@inproceedings{da-silva-ferreira-junior-etal-2025-generating,
title = "Generating Impact and Critique Explanations of Predictions made by a Goal Recognizer",
author = "da Silva Ferreira Junior, Jair and
Zukerman, Ingrid and
Makalic, Enes and
Paris, Cecile L. and
Vered, Mor",
editor = "Flek, Lucie and
Narayan, Shashi and
Phương, L{\^e} Hồng and
Pei, Jiahuan",
booktitle = "Proceedings of the 18th International Natural Language Generation Conference",
month = oct,
year = "2025",
address = "Hanoi, Vietnam",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.inlg-main.34/",
pages = "554--575",
abstract = "In this paper, we generate two types of explanations, Impact and Critique, of predictions made by a Goal Recognizer (GR) {--} a system that infers agents' goals from observations. Impact explanations describe the top-predicted goal(s) and the main observations that led to these predictions. Critique explanations augment these explanations with evidence that challenges the GR{'}s predictions if so warranted. Our user study compares users' goal-recognition accuracy for Impact and Critique explanations, and users' views about these explanations, under three prediction-correctness conditions: correct, partially correct and incorrect. Our results show that (1) users stick with a GR{'}s predictions, even when a Critique explanation highlights its flaws; yet (2) Critique explanations are deemed better than Impact explanations in most respects."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="da-silva-ferreira-junior-etal-2025-generating">
<titleInfo>
<title>Generating Impact and Critique Explanations of Predictions made by a Goal Recognizer</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jair</namePart>
<namePart type="family">da Silva Ferreira Junior</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ingrid</namePart>
<namePart type="family">Zukerman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enes</namePart>
<namePart type="family">Makalic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cecile</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Paris</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mor</namePart>
<namePart type="family">Vered</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Natural Language Generation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lucie</namePart>
<namePart type="family">Flek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shashi</namePart>
<namePart type="family">Narayan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lê</namePart>
<namePart type="given">Hồng</namePart>
<namePart type="family">Phương</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiahuan</namePart>
<namePart type="family">Pei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hanoi, Vietnam</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we generate two types of explanations, Impact and Critique, of predictions made by a Goal Recognizer (GR) – a system that infers agents’ goals from observations. Impact explanations describe the top-predicted goal(s) and the main observations that led to these predictions. Critique explanations augment these explanations with evidence that challenges the GR’s predictions if so warranted. Our user study compares users’ goal-recognition accuracy for Impact and Critique explanations, and users’ views about these explanations, under three prediction-correctness conditions: correct, partially correct and incorrect. Our results show that (1) users stick with a GR’s predictions, even when a Critique explanation highlights its flaws; yet (2) Critique explanations are deemed better than Impact explanations in most respects.</abstract>
<identifier type="citekey">da-silva-ferreira-junior-etal-2025-generating</identifier>
<location>
<url>https://aclanthology.org/2025.inlg-main.34/</url>
</location>
<part>
<date>2025-10</date>
<extent unit="page">
<start>554</start>
<end>575</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating Impact and Critique Explanations of Predictions made by a Goal Recognizer
%A da Silva Ferreira Junior, Jair
%A Zukerman, Ingrid
%A Makalic, Enes
%A Paris, Cecile L.
%A Vered, Mor
%Y Flek, Lucie
%Y Narayan, Shashi
%Y Phương, Lê Hồng
%Y Pei, Jiahuan
%S Proceedings of the 18th International Natural Language Generation Conference
%D 2025
%8 October
%I Association for Computational Linguistics
%C Hanoi, Vietnam
%F da-silva-ferreira-junior-etal-2025-generating
%X In this paper, we generate two types of explanations, Impact and Critique, of predictions made by a Goal Recognizer (GR) – a system that infers agents’ goals from observations. Impact explanations describe the top-predicted goal(s) and the main observations that led to these predictions. Critique explanations augment these explanations with evidence that challenges the GR’s predictions if so warranted. Our user study compares users’ goal-recognition accuracy for Impact and Critique explanations, and users’ views about these explanations, under three prediction-correctness conditions: correct, partially correct and incorrect. Our results show that (1) users stick with a GR’s predictions, even when a Critique explanation highlights its flaws; yet (2) Critique explanations are deemed better than Impact explanations in most respects.
%U https://aclanthology.org/2025.inlg-main.34/
%P 554-575
Markdown (Informal)
[Generating Impact and Critique Explanations of Predictions made by a Goal Recognizer](https://aclanthology.org/2025.inlg-main.34/) (da Silva Ferreira Junior et al., INLG 2025)
ACL