@inproceedings{pardasani-singh-2026-recognized,
title = "Recognized but Not Produced: A Generation Benchmark for Culturally Specific Kinship Terms",
author = "Pardasani, Sahil and
Singh, Madhusudan",
editor = "Ranaldi, Leonardo and
Pucci, Giulia and
Ranaldi, Federico and
Valentino, Marco and
Birch, Alexandra and
Zanzotto, Fabio Massimo",
booktitle = "The Proceedings of the Workshop on Open Reasoning Across Cultures Languages ({ORACLE})",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.oracle-main.31/",
pages = "459--467",
ISBN = "979-8-89176-483-5",
abstract = "Current literature evaluates large language models (LLMs) on multilingual kinship understanding using multiple-choice benchmarks, treating it as a recognition problem. We instead prompt five open-weight LLMs to generate kinship terms in three non-Western languages (Hindi, Tamil, and Korean) across two communicative tasks, and pair this with a matched option-supported selection baseline. On identical relation{--}language cells, GPT-OSS120B selects the correct term in 90.67{\%} of 75 valid cells but produces an accepted term in 36.00{\%} of the corresponding attempts; Llama3.3-70B shows the same pattern (77.92{\%} versus 24.24{\%}). Since the four-option condition displays the candidate terms and does not require script production, the difference is interpreted as an evaluation-format gap rather than direct proof that lexical knowledge is intact. On explicitly specified L3 prompts, accuracy varies sharply, from GLM-5.1 at 72.29{\%} to Llama3.3-70B at 24.24{\%}. The paternal-lineage advantage is language-specific: it is large in Hindi, but weak or reversed in Korean, while Tamil shared-term pairs provide a control for measurement variation. These results show that culturally specific kinship generation remains difficult even when the relationship is explicitly stated and motivate generation-based evaluation alongside multiple-choice testing."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pardasani-singh-2026-recognized">
<titleInfo>
<title>Recognized but Not Produced: A Generation Benchmark for Culturally Specific Kinship Terms</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sahil</namePart>
<namePart type="family">Pardasani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Madhusudan</namePart>
<namePart type="family">Singh</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>The Proceedings of the Workshop on Open Reasoning Across Cultures Languages (ORACLE)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leonardo</namePart>
<namePart type="family">Ranaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giulia</namePart>
<namePart type="family">Pucci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Federico</namePart>
<namePart type="family">Ranaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Valentino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Birch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="given">Massimo</namePart>
<namePart type="family">Zanzotto</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">979-8-89176-483-5</identifier>
</relatedItem>
<abstract>Current literature evaluates large language models (LLMs) on multilingual kinship understanding using multiple-choice benchmarks, treating it as a recognition problem. We instead prompt five open-weight LLMs to generate kinship terms in three non-Western languages (Hindi, Tamil, and Korean) across two communicative tasks, and pair this with a matched option-supported selection baseline. On identical relation–language cells, GPT-OSS120B selects the correct term in 90.67% of 75 valid cells but produces an accepted term in 36.00% of the corresponding attempts; Llama3.3-70B shows the same pattern (77.92% versus 24.24%). Since the four-option condition displays the candidate terms and does not require script production, the difference is interpreted as an evaluation-format gap rather than direct proof that lexical knowledge is intact. On explicitly specified L3 prompts, accuracy varies sharply, from GLM-5.1 at 72.29% to Llama3.3-70B at 24.24%. The paternal-lineage advantage is language-specific: it is large in Hindi, but weak or reversed in Korean, while Tamil shared-term pairs provide a control for measurement variation. These results show that culturally specific kinship generation remains difficult even when the relationship is explicitly stated and motivate generation-based evaluation alongside multiple-choice testing.</abstract>
<identifier type="citekey">pardasani-singh-2026-recognized</identifier>
<location>
<url>https://aclanthology.org/2026.oracle-main.31/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>459</start>
<end>467</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Recognized but Not Produced: A Generation Benchmark for Culturally Specific Kinship Terms
%A Pardasani, Sahil
%A Singh, Madhusudan
%Y Ranaldi, Leonardo
%Y Pucci, Giulia
%Y Ranaldi, Federico
%Y Valentino, Marco
%Y Birch, Alexandra
%Y Zanzotto, Fabio Massimo
%S The Proceedings of the Workshop on Open Reasoning Across Cultures Languages (ORACLE)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-483-5
%F pardasani-singh-2026-recognized
%X Current literature evaluates large language models (LLMs) on multilingual kinship understanding using multiple-choice benchmarks, treating it as a recognition problem. We instead prompt five open-weight LLMs to generate kinship terms in three non-Western languages (Hindi, Tamil, and Korean) across two communicative tasks, and pair this with a matched option-supported selection baseline. On identical relation–language cells, GPT-OSS120B selects the correct term in 90.67% of 75 valid cells but produces an accepted term in 36.00% of the corresponding attempts; Llama3.3-70B shows the same pattern (77.92% versus 24.24%). Since the four-option condition displays the candidate terms and does not require script production, the difference is interpreted as an evaluation-format gap rather than direct proof that lexical knowledge is intact. On explicitly specified L3 prompts, accuracy varies sharply, from GLM-5.1 at 72.29% to Llama3.3-70B at 24.24%. The paternal-lineage advantage is language-specific: it is large in Hindi, but weak or reversed in Korean, while Tamil shared-term pairs provide a control for measurement variation. These results show that culturally specific kinship generation remains difficult even when the relationship is explicitly stated and motivate generation-based evaluation alongside multiple-choice testing.
%U https://aclanthology.org/2026.oracle-main.31/
%P 459-467
Markdown (Informal)
[Recognized but Not Produced: A Generation Benchmark for Culturally Specific Kinship Terms](https://aclanthology.org/2026.oracle-main.31/) (Pardasani & Singh, ORACLE 2026)
ACL