collaborators

7 papers

cs.CL2026

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…

cs.AI2026

RepIt: Steering Language Models with Concept-Specific Refusal Vectors

Vincent Siu, Nathan W. Henry, Nicholas Crispino +3

Current safety evaluations of language models rely on benchmark-based assessments that may miss localized vulnerabilities. We present RepIt, a simple and data-efficient framework f…

cs.AI2025

LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess

Sai Kolasani, Maxim Saplin, Nicholas Crispino +5

We introduce LLM CHESS, an evaluation framework designed to probe the generalization of reasoning and instruction-following abilities in large language models (LLMs) through extend…

cs.CV2025

VMDT: Decoding the Trustworthiness of Video Foundation Models

Yujin Potter, Zhun Wang, Nicholas Crispino +11

As foundation models become more sophisticated, ensuring their trustworthiness becomes increasingly critical; yet, unlike text and image, the video modality still lacks comprehensi…

cs.AI2025

SteeringSafety: Benchmarking Representation Steering in LLMs Across Safety Perspectives

Vincent Siu, Nicholas Crispino, David Park +5

We introduce SteeringSafety, a benchmark for evaluating representation steering methods across nine safety perspectives spanning 18 datasets. While prior work highlights the genera…

cs.CL2025

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.…