Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations

16 April 2024

Papers citing "Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations"

6 / 6 papers shown

Title
Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations Ziwei Ji L. Yu Yeskendir Koishekenov Yejin Bang Anthony Hartshorn Alan Schelten Cheng Zhang Pascale Fung Nicola Cancedda 49 1 0 18 Mar 2025
R2-KG: General-Purpose Dual-Agent Framework for Reliable Reasoning on Knowledge Graphs Sumin Jo Junseong Choi Jiho Kim E. Choi 41 0 0 18 Feb 2025
Cognitively Inspired Energy-Based World Models Alexi Gladstone Ganesh Nanduru Md. Mofijul Islam Aman Chadha Jundong Li Tariq Iqbal 31 0 0 13 Jun 2024
Investigating Uncertainty Calibration of Aligned Language Models under the Multiple-Choice Setting Guande He Peng Cui Jianfei Chen Wenbo Hu Jun Zhu 47 11 0 18 Oct 2023
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned Deep Ganguli Liane Lovitt John Kernion Amanda Askell Yuntao Bai ... Nicholas Joseph Sam McCandlish C. Olah Jared Kaplan Jack Clark 225 443 0 23 Aug 2022
Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies Mor Geva Daniel Khashabi Elad Segal Tushar Khot Dan Roth Jonathan Berant RALM 250 672 0 06 Jan 2021