@inproceedings{kim-etal-2026-retrieval,
title = "Retrieval Without Relevance: Prompt Dependence in Small Machine Translation Models",
author = "Kim, Heesu and
Sato, Shota and
Komachi, Mamoru",
editor = "Choshen, Leshem and
Cotterell, Ryan and
Gul, Mustafa Omer and
Jumelet, Jaap and
Linzen, Tal and
Mueller, Aaron and
Salhan, Suchir and
Shah, Raj Sanjay and
Warstadt, Alex and
Wilcox, Ethan Gotlieb",
booktitle = "Proceedings of the Second {B}aby{LM} Workshop",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.babylm-main.9/",
pages = "105--122",
ISBN = "979-8-89176-475-0",
abstract = "We study how a small machine translation model should allocate a fixed data budget between parametric training and retrieval memory. We define a shared 100M-token corpus-access ledger that charges pretraining, fine-tuning, and retrieval-datastore tokens alike. Using $\approx$42M-parameter models, we compare three uses of the same per-pair datastore across 12 directed pairs of English, Chinese, Japanese, and Korean: leaving it unused, training on it, or retrieving from it into the prompt. We evaluate retrieval additivity across all 12 pairs and analyze retrieval-conditioned behavior in a four-pair core set. Retrieval shows no consistent additive gain over simply not using the datastore, a result that persists under an off-budget dense retriever and pools up to approximately $1000\times$ larger. On the four-pair core set, retrieval-trained models are nevertheless highly context-dependent: removing retrieved examples causes large score drops, while replacing them with query-unrelated, count-matched same-pair examples recovers nearly the full score. This suggests that the learned dependence is primarily on exemplar-shaped context rather than on query-specific information carried by the retrieved neighbors. Our training and evaluation code is available at https://github.com/kheesu/retrieval-without-relevance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2026-retrieval">
<titleInfo>
<title>Retrieval Without Relevance: Prompt Dependence in Small Machine Translation Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Heesu</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shota</namePart>
<namePart type="family">Sato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</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 Second BabyLM Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leshem</namePart>
<namePart type="family">Choshen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mustafa</namePart>
<namePart type="given">Omer</namePart>
<namePart type="family">Gul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaap</namePart>
<namePart type="family">Jumelet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tal</namePart>
<namePart type="family">Linzen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Mueller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suchir</namePart>
<namePart type="family">Salhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="given">Sanjay</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Warstadt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ethan</namePart>
<namePart type="given">Gotlieb</namePart>
<namePart type="family">Wilcox</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">979-8-89176-475-0</identifier>
</relatedItem>
<abstract>We study how a small machine translation model should allocate a fixed data budget between parametric training and retrieval memory. We define a shared 100M-token corpus-access ledger that charges pretraining, fine-tuning, and retrieval-datastore tokens alike. Using \approx42M-parameter models, we compare three uses of the same per-pair datastore across 12 directed pairs of English, Chinese, Japanese, and Korean: leaving it unused, training on it, or retrieving from it into the prompt. We evaluate retrieval additivity across all 12 pairs and analyze retrieval-conditioned behavior in a four-pair core set. Retrieval shows no consistent additive gain over simply not using the datastore, a result that persists under an off-budget dense retriever and pools up to approximately 1000\times larger. On the four-pair core set, retrieval-trained models are nevertheless highly context-dependent: removing retrieved examples causes large score drops, while replacing them with query-unrelated, count-matched same-pair examples recovers nearly the full score. This suggests that the learned dependence is primarily on exemplar-shaped context rather than on query-specific information carried by the retrieved neighbors. Our training and evaluation code is available at https://github.com/kheesu/retrieval-without-relevance.</abstract>
<identifier type="citekey">kim-etal-2026-retrieval</identifier>
<location>
<url>https://aclanthology.org/2026.babylm-main.9/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>105</start>
<end>122</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Retrieval Without Relevance: Prompt Dependence in Small Machine Translation Models
%A Kim, Heesu
%A Sato, Shota
%A Komachi, Mamoru
%Y Choshen, Leshem
%Y Cotterell, Ryan
%Y Gul, Mustafa Omer
%Y Jumelet, Jaap
%Y Linzen, Tal
%Y Mueller, Aaron
%Y Salhan, Suchir
%Y Shah, Raj Sanjay
%Y Warstadt, Alex
%Y Wilcox, Ethan Gotlieb
%S Proceedings of the Second BabyLM Workshop
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-475-0
%F kim-etal-2026-retrieval
%X We study how a small machine translation model should allocate a fixed data budget between parametric training and retrieval memory. We define a shared 100M-token corpus-access ledger that charges pretraining, fine-tuning, and retrieval-datastore tokens alike. Using \approx42M-parameter models, we compare three uses of the same per-pair datastore across 12 directed pairs of English, Chinese, Japanese, and Korean: leaving it unused, training on it, or retrieving from it into the prompt. We evaluate retrieval additivity across all 12 pairs and analyze retrieval-conditioned behavior in a four-pair core set. Retrieval shows no consistent additive gain over simply not using the datastore, a result that persists under an off-budget dense retriever and pools up to approximately 1000\times larger. On the four-pair core set, retrieval-trained models are nevertheless highly context-dependent: removing retrieved examples causes large score drops, while replacing them with query-unrelated, count-matched same-pair examples recovers nearly the full score. This suggests that the learned dependence is primarily on exemplar-shaped context rather than on query-specific information carried by the retrieved neighbors. Our training and evaluation code is available at https://github.com/kheesu/retrieval-without-relevance.
%U https://aclanthology.org/2026.babylm-main.9/
%P 105-122
Markdown (Informal)
[Retrieval Without Relevance: Prompt Dependence in Small Machine Translation Models](https://aclanthology.org/2026.babylm-main.9/) (Kim et al., BabyLM 2026)
ACL