Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models
Open Access
- 1 January 2024
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 4864-4888
Abstract
Chen Qian, Jie Zhang, Wei Yao, Dongrui Liu, Zhenfei Yin, Yu Qiao, Yong Liu, Jing Shao. Findings of the Association for Computational Linguistics ACL 2024. 2024.Keywords
All Related Versions
This publication has 23 references indexed in Scilit:
- Understanding Probe Behaviors Through Variational Bounds of Mutual Information2024
- Explainability for Large Language Models: A SurveyACM Transactions on Intelligent Systems and Technology, 2024
- PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts2023
- Trustworthy AI: A Computational PerspectiveACM Transactions on Intelligent Systems and Technology, 2022
- Probing Classifiers: Promises, Shortcomings, and AdvancesComputational Linguistics, 2022
- TruthfulQA: Measuring How Models Mimic Human Falsehoods2022
- Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance?2021
- Implicit Representations of Meaning in Neural Language Models2021
- The Information Bottleneck Problem and its Applications in Machine LearningIEEE Journal on Selected Areas in Information Theory, 2020
- Information-Theoretic Probing for Linguistic Structure2020