Exploring Memorization and Copyright Violation in Frontier LLMs: A Study of the New York Times…
BatchTopK Sparse Autoencodersby Bart Bussmann, Patrick Leask, Neel NandaFirst submitted to arxiv on: 9 Dec…
Optimizing Multi-Task Learning for Enhanced Performance in Large Language Modelsby Zhen Qi, Jiajing Chen, Shuo…
Towards Learning to Reason: Comparing LLMs with Neuro-Symbolic on Arithmetic Relations in Abstract Reasoningby Michael…
Nearly Solved? Robust Deepfake Detection Requires More than Visual Forensicsby Guy Levy, Nathan LiebmannFirst submitted…
The BrowserGym Ecosystem for Web Agent Researchby Thibault Le Sellier De Chezelles, Maxime Gasse, Alexandre…
BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasksby Juan Rodriguez,…
A Water Efficiency Dataset for African Data Centersby Noah Shumba, Opelo Tshekiso, Pengfei Li, Giulia…
FANAL – Financial Activity News Alerting Language Modeling Frameworkby Urjitkumar Patel, Fang-Chun Yeh, Chinmay Gondhalekar,…
Best-of-N Jailbreakingby John Hughes, Sara Price, Aengus Lynch, Rylan Schaeffer, Fazl Barez, Sanmi Koyejo, Henry…