@inproceedings{lin-etal-2024-towards,
title = "Towards Healthy {AI}: Large Language Models Need Therapists Too",
author = "Lin, Baihan and
Bouneffouf, Djallel and
Cecchi, Guillermo and
Varshney, Kush",
editor = "Ovalle, Anaelia and
Chang, Kai-Wei and
Cao, Yang Trista and
Mehrabi, Ninareh and
Zhao, Jieyu and
Galstyan, Aram and
Dhamala, Jwala and
Kumar, Anoop and
Gupta, Rahul",
booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.trustnlp-1.6",
doi = "10.18653/v1/2024.trustnlp-1.6",
pages = "61--70",
abstract = "Recent advances in large language models (LLMs) have led to the development of powerful chatbots capable of engaging in fluent human-like conversations. However, these chatbots may be harmful, exhibiting manipulation, gaslighting, narcissism, and other toxicity. To work toward safer and more well-adjusted models, we propose a framework that uses psychotherapy to identify and mitigate harmful chatbot behaviors. The framework involves four different artificial intelligence (AI) agents: the Chatbot whose behavior is to be adjusted, a User, a Therapist, and a Critic that can be paired with reinforcement learning-based LLM tuning. We illustrate the framework with a working example of a social conversation involving four instances of ChatGPT, showing that the framework may mitigate the toxicity in conversations between LLM-driven chatbots and people. Although there are still several challenges and directions to be addressed in the future, the proposed framework is a promising approach to improving the alignment between LLMs and human values.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-etal-2024-towards">
<titleInfo>
<title>Towards Healthy AI: Large Language Models Need Therapists Too</title>
</titleInfo>
<name type="personal">
<namePart type="given">Baihan</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Djallel</namePart>
<namePart type="family">Bouneffouf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guillermo</namePart>
<namePart type="family">Cecchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kush</namePart>
<namePart type="family">Varshney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anaelia</namePart>
<namePart type="family">Ovalle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai-Wei</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="given">Trista</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ninareh</namePart>
<namePart type="family">Mehrabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jieyu</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aram</namePart>
<namePart type="family">Galstyan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jwala</namePart>
<namePart type="family">Dhamala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advances in large language models (LLMs) have led to the development of powerful chatbots capable of engaging in fluent human-like conversations. However, these chatbots may be harmful, exhibiting manipulation, gaslighting, narcissism, and other toxicity. To work toward safer and more well-adjusted models, we propose a framework that uses psychotherapy to identify and mitigate harmful chatbot behaviors. The framework involves four different artificial intelligence (AI) agents: the Chatbot whose behavior is to be adjusted, a User, a Therapist, and a Critic that can be paired with reinforcement learning-based LLM tuning. We illustrate the framework with a working example of a social conversation involving four instances of ChatGPT, showing that the framework may mitigate the toxicity in conversations between LLM-driven chatbots and people. Although there are still several challenges and directions to be addressed in the future, the proposed framework is a promising approach to improving the alignment between LLMs and human values.</abstract>
<identifier type="citekey">lin-etal-2024-towards</identifier>
<identifier type="doi">10.18653/v1/2024.trustnlp-1.6</identifier>
<location>
<url>https://aclanthology.org/2024.trustnlp-1.6</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>61</start>
<end>70</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Healthy AI: Large Language Models Need Therapists Too
%A Lin, Baihan
%A Bouneffouf, Djallel
%A Cecchi, Guillermo
%A Varshney, Kush
%Y Ovalle, Anaelia
%Y Chang, Kai-Wei
%Y Cao, Yang Trista
%Y Mehrabi, Ninareh
%Y Zhao, Jieyu
%Y Galstyan, Aram
%Y Dhamala, Jwala
%Y Kumar, Anoop
%Y Gupta, Rahul
%S Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F lin-etal-2024-towards
%X Recent advances in large language models (LLMs) have led to the development of powerful chatbots capable of engaging in fluent human-like conversations. However, these chatbots may be harmful, exhibiting manipulation, gaslighting, narcissism, and other toxicity. To work toward safer and more well-adjusted models, we propose a framework that uses psychotherapy to identify and mitigate harmful chatbot behaviors. The framework involves four different artificial intelligence (AI) agents: the Chatbot whose behavior is to be adjusted, a User, a Therapist, and a Critic that can be paired with reinforcement learning-based LLM tuning. We illustrate the framework with a working example of a social conversation involving four instances of ChatGPT, showing that the framework may mitigate the toxicity in conversations between LLM-driven chatbots and people. Although there are still several challenges and directions to be addressed in the future, the proposed framework is a promising approach to improving the alignment between LLMs and human values.
%R 10.18653/v1/2024.trustnlp-1.6
%U https://aclanthology.org/2024.trustnlp-1.6
%U https://doi.org/10.18653/v1/2024.trustnlp-1.6
%P 61-70
Markdown (Informal)
[Towards Healthy AI: Large Language Models Need Therapists Too](https://aclanthology.org/2024.trustnlp-1.6) (Lin et al., TrustNLP-WS 2024)
ACL
- Baihan Lin, Djallel Bouneffouf, Guillermo Cecchi, and Kush Varshney. 2024. Towards Healthy AI: Large Language Models Need Therapists Too. In Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024), pages 61–70, Mexico City, Mexico. Association for Computational Linguistics.