@inproceedings{yang-2024-innovative,
title = "Innovative Approaches to Enhancing Safety and Ethical {AI} Interactions in Digital Environments",
author = "Yang, Zachary",
editor = "Inoue, Koji and
Fu, Yahui and
Axelsson, Agnes and
Ohashi, Atsumoto and
Madureira, Brielen and
Zenimoto, Yuki and
Mohapatra, Biswesh and
Stricker, Armand and
Khosla, Sopan",
booktitle = "Proceedings of the 20th Workshop of Young Researchers' Roundtable on Spoken Dialogue Systems",
month = sep,
year = "2024",
address = "Kyoto, Japan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.yrrsds-1.24",
pages = "64--67",
abstract = "Ensuring safe online environments is a formidable challenge, but nonetheless an important one as people are now chronically online. The increasing online presence of people paired with the prevalence of harmful content such as toxicity, hate speech, misinformation and disinformation across various social media platforms and within different video calls for stronger detection and prevention methods. My research interests primarily lie in applied natural language processing for social good. Previously, I focused on measuring partisan polarization on social media during the COVID-19 pandemic and its societal impacts. Currently, at Ubisoft La Forge, I am dedicated to enhancing player safety within in-game chat systems by developing methods to detect toxicity, evaluating the biases in these detection systems, and assessing the current ecological state of online interactions. Additionally, I am engaged in simulating social media environments using LLMs to ethically test detection methods, evaluate the effectiveness of current mitigation strategies, and potentially introduce new, successful strategies. My suggested topics for discussion: 1. Understanding and mitigating social harms through high fidelity simulated social media environments 2. Enhancing safety in online environments such as within in-game chats (text and speech) 3. Personification of LLM agents 4. Ethically simulating social media sandbox environments at scale with LLM agents 5. Re-balancing the playing field between good and bad actors: Strategies for countering societal-scale manipulation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-2024-innovative">
<titleInfo>
<title>Innovative Approaches to Enhancing Safety and Ethical AI Interactions in Digital Environments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zachary</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th Workshop of Young Researchers’ Roundtable on Spoken Dialogue Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Koji</namePart>
<namePart type="family">Inoue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yahui</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agnes</namePart>
<namePart type="family">Axelsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atsumoto</namePart>
<namePart type="family">Ohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brielen</namePart>
<namePart type="family">Madureira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuki</namePart>
<namePart type="family">Zenimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biswesh</namePart>
<namePart type="family">Mohapatra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Armand</namePart>
<namePart type="family">Stricker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sopan</namePart>
<namePart type="family">Khosla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kyoto, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Ensuring safe online environments is a formidable challenge, but nonetheless an important one as people are now chronically online. The increasing online presence of people paired with the prevalence of harmful content such as toxicity, hate speech, misinformation and disinformation across various social media platforms and within different video calls for stronger detection and prevention methods. My research interests primarily lie in applied natural language processing for social good. Previously, I focused on measuring partisan polarization on social media during the COVID-19 pandemic and its societal impacts. Currently, at Ubisoft La Forge, I am dedicated to enhancing player safety within in-game chat systems by developing methods to detect toxicity, evaluating the biases in these detection systems, and assessing the current ecological state of online interactions. Additionally, I am engaged in simulating social media environments using LLMs to ethically test detection methods, evaluate the effectiveness of current mitigation strategies, and potentially introduce new, successful strategies. My suggested topics for discussion: 1. Understanding and mitigating social harms through high fidelity simulated social media environments 2. Enhancing safety in online environments such as within in-game chats (text and speech) 3. Personification of LLM agents 4. Ethically simulating social media sandbox environments at scale with LLM agents 5. Re-balancing the playing field between good and bad actors: Strategies for countering societal-scale manipulation.</abstract>
<identifier type="citekey">yang-2024-innovative</identifier>
<location>
<url>https://aclanthology.org/2024.yrrsds-1.24</url>
</location>
<part>
<date>2024-09</date>
<extent unit="page">
<start>64</start>
<end>67</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Innovative Approaches to Enhancing Safety and Ethical AI Interactions in Digital Environments
%A Yang, Zachary
%Y Inoue, Koji
%Y Fu, Yahui
%Y Axelsson, Agnes
%Y Ohashi, Atsumoto
%Y Madureira, Brielen
%Y Zenimoto, Yuki
%Y Mohapatra, Biswesh
%Y Stricker, Armand
%Y Khosla, Sopan
%S Proceedings of the 20th Workshop of Young Researchers’ Roundtable on Spoken Dialogue Systems
%D 2024
%8 September
%I Association for Computational Linguistics
%C Kyoto, Japan
%F yang-2024-innovative
%X Ensuring safe online environments is a formidable challenge, but nonetheless an important one as people are now chronically online. The increasing online presence of people paired with the prevalence of harmful content such as toxicity, hate speech, misinformation and disinformation across various social media platforms and within different video calls for stronger detection and prevention methods. My research interests primarily lie in applied natural language processing for social good. Previously, I focused on measuring partisan polarization on social media during the COVID-19 pandemic and its societal impacts. Currently, at Ubisoft La Forge, I am dedicated to enhancing player safety within in-game chat systems by developing methods to detect toxicity, evaluating the biases in these detection systems, and assessing the current ecological state of online interactions. Additionally, I am engaged in simulating social media environments using LLMs to ethically test detection methods, evaluate the effectiveness of current mitigation strategies, and potentially introduce new, successful strategies. My suggested topics for discussion: 1. Understanding and mitigating social harms through high fidelity simulated social media environments 2. Enhancing safety in online environments such as within in-game chats (text and speech) 3. Personification of LLM agents 4. Ethically simulating social media sandbox environments at scale with LLM agents 5. Re-balancing the playing field between good and bad actors: Strategies for countering societal-scale manipulation.
%U https://aclanthology.org/2024.yrrsds-1.24
%P 64-67
Markdown (Informal)
[Innovative Approaches to Enhancing Safety and Ethical AI Interactions in Digital Environments](https://aclanthology.org/2024.yrrsds-1.24) (Yang, YRRSDS-WS 2024)
ACL