Length and Meaning for Language Model Maps

Momose Oyama; Ryo Kishino; Hiroaki Yamagiwa; Hidetoshi Shimodaira

Length and Meaning for Language Model Maps

Momose Oyama, Ryo Kishino, Hiroaki Yamagiwa, Hidetoshi Shimodaira

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

Various studies have proposed methods to quantify and compare the rapidly growing number of large language models (LLMs). However, when constructing a macroscopic map of LLMs, there is a trade-off between estimation accuracy and computational cost, making the selection of evaluation texts critical. In this work, we propose Predictive Importance Sampling (PredIS), which selects informative texts by predicting likelihood variance from text-level features. Experiments on 100 LLMs across 25 domains demonstrate that our predictor generalizes robustly. Furthermore, we reveal that text importance cannot be explained by text length alone, as it is also closely tied to meaning reflected in the embedding space.

Anthology ID:: 2026.emnlp-main.1510
Volume:: Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Month:: October
Year:: 2026
Address:: Budapest, Hungary
Editors:: Hung-Yi Lee, Sunipa Dev, Jessy Li, Desmond Elliott
Venue:: EMNLP
SIG:: SIGDAT
Publisher:: Association for Computational Linguistics
Note:
Pages:: 34472–34487
Language:
URL:: https://aclanthology.org/2026.emnlp-main.1510/
DOI:
Bibkey:
Cite (ACL):: Momose Oyama, Ryo Kishino, Hiroaki Yamagiwa, and Hidetoshi Shimodaira. 2026. Length and Meaning for Language Model Maps. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 34472–34487, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: Length and Meaning for Language Model Maps (Oyama et al., EMNLP 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.emnlp-main.1510.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{oyama-etal-2026-length,
    title = "Length and Meaning for Language Model Maps",
    author = "Oyama, Momose  and
      Kishino, Ryo  and
      Yamagiwa, Hiroaki  and
      Shimodaira, Hidetoshi",
    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.1510/",
    pages = "34472--34487",
    ISBN = "979-8-89176-459-0",
    abstract = "Various studies have proposed methods to quantify and compare the rapidly growing number of large language models (LLMs). However, when constructing a macroscopic map of LLMs, there is a trade-off between estimation accuracy and computational cost, making the selection of evaluation texts critical. In this work, we propose Predictive Importance Sampling (PredIS), which selects informative texts by predicting likelihood variance from text-level features. Experiments on 100 LLMs across 25 domains demonstrate that our predictor generalizes robustly. Furthermore, we reveal that text importance cannot be explained by text length alone, as it is also closely tied to meaning reflected in the embedding space."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="oyama-etal-2026-length">
    <titleInfo>
        <title>Length and Meaning for Language Model Maps</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Momose</namePart>
        <namePart type="family">Oyama</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ryo</namePart>
        <namePart type="family">Kishino</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hiroaki</namePart>
        <namePart type="family">Yamagiwa</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hidetoshi</namePart>
        <namePart type="family">Shimodaira</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>Various studies have proposed methods to quantify and compare the rapidly growing number of large language models (LLMs). However, when constructing a macroscopic map of LLMs, there is a trade-off between estimation accuracy and computational cost, making the selection of evaluation texts critical. In this work, we propose Predictive Importance Sampling (PredIS), which selects informative texts by predicting likelihood variance from text-level features. Experiments on 100 LLMs across 25 domains demonstrate that our predictor generalizes robustly. Furthermore, we reveal that text importance cannot be explained by text length alone, as it is also closely tied to meaning reflected in the embedding space.</abstract>
    <identifier type="citekey">oyama-etal-2026-length</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1510/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>34472</start>
            <end>34487</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Length and Meaning for Language Model Maps
%A Oyama, Momose
%A Kishino, Ryo
%A Yamagiwa, Hiroaki
%A Shimodaira, Hidetoshi
%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 oyama-etal-2026-length
%X Various studies have proposed methods to quantify and compare the rapidly growing number of large language models (LLMs). However, when constructing a macroscopic map of LLMs, there is a trade-off between estimation accuracy and computational cost, making the selection of evaluation texts critical. In this work, we propose Predictive Importance Sampling (PredIS), which selects informative texts by predicting likelihood variance from text-level features. Experiments on 100 LLMs across 25 domains demonstrate that our predictor generalizes robustly. Furthermore, we reveal that text importance cannot be explained by text length alone, as it is also closely tied to meaning reflected in the embedding space.
%U https://aclanthology.org/2026.emnlp-main.1510/
%P 34472-34487

Download as File

Markdown (Informal)

[Length and Meaning for Language Model Maps](https://aclanthology.org/2026.emnlp-main.1510/) (Oyama et al., EMNLP 2026)

Length and Meaning for Language Model Maps (Oyama et al., EMNLP 2026)

ACL

Momose Oyama, Ryo Kishino, Hiroaki Yamagiwa, and Hidetoshi Shimodaira. 2026. Length and Meaning for Language Model Maps. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 34472–34487, Budapest, Hungary. Association for Computational Linguistics.