@inproceedings{catapang-2026-position,
title = "Position: Toward a Metric Typology for Language Model Evaluation",
author = "Catapang, Jasper Kyle",
editor = "Mille, Simon and
Gehrmann, Sebastian and
Schmidtov{\'a}, Patr{\'i}cia and
Du{\v{s}}ek, Ond{\v{r}}ej and
Fadaee, Marzieh and
Lo, Kyle and
Santus, Enrico and
Stanovsky, Gabriel",
booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.gem-main.78/",
pages = "1015--1020",
ISBN = "979-8-89176-423-1",
abstract = "The critique of scalar benchmark rankings as proxies for model quality is now well-established (Raji et al., 2021; Wallach et al.,2025; Bean et al., 2025; Gehrmann et al., 2021). What the field still lacks is a shared structural vocabulary for comparing, combining, and contextualizing metric design choices. This paper provides that vocabulary: a four-primitive typology{---}representation ($\phi$), comparison ($D$), aggregation ($A$), and context ($C$){---}under which existing metrics (BLEU, BERTScore, nDCG, LLM-as-judge, calibration scores, agentic outcome measures) are explicit parameterizations of a common form. This typology is paired with a measurement{--}decision split: metrics are noisy estimators of latent constructs, and model selection is context-dependent Pareto optimization over construct estimates, not over raw scores. The typology makes implicit metric assumptions comparable and debatable rather than hidden inside a single number."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="catapang-2026-position">
<titleInfo>
<title>Position: Toward a Metric Typology for Language Model Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jasper</namePart>
<namePart type="given">Kyle</namePart>
<namePart type="family">Catapang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics (GEM)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Mille</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrícia</namePart>
<namePart type="family">Schmidtová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Dušek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marzieh</namePart>
<namePart type="family">Fadaee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyle</namePart>
<namePart type="family">Lo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Stanovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-423-1</identifier>
</relatedItem>
<abstract>The critique of scalar benchmark rankings as proxies for model quality is now well-established (Raji et al., 2021; Wallach et al.,2025; Bean et al., 2025; Gehrmann et al., 2021). What the field still lacks is a shared structural vocabulary for comparing, combining, and contextualizing metric design choices. This paper provides that vocabulary: a four-primitive typology—representation (φ), comparison (D), aggregation (A), and context (C)—under which existing metrics (BLEU, BERTScore, nDCG, LLM-as-judge, calibration scores, agentic outcome measures) are explicit parameterizations of a common form. This typology is paired with a measurement–decision split: metrics are noisy estimators of latent constructs, and model selection is context-dependent Pareto optimization over construct estimates, not over raw scores. The typology makes implicit metric assumptions comparable and debatable rather than hidden inside a single number.</abstract>
<identifier type="citekey">catapang-2026-position</identifier>
<location>
<url>https://aclanthology.org/2026.gem-main.78/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1015</start>
<end>1020</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Position: Toward a Metric Typology for Language Model Evaluation
%A Catapang, Jasper Kyle
%Y Mille, Simon
%Y Gehrmann, Sebastian
%Y Schmidtová, Patrícia
%Y Dušek, Ondřej
%Y Fadaee, Marzieh
%Y Lo, Kyle
%Y Santus, Enrico
%Y Stanovsky, Gabriel
%S Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics (GEM)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-423-1
%F catapang-2026-position
%X The critique of scalar benchmark rankings as proxies for model quality is now well-established (Raji et al., 2021; Wallach et al.,2025; Bean et al., 2025; Gehrmann et al., 2021). What the field still lacks is a shared structural vocabulary for comparing, combining, and contextualizing metric design choices. This paper provides that vocabulary: a four-primitive typology—representation (φ), comparison (D), aggregation (A), and context (C)—under which existing metrics (BLEU, BERTScore, nDCG, LLM-as-judge, calibration scores, agentic outcome measures) are explicit parameterizations of a common form. This typology is paired with a measurement–decision split: metrics are noisy estimators of latent constructs, and model selection is context-dependent Pareto optimization over construct estimates, not over raw scores. The typology makes implicit metric assumptions comparable and debatable rather than hidden inside a single number.
%U https://aclanthology.org/2026.gem-main.78/
%P 1015-1020
Markdown (Informal)
[Position: Toward a Metric Typology for Language Model Evaluation](https://aclanthology.org/2026.gem-main.78/) (Catapang, GEM 2026)
ACL