5 papers
Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training
Yixin Liu, Yue Yu, DiJia Su +7
Reasoning LLMs-as-Judges, which can benefit from inference-time scaling, provide a promising path for extending the success of reasoning models to non-verifiable domains where the…
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…
AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs
Anselm Paulus, Arman Zharmagambetov, Chuan Guo +2
Large Language Models (LLMs) are vulnerable to jailbreaking attacks that lead to generation of inappropriate or harmful content. Manual red-teaming requires a time-consuming search…
To the Globe (TTG): Towards Language-Driven Guaranteed Travel Planning
Da JU, Song Jiang, Andrew Cohen +8
Travel planning is a challenging and time-consuming task that aims to find an itinerary which satisfies multiple, interdependent constraints regarding flights, accommodations, attr…
GenCO: Generating Diverse Designs with Combinatorial Constraints
Aaron Ferber, Arman Zharmagambetov, Taoan Huang +2
Deep generative models like GAN and VAE have shown impressive results in generating unconstrained objects like images. However, many design settings arising in industrial design, m…