is growing interest in in-context language learning (ICLL) for unseen languages with large language models, such languages usually suffer from the lack of NLP tools, data resources, and researcher expertise. This means that progress is difficult to assess, the field does not allow for easy large-scale experimentation, and findings on ICLL are often limited to very few languages and tasks. In light of such limitations, we introduce a framework (Rashid) for studying ICLL wherein we reversibly cipher high-resource languages (HRLs) to construct truly unseen languages with access to a wide range of resources available for HRLs, unlocking previously impossible exploration of ICLL phenomena. We use our framework to assess current ICLL methods for machine translation with SOTA evaluation tools and manual analysis, explore new directions leveraging otherwise expensive resources for improving ICLL, and test ICLL strategies for rich downstream tasks beyond machine translation. These lines of exploration showcase the possibilities enabled by our framework, as well as providing actionable insights regarding current performance and future directions in ICLL."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bafna-etal-2026-rashid">
<titleInfo>
<title>Rashid: A Cipher-Based Framework for Exploring In-Context Language Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Niyati</namePart>
<namePart type="family">Bafna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="given">Soh-Eun</namePart>
<namePart type="family">Shim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Yarowsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hale</namePart>
<namePart type="family">Sirin</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>While there is growing interest in in-context language learning (ICLL) for unseen languages with large language models, such languages usually suffer from the lack of NLP tools, data resources, and researcher expertise. This means that progress is difficult to assess, the field does not allow for easy large-scale experimentation, and findings on ICLL are often limited to very few languages and tasks. In light of such limitations, we introduce a framework (Rashid) for studying ICLL wherein we reversibly cipher high-resource languages (HRLs) to construct truly unseen languages with access to a wide range of resources available for HRLs, unlocking previously impossible exploration of ICLL phenomena. We use our framework to assess current ICLL methods for machine translation with SOTA evaluation tools and manual analysis, explore new directions leveraging otherwise expensive resources for improving ICLL, and test ICLL strategies for rich downstream tasks beyond machine translation. These lines of exploration showcase the possibilities enabled by our framework, as well as providing actionable insights regarding current performance and future directions in ICLL.</abstract>
<identifier type="citekey">bafna-etal-2026-rashid</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1743/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>39746</start>
<end>39783</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rashid: A Cipher-Based Framework for Exploring In-Context Language Learning
%A Bafna, Niyati
%A Shim, Ryan Soh-Eun
%A Plank, Barbara
%A Yarowsky, David
%A Sirin, Hale
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F bafna-etal-2026-rashid
%X While there is growing interest in in-context language learning (ICLL) for unseen languages with large language models, such languages usually suffer from the lack of NLP tools, data resources, and researcher expertise. This means that progress is difficult to assess, the field does not allow for easy large-scale experimentation, and findings on ICLL are often limited to very few languages and tasks. In light of such limitations, we introduce a framework (Rashid) for studying ICLL wherein we reversibly cipher high-resource languages (HRLs) to construct truly unseen languages with access to a wide range of resources available for HRLs, unlocking previously impossible exploration of ICLL phenomena. We use our framework to assess current ICLL methods for machine translation with SOTA evaluation tools and manual analysis, explore new directions leveraging otherwise expensive resources for improving ICLL, and test ICLL strategies for rich downstream tasks beyond machine translation. These lines of exploration showcase the possibilities enabled by our framework, as well as providing actionable insights regarding current performance and future directions in ICLL.
%U https://aclanthology.org/2026.emnlp-main.1743/
%P 39746-39783
Markdown (Informal)
[Rashid: A Cipher-Based Framework for Exploring In-Context Language Learning](https://aclanthology.org/2026.emnlp-main.1743/) (Bafna et al., EMNLP 2026)
ACL