@inproceedings{lasheras-pinheiro-2025-calquest,
title = "{C}a{LQ}uest.{PT}: Towards the Collection and Evaluation of Natural Causal Ladder Questions in {P}ortuguese for {AI} Agents",
author = "Lasheras, Uriel Anderson and
Pinheiro, Vladia",
editor = "Hettiarachchi, Hansi and
Ranasinghe, Tharindu and
Rayson, Paul and
Mitkov, Ruslan and
Gaber, Mohamed and
Premasiri, Damith and
Tan, Fiona Anting and
Uyangodage, Lasitha",
booktitle = "Proceedings of the First Workshop on Language Models for Low-Resource Languages",
month = jan,
year = "2025",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.loreslm-1.26/",
pages = "325--343",
abstract = "Large Language Models (LLMs) are increasingly central to the development of generative AI across diverse fields. While some anticipate these models may mark a step toward artificial general intelligence, their ability to handle complex causal reasoning remains unproven. Causal reasoning, particularly at Pearl`s interventional and counterfactual levels, is essential for true general intelligence. In this work, we introduce CaLQuest.PT, a dataset of over 8,000 natural causal questions in Portuguese, collected from real human interactions. Built upon a novel three-axis taxonomy, CaLQuest.PT categorizes questions by causal intent, action requirements, and the level of causal reasoning needed (associational, interventional, or counterfactual). Our findings from evaluating CaLQuest.PT`s seed questions with GPT-4o reveal that this LLM face challenges in handling interventional and relation-seeking causal queries. These results suggest limitations in using GPT-4o for extending causal question annotations and highlight the need for improved LLM strategies in causal reasoning. CaLQuest.PT provides a foundation for advancing LLM capabilities in causal understanding, particularly for the Portuguese-speaking world."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lasheras-pinheiro-2025-calquest">
<titleInfo>
<title>CaLQuest.PT: Towards the Collection and Evaluation of Natural Causal Ladder Questions in Portuguese for AI Agents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Uriel</namePart>
<namePart type="given">Anderson</namePart>
<namePart type="family">Lasheras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vladia</namePart>
<namePart type="family">Pinheiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Language Models for Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hansi</namePart>
<namePart type="family">Hettiarachchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Gaber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damith</namePart>
<namePart type="family">Premasiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fiona</namePart>
<namePart type="given">Anting</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lasitha</namePart>
<namePart type="family">Uyangodage</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Language Models (LLMs) are increasingly central to the development of generative AI across diverse fields. While some anticipate these models may mark a step toward artificial general intelligence, their ability to handle complex causal reasoning remains unproven. Causal reasoning, particularly at Pearl‘s interventional and counterfactual levels, is essential for true general intelligence. In this work, we introduce CaLQuest.PT, a dataset of over 8,000 natural causal questions in Portuguese, collected from real human interactions. Built upon a novel three-axis taxonomy, CaLQuest.PT categorizes questions by causal intent, action requirements, and the level of causal reasoning needed (associational, interventional, or counterfactual). Our findings from evaluating CaLQuest.PT‘s seed questions with GPT-4o reveal that this LLM face challenges in handling interventional and relation-seeking causal queries. These results suggest limitations in using GPT-4o for extending causal question annotations and highlight the need for improved LLM strategies in causal reasoning. CaLQuest.PT provides a foundation for advancing LLM capabilities in causal understanding, particularly for the Portuguese-speaking world.</abstract>
<identifier type="citekey">lasheras-pinheiro-2025-calquest</identifier>
<location>
<url>https://aclanthology.org/2025.loreslm-1.26/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>325</start>
<end>343</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CaLQuest.PT: Towards the Collection and Evaluation of Natural Causal Ladder Questions in Portuguese for AI Agents
%A Lasheras, Uriel Anderson
%A Pinheiro, Vladia
%Y Hettiarachchi, Hansi
%Y Ranasinghe, Tharindu
%Y Rayson, Paul
%Y Mitkov, Ruslan
%Y Gaber, Mohamed
%Y Premasiri, Damith
%Y Tan, Fiona Anting
%Y Uyangodage, Lasitha
%S Proceedings of the First Workshop on Language Models for Low-Resource Languages
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F lasheras-pinheiro-2025-calquest
%X Large Language Models (LLMs) are increasingly central to the development of generative AI across diverse fields. While some anticipate these models may mark a step toward artificial general intelligence, their ability to handle complex causal reasoning remains unproven. Causal reasoning, particularly at Pearl‘s interventional and counterfactual levels, is essential for true general intelligence. In this work, we introduce CaLQuest.PT, a dataset of over 8,000 natural causal questions in Portuguese, collected from real human interactions. Built upon a novel three-axis taxonomy, CaLQuest.PT categorizes questions by causal intent, action requirements, and the level of causal reasoning needed (associational, interventional, or counterfactual). Our findings from evaluating CaLQuest.PT‘s seed questions with GPT-4o reveal that this LLM face challenges in handling interventional and relation-seeking causal queries. These results suggest limitations in using GPT-4o for extending causal question annotations and highlight the need for improved LLM strategies in causal reasoning. CaLQuest.PT provides a foundation for advancing LLM capabilities in causal understanding, particularly for the Portuguese-speaking world.
%U https://aclanthology.org/2025.loreslm-1.26/
%P 325-343
Markdown (Informal)
[CaLQuest.PT: Towards the Collection and Evaluation of Natural Causal Ladder Questions in Portuguese for AI Agents](https://aclanthology.org/2025.loreslm-1.26/) (Lasheras & Pinheiro, LoResLM 2025)
ACL