9 citations · 25 across the 22 of their papers we have counts for
8 papers · 1 filter
Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for Interpretability
Usha Bhalla, Alex Oesterling, Claudio Mayrink Verdun +2
Translating the internal representations and computations of models into concepts that humans can understand is a key goal of interpretability. While recent dictionary learning met…
ProofCompass: Enhancing Specialized Provers with LLM Guidance
Nicolas Wischermann, Claudio Mayrink Verdun, Gabriel Poesia +1
Language models have become increasingly powerful tools for formal mathematical reasoning. However, most existing approaches rely exclusively on either large general-purpose models…
Inference-Time Reward Hacking in Large Language Models
Hadi Khalaf, Claudio Mayrink Verdun, Alex Oesterling +2
A common paradigm to improve the performance of large language models is optimizing for a reward model. Reward models assign a numerical score to an LLM's output that indicates, fo…
HeavyWater and SimplexWater: Distortion-Free LLM Watermarks for Low-Entropy Next-Token Predictions
Dor Tsur, Carol Xuan Long, Claudio Mayrink Verdun +5
Large language model (LLM) watermarks enable authentication of text provenance, curb misuse of machine-generated text, and promote trust in AI systems. Current watermarks operate b…
Multi-Group Proportional Representation for Text-to-Image Models
Sangwon Jung, Alex Oesterling, Claudio Mayrink Verdun +3
Text-to-image (T2I) generative models can create vivid, realistic images from textual descriptions. As these models proliferate, they expose new concerns about their ability to rep…
Optimized Couplings for Watermarking Large Language Models
Dor Tsur, Carol Xuan Long, Claudio Mayrink Verdun +3
Large-language models (LLMs) are now able to produce text that is, in many cases, seemingly indistinguishable from human-generated content. This has fueled the development of water…
Soft Best-of-n Sampling for Model Alignment
Claudio Mayrink Verdun, Alex Oesterling, Himabindu Lakkaraju +1
Best-of- (BoN) sampling is a practical approach for aligning language model outputs with human preferences without expensive fine-tuning. BoN sampling is performed by generating…
GradPCA: Leveraging NTK Alignment for Reliable Out-of-Distribution Detection
Mariia Seleznova, Hung-Hsu Chou, Claudio Mayrink Verdun +1
We introduce GradPCA, an Out-of-Distribution (OOD) detection method that exploits the low-rank structure of neural network gradients induced by Neural Tangent Kernel (NTK) alignmen…