8 papers
Flipping Against All Odds: Reducing LLM Coin Flip Bias via Verbalized Rejection Sampling
Tim Z. Xiao, Johannes Zenn, Zhen Liu +3
Large language models (LLMs) can often accurately describe probability distributions using natural language, yet they still struggle to generate faithful samples from them. This mi…
On the Challenges and Opportunities in Generative AI
Laura Manduchi, Clara Meister, Kushagra Pandey +23
The field of deep generative modeling has grown rapidly in the last few years. With the availability of massive amounts of training data coupled with advances in scalable unsupervi…
Regularized KL-Divergence for Well-Defined Function-Space Variational Inference in Bayesian neural networks
Tristan Cinquin, Robert Bamler
Bayesian neural networks (BNN) promise to combine the predictive performance of neural networks with principled uncertainty modeling important for safety-critical systems and decis…
Reducing Storage of Pretrained Neural Networks by Rate-Constrained Quantization and Entropy Coding
Alexander Conzelmann, Robert Bamler
The ever-growing size of neural networks poses serious challenges on resource-constrained devices, such as embedded sensors. Compression algorithms that reduce their size can mitig…
Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detector
Andi Zhang, Tim Z. Xiao, Weiyang Liu +2
We revisit the likelihood ratio between a pretrained large language model (LLM) and its finetuned variant as a criterion for out-of-distribution (OOD) detection. The intuition behi…
Verbalized Machine Learning: Revisiting Machine Learning with Language Models
Tim Z. Xiao, Robert Bamler, Bernhard Schölkopf +1
Motivated by the progress made by large language models (LLMs), we introduce the framework of verbalized machine learning (VML). In contrast to conventional machine learning (ML) m…