@inproceedings{sadlier-brown-etal-2024-useful,
title = "How Useful is Context, Actually? Comparing {LLM}s and Humans on Discourse Marker Prediction",
author = "Sadlier-Brown, Emily and
Lou, Millie and
Silfverberg, Miikka and
Kam, Carla",
editor = "Kuribayashi, Tatsuki and
Rambelli, Giulia and
Takmaz, Ece and
Wicke, Philipp and
Oseki, Yohei",
booktitle = "Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.cmcl-1.20/",
doi = "10.18653/v1/2024.cmcl-1.20",
pages = "231--241",
abstract = "This paper investigates the adverbial discourse particle actually. We compare LLM and human performance on cloze tests involving actually on examples sourced from the Providence Corpus of speech around children. We explore the impact of utterance context on cloze test performance. We find that context is always helpful, though the extent to which additional context is helpful, and what relative placement of context (i.e. before or after the masked word) is most helpful differs for individual models and humans. The best-performing LLM, GPT-4, narrowly outperforms humans. In an additional experiment, we explore cloze performance on synthetic LLM-generated examples, and find that several models vastly outperform humans."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sadlier-brown-etal-2024-useful">
<titleInfo>
<title>How Useful is Context, Actually? Comparing LLMs and Humans on Discourse Marker Prediction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Sadlier-Brown</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Millie</namePart>
<namePart type="family">Lou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miikka</namePart>
<namePart type="family">Silfverberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carla</namePart>
<namePart type="family">Kam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tatsuki</namePart>
<namePart type="family">Kuribayashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giulia</namePart>
<namePart type="family">Rambelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ece</namePart>
<namePart type="family">Takmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Wicke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yohei</namePart>
<namePart type="family">Oseki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper investigates the adverbial discourse particle actually. We compare LLM and human performance on cloze tests involving actually on examples sourced from the Providence Corpus of speech around children. We explore the impact of utterance context on cloze test performance. We find that context is always helpful, though the extent to which additional context is helpful, and what relative placement of context (i.e. before or after the masked word) is most helpful differs for individual models and humans. The best-performing LLM, GPT-4, narrowly outperforms humans. In an additional experiment, we explore cloze performance on synthetic LLM-generated examples, and find that several models vastly outperform humans.</abstract>
<identifier type="citekey">sadlier-brown-etal-2024-useful</identifier>
<identifier type="doi">10.18653/v1/2024.cmcl-1.20</identifier>
<location>
<url>https://aclanthology.org/2024.cmcl-1.20/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>231</start>
<end>241</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How Useful is Context, Actually? Comparing LLMs and Humans on Discourse Marker Prediction
%A Sadlier-Brown, Emily
%A Lou, Millie
%A Silfverberg, Miikka
%A Kam, Carla
%Y Kuribayashi, Tatsuki
%Y Rambelli, Giulia
%Y Takmaz, Ece
%Y Wicke, Philipp
%Y Oseki, Yohei
%S Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F sadlier-brown-etal-2024-useful
%X This paper investigates the adverbial discourse particle actually. We compare LLM and human performance on cloze tests involving actually on examples sourced from the Providence Corpus of speech around children. We explore the impact of utterance context on cloze test performance. We find that context is always helpful, though the extent to which additional context is helpful, and what relative placement of context (i.e. before or after the masked word) is most helpful differs for individual models and humans. The best-performing LLM, GPT-4, narrowly outperforms humans. In an additional experiment, we explore cloze performance on synthetic LLM-generated examples, and find that several models vastly outperform humans.
%R 10.18653/v1/2024.cmcl-1.20
%U https://aclanthology.org/2024.cmcl-1.20/
%U https://doi.org/10.18653/v1/2024.cmcl-1.20
%P 231-241
Markdown (Informal)
[How Useful is Context, Actually? Comparing LLMs and Humans on Discourse Marker Prediction](https://aclanthology.org/2024.cmcl-1.20/) (Sadlier-Brown et al., CMCL 2024)
ACL