@inproceedings{addlesee-etal-2024-clarifying-completions,
title = "Clarifying Completions: Evaluating How {LLM}s Respond to Incomplete Questions",
author = "Addlesee, Angus and
Lemon, Oliver and
Eshghi, Arash",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.288",
pages = "3242--3249",
abstract = "People understand and produce language incrementally on a word by word basis. This gives rise to many characteristic conversational phenomena including long mid-sentence pauses that are followed by incremental clarification requests (iCRs) intended to recover the rest of the truncated turn (see Fig. 1; (A), (B), (C)). The ability to generate iCRs is important in natural conversational AI systems, and crucial to their accessibility to users with memory impairment. In this paper, we collect, release and analyse SLUICE-CR: a large corpus of 3000 human produced iCRs. We then use this corpus to probe the incremental processing capability of a number of state of the art LLMs by evaluating the quality of the model{'}s generated iCRs in response to incomplete questions. Our evaluations show that the ability to generate contextually appropriate iCRs only emerges at larger LLM sizes, and only when prompted with example iCRs from our corpus. They also indicate that autoregressive LMs are, in principle, able to both understand and generate language incrementally.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="addlesee-etal-2024-clarifying-completions">
<titleInfo>
<title>Clarifying Completions: Evaluating How LLMs Respond to Incomplete Questions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Angus</namePart>
<namePart type="family">Addlesee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oliver</namePart>
<namePart type="family">Lemon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arash</namePart>
<namePart type="family">Eshghi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>People understand and produce language incrementally on a word by word basis. This gives rise to many characteristic conversational phenomena including long mid-sentence pauses that are followed by incremental clarification requests (iCRs) intended to recover the rest of the truncated turn (see Fig. 1; (A), (B), (C)). The ability to generate iCRs is important in natural conversational AI systems, and crucial to their accessibility to users with memory impairment. In this paper, we collect, release and analyse SLUICE-CR: a large corpus of 3000 human produced iCRs. We then use this corpus to probe the incremental processing capability of a number of state of the art LLMs by evaluating the quality of the model’s generated iCRs in response to incomplete questions. Our evaluations show that the ability to generate contextually appropriate iCRs only emerges at larger LLM sizes, and only when prompted with example iCRs from our corpus. They also indicate that autoregressive LMs are, in principle, able to both understand and generate language incrementally.</abstract>
<identifier type="citekey">addlesee-etal-2024-clarifying-completions</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.288</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>3242</start>
<end>3249</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Clarifying Completions: Evaluating How LLMs Respond to Incomplete Questions
%A Addlesee, Angus
%A Lemon, Oliver
%A Eshghi, Arash
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F addlesee-etal-2024-clarifying-completions
%X People understand and produce language incrementally on a word by word basis. This gives rise to many characteristic conversational phenomena including long mid-sentence pauses that are followed by incremental clarification requests (iCRs) intended to recover the rest of the truncated turn (see Fig. 1; (A), (B), (C)). The ability to generate iCRs is important in natural conversational AI systems, and crucial to their accessibility to users with memory impairment. In this paper, we collect, release and analyse SLUICE-CR: a large corpus of 3000 human produced iCRs. We then use this corpus to probe the incremental processing capability of a number of state of the art LLMs by evaluating the quality of the model’s generated iCRs in response to incomplete questions. Our evaluations show that the ability to generate contextually appropriate iCRs only emerges at larger LLM sizes, and only when prompted with example iCRs from our corpus. They also indicate that autoregressive LMs are, in principle, able to both understand and generate language incrementally.
%U https://aclanthology.org/2024.lrec-main.288
%P 3242-3249
Markdown (Informal)
[Clarifying Completions: Evaluating How LLMs Respond to Incomplete Questions](https://aclanthology.org/2024.lrec-main.288) (Addlesee et al., LREC-COLING 2024)
ACL