On Uncertainty In Natural Language Processing

D Ulmer - arxiv preprint arxiv:2410.03446, 2024 - arxiv.org
The last decade in deep learning has brought on increasingly capable systems that are
deployed on a wide variety of applications. In natural language processing, the field has …

Confidence estimation for llm-based dialogue state tracking

YJ Sun, S Dey, D Hakkani-Tür… - 2024 IEEE Spoken …, 2024 - ieeexplore.ieee.org
Estimation of a model's confidence on its outputs is critical for Conversational AI systems
based on large language models (LLMs), especially for reducing hallucination and …

Accounting for Sycophancy in Language Model Uncertainty Estimation

A Sicilia, M Inan, M Alikhani - arxiv preprint arxiv:2410.14746, 2024 - arxiv.org
Effective human-machine collaboration requires machine learning models to externalize
uncertainty, so users can reflect and intervene when necessary. For language models, these …

Eliciting Uncertainty in Chain-of-Thought to Mitigate Bias against Forecasting Harmful User Behaviors

A Sicilia, M Alikhani - arxiv preprint arxiv:2410.14744, 2024 - arxiv.org
Conversation forecasting tasks a model with predicting the outcome of an unfolding
conversation. For instance, it can be applied in social media moderation to predict harmful …

[BOK][B] Towards Computational Methods for Proactively Supporting Healthier Online Discussions

JPW Chang - 2024 - search.proquest.com
One of the biggest problems facing online platforms today is the prevalence of so-called
“toxic” behavior, such as personal attacks, harassment, and general incivility. While a …