The Curious Case of Hallucinatory (Un)answerability: Finding Truths in
the Hidden States of Over-Confident Large Language Models

The Curious Case of Hallucinatory (Un)answerability: Finding Truths in the Hidden States of Over-Confident Large Language Models

18 October 2023

Omer Goldman

Shauli Ravfogel

Papers citing "The Curious Case of Hallucinatory (Un)answerability: Finding Truths in the Hidden States of Over-Confident Large Language Models"

8 / 8 papers shown

Title
MAQA: Evaluating Uncertainty Quantification in LLMs Regarding Data Uncertainty Yongjin Yang Haneul Yoo Hwaran Lee 53 1 0 13 Aug 2024
"According to ...": Prompting Language Models Improves Quoting from Pre-Training Data Orion Weller Marc Marone Nathaniel Weir Dawn J Lawrie Daniel Khashabi Benjamin Van Durme HILM 58 44 0 22 May 2023
Poisoning Language Models During Instruction Tuning Alexander Wan Eric Wallace Sheng Shen Dan Klein SILM 90 124 0 01 May 2023
Dissecting Recall of Factual Associations in Auto-Regressive Language Models Mor Geva Jasmijn Bastings Katja Filippova Amir Globerson KELM 183 152 0 28 Apr 2023
Faithfulness-Aware Decoding Strategies for Abstractive Summarization David Wan Mengwen Liu Kathleen McKeown Markus Dreyer Mohit Bansal HILM 111 20 0 06 Mar 2023
Calibration of Pre-trained Transformers Shrey Desai Greg Durrett UQLM 229 288 0 17 Mar 2020
The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectives Elena Voita Rico Sennrich Ivan Titov 179 181 0 03 Sep 2019
What you can cram into a single vector: Probing sentence embeddings for linguistic properties Alexis Conneau Germán Kruszewski Guillaume Lample Loïc Barrault Marco Baroni 196 876 0 03 May 2018