@inproceedings{yang-etal-2022-gpt,
title = "What {GPT} Knows About Who is Who",
author = "Yang, Xiaohan and
Peynetti, Eduardo and
Meerman, Vasco and
Tanner, Chris",
editor = "Tafreshi, Shabnam and
Sedoc, Jo{\~a}o and
Rogers, Anna and
Drozd, Aleksandr and
Rumshisky, Anna and
Akula, Arjun",
booktitle = "Proceedings of the Third Workshop on Insights from Negative Results in NLP",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.insights-1.10",
doi = "10.18653/v1/2022.insights-1.10",
pages = "75--81",
abstract = "Coreference resolution {--} which is a crucial task for understanding discourse and language at large {--} has yet to witness widespread benefits from large language models (LLMs). Moreover, coreference resolution systems largely rely on supervised labels, which are highly expensive and difficult to annotate, thus making it ripe for prompt engineering. In this paper, we introduce a QA-based prompt-engineering method and discern \textit{generative}, pre-trained LLMs{'} abilities and limitations toward the task of coreference resolution. Our experiments show that GPT-2 and GPT-Neo can return valid answers, but that their capabilities to identify coreferent mentions are limited and prompt-sensitive, leading to inconsistent results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2022-gpt">
<titleInfo>
<title>What GPT Knows About Who is Who</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaohan</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eduardo</namePart>
<namePart type="family">Peynetti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vasco</namePart>
<namePart type="family">Meerman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Tanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Insights from Negative Results in NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shabnam</namePart>
<namePart type="family">Tafreshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleksandr</namePart>
<namePart type="family">Drozd</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arjun</namePart>
<namePart type="family">Akula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Coreference resolution – which is a crucial task for understanding discourse and language at large – has yet to witness widespread benefits from large language models (LLMs). Moreover, coreference resolution systems largely rely on supervised labels, which are highly expensive and difficult to annotate, thus making it ripe for prompt engineering. In this paper, we introduce a QA-based prompt-engineering method and discern generative, pre-trained LLMs’ abilities and limitations toward the task of coreference resolution. Our experiments show that GPT-2 and GPT-Neo can return valid answers, but that their capabilities to identify coreferent mentions are limited and prompt-sensitive, leading to inconsistent results.</abstract>
<identifier type="citekey">yang-etal-2022-gpt</identifier>
<identifier type="doi">10.18653/v1/2022.insights-1.10</identifier>
<location>
<url>https://aclanthology.org/2022.insights-1.10</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>75</start>
<end>81</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T What GPT Knows About Who is Who
%A Yang, Xiaohan
%A Peynetti, Eduardo
%A Meerman, Vasco
%A Tanner, Chris
%Y Tafreshi, Shabnam
%Y Sedoc, João
%Y Rogers, Anna
%Y Drozd, Aleksandr
%Y Rumshisky, Anna
%Y Akula, Arjun
%S Proceedings of the Third Workshop on Insights from Negative Results in NLP
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F yang-etal-2022-gpt
%X Coreference resolution – which is a crucial task for understanding discourse and language at large – has yet to witness widespread benefits from large language models (LLMs). Moreover, coreference resolution systems largely rely on supervised labels, which are highly expensive and difficult to annotate, thus making it ripe for prompt engineering. In this paper, we introduce a QA-based prompt-engineering method and discern generative, pre-trained LLMs’ abilities and limitations toward the task of coreference resolution. Our experiments show that GPT-2 and GPT-Neo can return valid answers, but that their capabilities to identify coreferent mentions are limited and prompt-sensitive, leading to inconsistent results.
%R 10.18653/v1/2022.insights-1.10
%U https://aclanthology.org/2022.insights-1.10
%U https://doi.org/10.18653/v1/2022.insights-1.10
%P 75-81
Markdown (Informal)
[What GPT Knows About Who is Who](https://aclanthology.org/2022.insights-1.10) (Yang et al., insights 2022)
ACL
- Xiaohan Yang, Eduardo Peynetti, Vasco Meerman, and Chris Tanner. 2022. What GPT Knows About Who is Who. In Proceedings of the Third Workshop on Insights from Negative Results in NLP, pages 75–81, Dublin, Ireland. Association for Computational Linguistics.