@inproceedings{wang-etal-2026-investigating,
title = "Investigating the Representation of Backchannels and Fillers in Fine-tuned Language Models",
author = "Wang, Yu and
Lao, Leyi and
Huang, Langchu and
Skantze, Gabriel and
Xu, Yang and
Buschmeier, Hendrik",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.241/",
pages = "5319--5348",
ISBN = "979-8-89176-390-6",
abstract = "Backchannels and fillers are important linguistic expressions in dialogue, but often treated as ``noise'' to be bypassed in modern transformer-based language models. Our work studies the representation of them in language models using three fine-tuning strategies. The models are trained on three dialogue corpora in English and Japanese, where backchannels and fillers are preserved and annotated, to investigate how fine-tuning can help LMs learn their representations. We first apply clustering analysis to the learnt representation of backchannels and fillers, and have found increased silhouette scores in representations from fine-tuned models, which suggests that fine-tuning enables LMs to distinguish the nuanced semantic variation in different backchannel and filler use. We also use natural language generation (NLG) metrics and qualitative analysis to confirm that the utterances generated by fine-tuned language models resemble human-produced utterances more closely. Our findings suggest the potentials of transforming general LMs into conversational LMs that are more capable of producing human-like languages adequately."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-investigating">
<titleInfo>
<title>Investigating the Representation of Backchannels and Fillers in Fine-tuned Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leyi</namePart>
<namePart type="family">Lao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Langchu</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Skantze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hendrik</namePart>
<namePart type="family">Buschmeier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Backchannels and fillers are important linguistic expressions in dialogue, but often treated as “noise” to be bypassed in modern transformer-based language models. Our work studies the representation of them in language models using three fine-tuning strategies. The models are trained on three dialogue corpora in English and Japanese, where backchannels and fillers are preserved and annotated, to investigate how fine-tuning can help LMs learn their representations. We first apply clustering analysis to the learnt representation of backchannels and fillers, and have found increased silhouette scores in representations from fine-tuned models, which suggests that fine-tuning enables LMs to distinguish the nuanced semantic variation in different backchannel and filler use. We also use natural language generation (NLG) metrics and qualitative analysis to confirm that the utterances generated by fine-tuned language models resemble human-produced utterances more closely. Our findings suggest the potentials of transforming general LMs into conversational LMs that are more capable of producing human-like languages adequately.</abstract>
<identifier type="citekey">wang-etal-2026-investigating</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.241/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>5319</start>
<end>5348</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Investigating the Representation of Backchannels and Fillers in Fine-tuned Language Models
%A Wang, Yu
%A Lao, Leyi
%A Huang, Langchu
%A Skantze, Gabriel
%A Xu, Yang
%A Buschmeier, Hendrik
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F wang-etal-2026-investigating
%X Backchannels and fillers are important linguistic expressions in dialogue, but often treated as “noise” to be bypassed in modern transformer-based language models. Our work studies the representation of them in language models using three fine-tuning strategies. The models are trained on three dialogue corpora in English and Japanese, where backchannels and fillers are preserved and annotated, to investigate how fine-tuning can help LMs learn their representations. We first apply clustering analysis to the learnt representation of backchannels and fillers, and have found increased silhouette scores in representations from fine-tuned models, which suggests that fine-tuning enables LMs to distinguish the nuanced semantic variation in different backchannel and filler use. We also use natural language generation (NLG) metrics and qualitative analysis to confirm that the utterances generated by fine-tuned language models resemble human-produced utterances more closely. Our findings suggest the potentials of transforming general LMs into conversational LMs that are more capable of producing human-like languages adequately.
%U https://aclanthology.org/2026.acl-long.241/
%P 5319-5348
Markdown (Informal)
[Investigating the Representation of Backchannels and Fillers in Fine-tuned Language Models](https://aclanthology.org/2026.acl-long.241/) (Wang et al., ACL 2026)
ACL