Recent advances in machine learning have enabled the development of next-generation
predictive models for complex computational biology problems, thereby spurring the use of …

We design probes trained on the internal representations of a transformer language model
to predict its hallucinatory behavior on three grounded generation tasks. To train the probes …

Large language models are known to hallucinate when faced with unfamiliar queries, but
the underlying mechanism that govern how models hallucinate are not yet fully understood …

Machine unlearning can be useful for removing harmful capabilities and memorized text
from large language models (LLMs), but there are not yet standardized methods for …

Accurate uncertainty quantification is crucial for the safe deployment of machine learning
models, and prior research has demonstrated improvements in the calibration of modern …

This paper investigates how generative AI can potentially undermine the integrity of
collective knowledge and the processes we rely on to acquire, assess, and trust information …

How can we train models to perform well on hard test data when hard training data is by
definition difficult to label correctly? This question has been termed the scalable oversight …

While numerous works have assessed the generative performance of language models
(LMs) on tasks requiring Theory of Mind reasoning, research into the models' internal …

The hallucination problem of Large Language Models (LLMs) significantly limits their
reliability and trustworthiness. Humans have a self-awareness process that allows us to …

Abstract Large Language Models (LLMs) exhibit positional bias, struggling to utilize
information from the middle or end of long contexts. Our study explores LLMs' long-context …