@inproceedings{diallo-etal-2024-pizzacommonsense,
title = "{P}izza{C}ommon{S}ense: A Dataset for Commonsense Reasoning about Intermediate Steps in Cooking Recipes",
author = "Diallo, Aissatou and
Bikakis, Antonis and
Dickens, Luke and
Hunter, Anthony and
Miller, Rob",
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.728",
pages = "12482--12496",
abstract = "Understanding procedural texts, such as cooking recipes, is essential for enabling machines to follow instructions and reason about tasks, a key aspect of intelligent reasoning. In cooking, these instructions can be interpreted as a series of modifications to a food preparation.For a model to effectively reason about cooking recipes, it must accurately discern and understand the inputs and outputs of intermediate steps within the recipe.We present a new corpus of cooking recipes enriched with descriptions of intermediate steps that describe the input and output for each step. PizzaCommonsense serves as a benchmark for the reasoning capabilities of LLMs because it demands rigorous explicit input-output descriptions to demonstrate the acquisition of implicit commonsense knowledge, which is unlikely to beeasily memorized. GPT-4 achieves only 26{\%} human-evaluated preference for generations, leaving room for future improvements.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="diallo-etal-2024-pizzacommonsense">
<titleInfo>
<title>PizzaCommonSense: A Dataset for Commonsense Reasoning about Intermediate Steps in Cooking Recipes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aissatou</namePart>
<namePart type="family">Diallo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonis</namePart>
<namePart type="family">Bikakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Dickens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anthony</namePart>
<namePart type="family">Hunter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rob</namePart>
<namePart type="family">Miller</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>Understanding procedural texts, such as cooking recipes, is essential for enabling machines to follow instructions and reason about tasks, a key aspect of intelligent reasoning. In cooking, these instructions can be interpreted as a series of modifications to a food preparation.For a model to effectively reason about cooking recipes, it must accurately discern and understand the inputs and outputs of intermediate steps within the recipe.We present a new corpus of cooking recipes enriched with descriptions of intermediate steps that describe the input and output for each step. PizzaCommonsense serves as a benchmark for the reasoning capabilities of LLMs because it demands rigorous explicit input-output descriptions to demonstrate the acquisition of implicit commonsense knowledge, which is unlikely to beeasily memorized. GPT-4 achieves only 26% human-evaluated preference for generations, leaving room for future improvements.</abstract>
<identifier type="citekey">diallo-etal-2024-pizzacommonsense</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.728</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>12482</start>
<end>12496</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PizzaCommonSense: A Dataset for Commonsense Reasoning about Intermediate Steps in Cooking Recipes
%A Diallo, Aissatou
%A Bikakis, Antonis
%A Dickens, Luke
%A Hunter, Anthony
%A Miller, Rob
%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 diallo-etal-2024-pizzacommonsense
%X Understanding procedural texts, such as cooking recipes, is essential for enabling machines to follow instructions and reason about tasks, a key aspect of intelligent reasoning. In cooking, these instructions can be interpreted as a series of modifications to a food preparation.For a model to effectively reason about cooking recipes, it must accurately discern and understand the inputs and outputs of intermediate steps within the recipe.We present a new corpus of cooking recipes enriched with descriptions of intermediate steps that describe the input and output for each step. PizzaCommonsense serves as a benchmark for the reasoning capabilities of LLMs because it demands rigorous explicit input-output descriptions to demonstrate the acquisition of implicit commonsense knowledge, which is unlikely to beeasily memorized. GPT-4 achieves only 26% human-evaluated preference for generations, leaving room for future improvements.
%U https://aclanthology.org/2024.findings-emnlp.728
%P 12482-12496
Markdown (Informal)
[PizzaCommonSense: A Dataset for Commonsense Reasoning about Intermediate Steps in Cooking Recipes](https://aclanthology.org/2024.findings-emnlp.728) (Diallo et al., Findings 2024)
ACL