@inproceedings{chen-etal-2024-mdcr,
title = "{MDCR}: A Dataset for Multi-Document Conditional Reasoning",
author = "Chen, Peter Baile and
Zhang, Yi and
Liu, Chunwei and
Gupta, Sejal and
Kim, Yoon and
Cafarella, Mike",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.667",
pages = "11407--11424",
abstract = "The same real-life questions posed to different individuals may lead to different answers based on their unique situations. For instance, whether a student is eligible for a scholarship depends on eligibility conditions, such as major or degree required. ConditionalQA was proposed to evaluate models{'} capability of reading a document and answering eligibility questions, considering *unmentioned* conditions. However, it is limited to questions on single documents, neglecting harder cases that may require *cross-document reasoning* and *optimization*, for example, {``}What is the maximum number of scholarships attainable?{''} Such questions over multiple documents are not only more challenging due to more context to understand, but also because the model has to (1) explore all possible combinations of unmentioned conditions and (2) understand the relationship between conditions across documents, to reason about the optimal outcome. To evaluate models{'} capability of answering such questions, we propose a new dataset MDCR, which can reflect real-world challenges and serve as a new test bed for complex conditional reasoning that requires optimization. We evaluate this dataset using the most recent LLMs and demonstrate their limitations in solving this task. We believe this dataset will facilitate future research in answering optimization questions with unknown conditions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2024-mdcr">
<titleInfo>
<title>MDCR: A Dataset for Multi-Document Conditional Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="given">Baile</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chunwei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sejal</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoon</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Cafarella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The same real-life questions posed to different individuals may lead to different answers based on their unique situations. For instance, whether a student is eligible for a scholarship depends on eligibility conditions, such as major or degree required. ConditionalQA was proposed to evaluate models’ capability of reading a document and answering eligibility questions, considering *unmentioned* conditions. However, it is limited to questions on single documents, neglecting harder cases that may require *cross-document reasoning* and *optimization*, for example, “What is the maximum number of scholarships attainable?” Such questions over multiple documents are not only more challenging due to more context to understand, but also because the model has to (1) explore all possible combinations of unmentioned conditions and (2) understand the relationship between conditions across documents, to reason about the optimal outcome. To evaluate models’ capability of answering such questions, we propose a new dataset MDCR, which can reflect real-world challenges and serve as a new test bed for complex conditional reasoning that requires optimization. We evaluate this dataset using the most recent LLMs and demonstrate their limitations in solving this task. We believe this dataset will facilitate future research in answering optimization questions with unknown conditions.</abstract>
<identifier type="citekey">chen-etal-2024-mdcr</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.667</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>11407</start>
<end>11424</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MDCR: A Dataset for Multi-Document Conditional Reasoning
%A Chen, Peter Baile
%A Zhang, Yi
%A Liu, Chunwei
%A Gupta, Sejal
%A Kim, Yoon
%A Cafarella, Mike
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F chen-etal-2024-mdcr
%X The same real-life questions posed to different individuals may lead to different answers based on their unique situations. For instance, whether a student is eligible for a scholarship depends on eligibility conditions, such as major or degree required. ConditionalQA was proposed to evaluate models’ capability of reading a document and answering eligibility questions, considering *unmentioned* conditions. However, it is limited to questions on single documents, neglecting harder cases that may require *cross-document reasoning* and *optimization*, for example, “What is the maximum number of scholarships attainable?” Such questions over multiple documents are not only more challenging due to more context to understand, but also because the model has to (1) explore all possible combinations of unmentioned conditions and (2) understand the relationship between conditions across documents, to reason about the optimal outcome. To evaluate models’ capability of answering such questions, we propose a new dataset MDCR, which can reflect real-world challenges and serve as a new test bed for complex conditional reasoning that requires optimization. We evaluate this dataset using the most recent LLMs and demonstrate their limitations in solving this task. We believe this dataset will facilitate future research in answering optimization questions with unknown conditions.
%U https://aclanthology.org/2024.findings-emnlp.667
%P 11407-11424
Markdown (Informal)
[MDCR: A Dataset for Multi-Document Conditional Reasoning](https://aclanthology.org/2024.findings-emnlp.667) (Chen et al., Findings 2024)
ACL
- Peter Baile Chen, Yi Zhang, Chunwei Liu, Sejal Gupta, Yoon Kim, and Mike Cafarella. 2024. MDCR: A Dataset for Multi-Document Conditional Reasoning. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 11407–11424, Miami, Florida, USA. Association for Computational Linguistics.