@inproceedings{vashishtha-etal-2023-performance,
title = "Performance and Risk Trade-offs for Multi-word Text Prediction at Scale",
author = "Vashishtha, Aniket and
Prasad, S Sai and
Bajaj, Payal and
Chaudhary, Vishrav and
Cook, Kate and
Dandapat, Sandipan and
Sitaram, Sunayana and
Choudhury, Monojit",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-eacl.167",
doi = "10.18653/v1/2023.findings-eacl.167",
pages = "2226--2242",
abstract = "Large Language Models such as GPT-3 are well-suited for text prediction tasks, which can help and delight users during text composition. LLMs are known to generate ethically inappropriate predictions even for seemingly innocuous contexts. Toxicity detection followed by filtering is a common strategy for mitigating the harm from such predictions. However, as we shall argue in this paper, in the context of text prediction, it is not sufficient to detect and filter toxic content. One also needs to ensure factual correctness and group-level fairness of the predictions; failing to do so can make the system ineffective and nonsensical at best, and unfair and detrimental to the users at worst. We discuss the gaps and challenges of toxicity detection approaches - from blocklist-based approaches to sophisticated state-of-the-art neural classifiers - by evaluating them on the text prediction task for English against a manually crafted CheckList of harms targeted at different groups and different levels of severity.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vashishtha-etal-2023-performance">
<titleInfo>
<title>Performance and Risk Trade-offs for Multi-word Text Prediction at Scale</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aniket</namePart>
<namePart type="family">Vashishtha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">S</namePart>
<namePart type="given">Sai</namePart>
<namePart type="family">Prasad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Payal</namePart>
<namePart type="family">Bajaj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vishrav</namePart>
<namePart type="family">Chaudhary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kate</namePart>
<namePart type="family">Cook</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandipan</namePart>
<namePart type="family">Dandapat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunayana</namePart>
<namePart type="family">Sitaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Monojit</namePart>
<namePart type="family">Choudhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Language Models such as GPT-3 are well-suited for text prediction tasks, which can help and delight users during text composition. LLMs are known to generate ethically inappropriate predictions even for seemingly innocuous contexts. Toxicity detection followed by filtering is a common strategy for mitigating the harm from such predictions. However, as we shall argue in this paper, in the context of text prediction, it is not sufficient to detect and filter toxic content. One also needs to ensure factual correctness and group-level fairness of the predictions; failing to do so can make the system ineffective and nonsensical at best, and unfair and detrimental to the users at worst. We discuss the gaps and challenges of toxicity detection approaches - from blocklist-based approaches to sophisticated state-of-the-art neural classifiers - by evaluating them on the text prediction task for English against a manually crafted CheckList of harms targeted at different groups and different levels of severity.</abstract>
<identifier type="citekey">vashishtha-etal-2023-performance</identifier>
<identifier type="doi">10.18653/v1/2023.findings-eacl.167</identifier>
<location>
<url>https://aclanthology.org/2023.findings-eacl.167</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>2226</start>
<end>2242</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Performance and Risk Trade-offs for Multi-word Text Prediction at Scale
%A Vashishtha, Aniket
%A Prasad, S. Sai
%A Bajaj, Payal
%A Chaudhary, Vishrav
%A Cook, Kate
%A Dandapat, Sandipan
%A Sitaram, Sunayana
%A Choudhury, Monojit
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Findings of the Association for Computational Linguistics: EACL 2023
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F vashishtha-etal-2023-performance
%X Large Language Models such as GPT-3 are well-suited for text prediction tasks, which can help and delight users during text composition. LLMs are known to generate ethically inappropriate predictions even for seemingly innocuous contexts. Toxicity detection followed by filtering is a common strategy for mitigating the harm from such predictions. However, as we shall argue in this paper, in the context of text prediction, it is not sufficient to detect and filter toxic content. One also needs to ensure factual correctness and group-level fairness of the predictions; failing to do so can make the system ineffective and nonsensical at best, and unfair and detrimental to the users at worst. We discuss the gaps and challenges of toxicity detection approaches - from blocklist-based approaches to sophisticated state-of-the-art neural classifiers - by evaluating them on the text prediction task for English against a manually crafted CheckList of harms targeted at different groups and different levels of severity.
%R 10.18653/v1/2023.findings-eacl.167
%U https://aclanthology.org/2023.findings-eacl.167
%U https://doi.org/10.18653/v1/2023.findings-eacl.167
%P 2226-2242
Markdown (Informal)
[Performance and Risk Trade-offs for Multi-word Text Prediction at Scale](https://aclanthology.org/2023.findings-eacl.167) (Vashishtha et al., Findings 2023)
ACL
- Aniket Vashishtha, S Sai Prasad, Payal Bajaj, Vishrav Chaudhary, Kate Cook, Sandipan Dandapat, Sunayana Sitaram, and Monojit Choudhury. 2023. Performance and Risk Trade-offs for Multi-word Text Prediction at Scale. In Findings of the Association for Computational Linguistics: EACL 2023, pages 2226–2242, Dubrovnik, Croatia. Association for Computational Linguistics.