@inproceedings{stoyanchev-etal-2026-context,
title = "Context-Aware Language Understanding in Human-Robot Dialogue with {LLM}s",
author = "Stoyanchev, Svetlana and
Farag, Youmna and
Keizer, Simon and
Li, Mohan and
Doddipatla, Rama Sanand",
editor = "Riccardi, Giuseppe and
Mousavi, Seyed Mahed and
Torres, Maria Ines and
Yoshino, Koichiro and
Callejas, Zoraida and
Chowdhury, Shammur Absar and
Chen, Yun-Nung and
Bechet, Frederic and
Gustafson, Joakim and
Damnati, G{\'e}raldine and
Papangelis, Alex and
D{'}Haro, Luis Fernando and
Mendon{\c{c}}a, John and
Bernardi, Raffaella and
Hakkani-Tur, Dilek and
Di Fabbrizio, Giuseppe {''}Pino{''} and
Kawahara, Tatsuya and
Alam, Firoj and
Tur, Gokhan and
Johnston, Michael",
booktitle = "Proceedings of the 16th International Workshop on Spoken Dialogue System Technology",
month = feb,
year = "2026",
address = "Trento, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.iwsds-1.27/",
pages = "262--274",
abstract = "In this work, we explore the use of large language models ({LLM}s) as interpreters of user utterances within a human-robot language interface. A user interacting with a robot that operates in a physical environment should be able to issue commands that interrupt the robot{'}s actions, for example, corrections or refinement of the task. This study addresses the context-aware interpretation of user utterances, including those issued while the robot is actively engaged in task execution, exploring whether {LLM}s, without fine-tuning, can translate user commands into corresponding sequences of robot actions. Using an interactive multimodal interface{---}combining text and video{---}for a virtual robot operating in simulated home environments, we collect a dataset of user utterances that guide the robot through various household tasks simultaneously capturing manual interpretation when the automatic one fails. Driven by practical considerations, the collected dataset is used to compare the interpretive performance of {GPT} models with smaller publicly available alternatives. Our findings reveal that action-interrupting utterances pose challenges for all models. While {GPT} consistently outperforms the smaller models, interpretation accuracy improves across the board when relevant dynamically selected in-context learning examples are included in the prompt."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stoyanchev-etal-2026-context">
<titleInfo>
<title>Context-Aware Language Understanding in Human-Robot Dialogue with LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Svetlana</namePart>
<namePart type="family">Stoyanchev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youmna</namePart>
<namePart type="family">Farag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Keizer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rama</namePart>
<namePart type="given">Sanand</namePart>
<namePart type="family">Doddipatla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-02</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th International Workshop on Spoken Dialogue System Technology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Riccardi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seyed</namePart>
<namePart type="given">Mahed</namePart>
<namePart type="family">Mousavi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Ines</namePart>
<namePart type="family">Torres</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koichiro</namePart>
<namePart type="family">Yoshino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zoraida</namePart>
<namePart type="family">Callejas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shammur</namePart>
<namePart type="given">Absar</namePart>
<namePart type="family">Chowdhury</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>
<name type="personal">
<namePart type="given">Frederic</namePart>
<namePart type="family">Bechet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joakim</namePart>
<namePart type="family">Gustafson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Géraldine</namePart>
<namePart type="family">Damnati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Papangelis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="given">Fernando</namePart>
<namePart type="family">D’Haro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Mendonça</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raffaella</namePart>
<namePart type="family">Bernardi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="given">”Pino”</namePart>
<namePart type="family">Di Fabbrizio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tatsuya</namePart>
<namePart type="family">Kawahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Firoj</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gokhan</namePart>
<namePart type="family">Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Johnston</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Trento, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we explore the use of large language models (LLMs) as interpreters of user utterances within a human-robot language interface. A user interacting with a robot that operates in a physical environment should be able to issue commands that interrupt the robot’s actions, for example, corrections or refinement of the task. This study addresses the context-aware interpretation of user utterances, including those issued while the robot is actively engaged in task execution, exploring whether LLMs, without fine-tuning, can translate user commands into corresponding sequences of robot actions. Using an interactive multimodal interface—combining text and video—for a virtual robot operating in simulated home environments, we collect a dataset of user utterances that guide the robot through various household tasks simultaneously capturing manual interpretation when the automatic one fails. Driven by practical considerations, the collected dataset is used to compare the interpretive performance of GPT models with smaller publicly available alternatives. Our findings reveal that action-interrupting utterances pose challenges for all models. While GPT consistently outperforms the smaller models, interpretation accuracy improves across the board when relevant dynamically selected in-context learning examples are included in the prompt.</abstract>
<identifier type="citekey">stoyanchev-etal-2026-context</identifier>
<location>
<url>https://aclanthology.org/2026.iwsds-1.27/</url>
</location>
<part>
<date>2026-02</date>
<extent unit="page">
<start>262</start>
<end>274</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Context-Aware Language Understanding in Human-Robot Dialogue with LLMs
%A Stoyanchev, Svetlana
%A Farag, Youmna
%A Keizer, Simon
%A Li, Mohan
%A Doddipatla, Rama Sanand
%Y Riccardi, Giuseppe
%Y Mousavi, Seyed Mahed
%Y Torres, Maria Ines
%Y Yoshino, Koichiro
%Y Callejas, Zoraida
%Y Chowdhury, Shammur Absar
%Y Chen, Yun-Nung
%Y Bechet, Frederic
%Y Gustafson, Joakim
%Y Damnati, Géraldine
%Y Papangelis, Alex
%Y D’Haro, Luis Fernando
%Y Mendonça, John
%Y Bernardi, Raffaella
%Y Hakkani-Tur, Dilek
%Y Di Fabbrizio, Giuseppe ”Pino”
%Y Kawahara, Tatsuya
%Y Alam, Firoj
%Y Tur, Gokhan
%Y Johnston, Michael
%S Proceedings of the 16th International Workshop on Spoken Dialogue System Technology
%D 2026
%8 February
%I Association for Computational Linguistics
%C Trento, Italy
%F stoyanchev-etal-2026-context
%X In this work, we explore the use of large language models (LLMs) as interpreters of user utterances within a human-robot language interface. A user interacting with a robot that operates in a physical environment should be able to issue commands that interrupt the robot’s actions, for example, corrections or refinement of the task. This study addresses the context-aware interpretation of user utterances, including those issued while the robot is actively engaged in task execution, exploring whether LLMs, without fine-tuning, can translate user commands into corresponding sequences of robot actions. Using an interactive multimodal interface—combining text and video—for a virtual robot operating in simulated home environments, we collect a dataset of user utterances that guide the robot through various household tasks simultaneously capturing manual interpretation when the automatic one fails. Driven by practical considerations, the collected dataset is used to compare the interpretive performance of GPT models with smaller publicly available alternatives. Our findings reveal that action-interrupting utterances pose challenges for all models. While GPT consistently outperforms the smaller models, interpretation accuracy improves across the board when relevant dynamically selected in-context learning examples are included in the prompt.
%U https://aclanthology.org/2026.iwsds-1.27/
%P 262-274
Markdown (Informal)
[Context-Aware Language Understanding in Human-Robot Dialogue with LLMs](https://aclanthology.org/2026.iwsds-1.27/) (Stoyanchev et al., IWSDS 2026)
ACL