<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kennington-etal-2025-prior">
    <titleInfo>
        <title>Prior Lessons of Incremental Dialogue and Robot Action Management for the Age of Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Casey</namePart>
        <namePart type="family">Kennington</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pierre</namePart>
        <namePart type="family">Lison</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">David</namePart>
        <namePart type="family">Schlangen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Dialogue &amp; Discourse</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>University of Illinois Chicago</publisher>
            <place>
                <placeTerm type="text">Chicago, Illinois, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Efforts towards endowing robots with the ability to speak have benefited from recent advancements in natural language processing, in particular large language models. However, current language models are not fully incremental, as their processing is inherently monotonic and thus lack the ability to revise their interpretations or output in light of newer observations. This monotonicity has important implications for the development of dialogue systems for human–robot interaction. In this paper, we review the literature on interactive systems that operate incrementally (i.e., at the word level or below it). We motivate the need for incremental systems, survey incremental modeling of important aspects of dialogue like speech recognition and language generation. Primary focus is on the part of the system that makes decisions, known as the dialogue manager. We find that there is very little research on incremental dialogue management, offer some requirements for practical incremental dialogue management, and implications of incremental dialogue for embodied, robotic platforms in the age of large language models.</abstract>
    <identifier type="citekey">kennington-etal-2025-prior</identifier>
    <identifier type="doi">10.5210/dad.2025.305</identifier>
    <location>
        <url>https://aclanthology.org/2025.dnd-16.10/</url>
    </location>
    <part>
        <date>2025-12</date>
        <detail type="volume"><number>16</number></detail>
        <extent unit="page">
            <start>96</start>
            <end>130</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Prior Lessons of Incremental Dialogue and Robot Action Management for the Age of Language Models
%A Kennington, Casey
%A Lison, Pierre
%A Schlangen, David
%J Dialogue & Discourse
%D 2025
%8 December
%V 16
%I University of Illinois Chicago
%C Chicago, Illinois, USA
%F kennington-etal-2025-prior
%X Efforts towards endowing robots with the ability to speak have benefited from recent advancements in natural language processing, in particular large language models. However, current language models are not fully incremental, as their processing is inherently monotonic and thus lack the ability to revise their interpretations or output in light of newer observations. This monotonicity has important implications for the development of dialogue systems for human–robot interaction. In this paper, we review the literature on interactive systems that operate incrementally (i.e., at the word level or below it). We motivate the need for incremental systems, survey incremental modeling of important aspects of dialogue like speech recognition and language generation. Primary focus is on the part of the system that makes decisions, known as the dialogue manager. We find that there is very little research on incremental dialogue management, offer some requirements for practical incremental dialogue management, and implications of incremental dialogue for embodied, robotic platforms in the age of large language models.
%R 10.5210/dad.2025.305
%U https://aclanthology.org/2025.dnd-16.10/
%U https://doi.org/10.5210/dad.2025.305
%P 96-130

Markdown (Informal)

[Prior Lessons of Incremental Dialogue and Robot Action Management for the Age of Language Models](https://aclanthology.org/2025.dnd-16.10/) (Kennington et al., DND 2025)

• Prior Lessons of Incremental Dialogue and Robot Action Management for the Age of Language Models (Kennington et al., DND 2025)

ACL

• Casey Kennington, Pierre Lison, and David Schlangen. 2025. Prior Lessons of Incremental Dialogue and Robot Action Management for the Age of Language Models. Dialogue & Discourse, 16:96–130.