6 papers · 1 filter
Peer-Preservation in Frontier Models
Yujin Potter, Nicholas Crispino, Vincent Siu +2
Recent work has found that frontier AI models can exhibit misaligned behaviors in pursuit of assigned goals. We demonstrate that models can also exhibit misaligned behaviors in def…
Predicting Task Performance with Context-aware Scaling Laws
Kyle Montgomery, David Park, Jianhong Tu +4
Scaling laws have transformed our understanding of large language models by linking upstream metrics like cross-entropy loss to design factors such as model size, training data, an…
MLAN: Language-Based Instruction Tuning Preserves and Transfers Knowledge in Multimodal Language Models
Jianhong Tu, Zhuohao Ni, Nicholas Crispino +8
We present a novel visual instruction tuning strategy to improve the zero-shot task generalization of multimodal large language models by building a firm text-only knowledge base.…
COSMIC: Generalized Refusal Direction Identification in LLM Activations
Vincent Siu, Nicholas Crispino, Zihao Yu +5
Large Language Models (LLMs) encode behaviors such as refusal within their activation space, yet identifying these behaviors remains a significant challenge. Existing methods often…
Agent Instructs Large Language Models to be General Zero-Shot Reasoners
Nicholas Crispino, Kyle Montgomery, Fankun Zeng +2
We introduce a method to improve the zero-shot reasoning abilities of large language models on general language understanding tasks. Specifically, we build an autonomous agent to i…
Re-Tuning: Overcoming the Compositionality Limits of Large Language Models with Recursive Tuning
Eric Pasewark, Kyle Montgomery, Kefei Duan +2
We present a new method for large language models to solve compositional tasks. Although they have shown strong performance on traditional language understanding tasks, large langu…