22 papers
Safety Alignment of LMs via Non-cooperative Games
Anselm Paulus, Ilia Kulikov, Brandon Amos +4
Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment. Current approaches rely on sequential adversarial trai…
Muse Spark Safety & Preparedness Report
Cristina Menghini, Peter Ney, Hamza Kwisaba +117
Muse Spark is the latest large language model developed by Meta. In this report, we first present evaluations for catastrophic risk domains under Meta's Advanced AI Scaling Framewo…
Large Reasoning Models Learn Better Alignment from Flawed Thinking
ShengYun Peng, Eric Smith, Ivan Evtimov +7
Large reasoning models (LRMs) "think" by generating structured chain-of-thought (CoT) before producing a final answer, yet they still lack the ability to reason critically about sa…
Gender Bias in MT for a Genderless Language: New Benchmarks for Basque
Amaia Murillo, Olatz-Perez-de-Viñaspre, Naiara Perez
Large language models (LLMs) and machine translation (MT) systems are increasingly used in our daily lives, but their outputs can reproduce gender bias present in the training data…
The Llama 4 Herd: Architecture, Training, Evaluation, and Deployment Notes
Redacted by arXiv
This document consolidates publicly reported technical details about Metas Llama 4 model family. It summarizes (i) released variants (Scout and Maverick) and the broader herd conte…
AdvPrefix: An Objective for Nuanced LLM Jailbreaks
Sicheng Zhu, Brandon Amos, Yuandong Tian +2
Many jailbreak attacks on large language models (LLMs) rely on a common objective: making the model respond with the prefix ``Sure, here is (harmful request)''. While straightforwa…