10 papers
GPT-Red: Automated Red Teaming via Self-Play at Scale
Eric Wallace, Christopher A. Choquette-Choo, Nikhil Kandpal +15
The paper presents GPT-Red, an automated red‑teaming system that uses self‑play to generate novel prompt‑injection attacks against large language models and improve their robustnes…
Why Does Feedback-Augmented Self-Distillation Fail to Improve Retrieval-Interleaved Search Agents?
Fan Yang, Rui Meng, Yuxin Wen
On-policy self-distillation (OPSD) offers a promising approach for training large language models without relying on a separate teacher model. However, its effectiveness on complex…
Flash-BoN: Instant Drafts for Inference-Time Scaling in Diffusion Models
Ruchit Rawal, Reza Shirkavand, Sayak Paul +5
Inference-time scaling for text-to-image generation has progressed from simple Best-of- (BoN) sampling to guided search methods that verify and steer candidate trajectories at i…
KEPO: Knowledge-Enhanced Preference Optimization for Multimodal Reasoning with Applications to Medical VQA
Fan Yang, Rui Meng, Trudi Di Qi +2
Reinforcement learning (RL) has emerged as a promising paradigm for inducing explicit reasoning behaviors in large language and vision-language models. However, reasoning-oriented…
FictionalQA: A Dataset for Studying Memorization and Knowledge Acquisition
John Kirchenbauer, Janny Mongkolsupawan, Yuxin Wen +2
When language models are trained on textual data, they acquire both knowledge about the structure of language as well as knowledge of facts about the world. At inference time, thei…
RL Is a Hammer and LLMs Are Nails: A Simple Reinforcement Learning Recipe for Strong Prompt Injection
Yuxin Wen, Arman Zharmagambetov, Ivan Evtimov +4
Prompt injection poses a serious threat to the reliability and safety of LLM agents. Recent defenses against prompt injection, such as Instruction Hierarchy and SecAlign, have show…