Katalog Plus
Bibliothek der Frankfurt UAS
Bald neuer Katalog: sichern Sie sich schon vorab Ihre persönlichen Merklisten im Nutzerkonto: Anleitung.
Dieses Ergebnis aus BASE kann Gästen nicht angezeigt werden.  Login für vollen Zugriff.

Evaluating the Efficacy of Prompting Techniques for Debiasing Language Model Outputs (Student Abstract)

Title: Evaluating the Efficacy of Prompting Techniques for Debiasing Language Model Outputs (Student Abstract)
Authors: Furniturewala, Shaz; Jandial, Surgan; Java, Abhinav; Shahid, Simra; Banerjee, Pragyan; Krishnamurthy, Balaji; Bhatia, Sumit; Jaidka, Kokil
Source: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 38 No. 21: IAAI-24, EAAI-24, AAAI-24 Student Abstracts, Undergraduate Consortium and Demonstrations; 23492-23493 ; 2374-3468 ; 2159-5399
Publisher Information: Association for the Advancement of Artificial Intelligence
Publication Year: 2024
Collection: Association for the Advancement of Artificial Intelligence: AAAI Publications
Subject Terms: LLM; Debiasing; Fairness; Zeroshot; Text Generation
Description: Achieving fairness in Large Language Models (LLMs) continues to pose a persistent challenge, as these models are prone to inheriting biases from their training data, which can subsequently impact their performance in various applications. There is a need to systematically explore whether structured prompting techniques can offer opportunities for debiased text generation by LLMs. In this work, we designed an evaluative framework to test the efficacy of different prompting techniques for debiasing text along different dimensions. We aim to devise a general structured prompting approach to achieve fairness that generalizes well to different texts and LLMs.
Document Type: article in journal/newspaper
File Description: application/pdf
Language: English
ISBN: 978-2-349-22349-4; 2-349-22349-3
Relation: https://ojs.aaai.org/index.php/AAAI/article/view/30443/32533; https://ojs.aaai.org/index.php/AAAI/article/view/30443/32534; https://ojs.aaai.org/index.php/AAAI/article/view/30443
DOI: 10.1609/aaai.v38i21.30443
Availability: https://ojs.aaai.org/index.php/AAAI/article/view/30443; https://doi.org/10.1609/aaai.v38i21.30443
Rights: Copyright (c) 2024 Association for the Advancement of Artificial Intelligence
Accession Number: edsbas.83351977
Database: BASE