@inproceedings{collado-montanez-etal-2026-evalex,
title = "{E}va{L}ex: Automatic Evaluation of Lexical Competence in Language Models",
author = "Collado-Monta{\~n}ez, Jaime and
Ure{\~n}a, L. Alfonso and
Montejo-R{\'a}ez, Arturo",
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.2490/",
pages = "56526--56539",
ISBN = "979-8-89176-459-0",
abstract = "Existing methods for evaluating lexical competence in language models often rely on discriminative tasks or expensive, human-curated datasets. We introduce EvaLex, an automated framework to evaluate lexical competence in language models without gold labels. EvaLex employs a bidirectional approach: it first prompts a model to define a target word and subsequently tasks the model with retrieving that same word from its own generated definition in a separate inference session. We evaluate EvaLex on two Spanish datasets: CREA-10k-POS (7,784 words) and CREA-10k-Lemmas (4,594 lemmas), and we further validate against an expert-annotated DEA sample (100 words). We compare similarly sized LLMs (Llama, Mistral, Yi, Gemma) alongside Spanish-centric models (Gromenauer, Salamandra). EvaLex scores correlate strongly with expert manual annotations (Pearson r = 0.8539, Spearman rho = 0.8) across the four models for which manual annotations were available, supporting its use as a proxy for human judgments. Broader validation across more models and languages remains an open priority. We also observe a clear frequency effect, with Spanish-specific models remaining more robust on low-frequency terms. Overall, EvaLex provides a scalable and low-cost method for model selection and for diagnosing lexical gaps in low-resource and cross-lingual settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="collado-montanez-etal-2026-evalex">
<titleInfo>
<title>EvaLex: Automatic Evaluation of Lexical Competence in Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jaime</namePart>
<namePart type="family">Collado-Montañez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">L</namePart>
<namePart type="given">Alfonso</namePart>
<namePart type="family">Ureña</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arturo</namePart>
<namePart type="family">Montejo-Ráez</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>Existing methods for evaluating lexical competence in language models often rely on discriminative tasks or expensive, human-curated datasets. We introduce EvaLex, an automated framework to evaluate lexical competence in language models without gold labels. EvaLex employs a bidirectional approach: it first prompts a model to define a target word and subsequently tasks the model with retrieving that same word from its own generated definition in a separate inference session. We evaluate EvaLex on two Spanish datasets: CREA-10k-POS (7,784 words) and CREA-10k-Lemmas (4,594 lemmas), and we further validate against an expert-annotated DEA sample (100 words). We compare similarly sized LLMs (Llama, Mistral, Yi, Gemma) alongside Spanish-centric models (Gromenauer, Salamandra). EvaLex scores correlate strongly with expert manual annotations (Pearson r = 0.8539, Spearman rho = 0.8) across the four models for which manual annotations were available, supporting its use as a proxy for human judgments. Broader validation across more models and languages remains an open priority. We also observe a clear frequency effect, with Spanish-specific models remaining more robust on low-frequency terms. Overall, EvaLex provides a scalable and low-cost method for model selection and for diagnosing lexical gaps in low-resource and cross-lingual settings.</abstract>
<identifier type="citekey">collado-montanez-etal-2026-evalex</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2490/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>56526</start>
<end>56539</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EvaLex: Automatic Evaluation of Lexical Competence in Language Models
%A Collado-Montañez, Jaime
%A Ureña, L. Alfonso
%A Montejo-Ráez, Arturo
%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 collado-montanez-etal-2026-evalex
%X Existing methods for evaluating lexical competence in language models often rely on discriminative tasks or expensive, human-curated datasets. We introduce EvaLex, an automated framework to evaluate lexical competence in language models without gold labels. EvaLex employs a bidirectional approach: it first prompts a model to define a target word and subsequently tasks the model with retrieving that same word from its own generated definition in a separate inference session. We evaluate EvaLex on two Spanish datasets: CREA-10k-POS (7,784 words) and CREA-10k-Lemmas (4,594 lemmas), and we further validate against an expert-annotated DEA sample (100 words). We compare similarly sized LLMs (Llama, Mistral, Yi, Gemma) alongside Spanish-centric models (Gromenauer, Salamandra). EvaLex scores correlate strongly with expert manual annotations (Pearson r = 0.8539, Spearman rho = 0.8) across the four models for which manual annotations were available, supporting its use as a proxy for human judgments. Broader validation across more models and languages remains an open priority. We also observe a clear frequency effect, with Spanish-specific models remaining more robust on low-frequency terms. Overall, EvaLex provides a scalable and low-cost method for model selection and for diagnosing lexical gaps in low-resource and cross-lingual settings.
%U https://aclanthology.org/2026.emnlp-main.2490/
%P 56526-56539
Markdown (Informal)
[EvaLex: Automatic Evaluation of Lexical Competence in Language Models](https://aclanthology.org/2026.emnlp-main.2490/) (Collado-Montañez et al., EMNLP 2026)
ACL