2 citations · 5 across the 20 of their papers we have counts for
20 papers
Code Monitor Red Teaming for Public-Test-Passing Code
Junchi Liao, Jiawen Deng, Fuji Ren
Visible tests are a common gate for LLM-generated code, but passing them does not certify specification correctness. We study a deployment-like monitoring problem: after code has p…
MANATEE: Inference-Time Lightweight Diffusion Based Safety Defense for LLMs
Chun Yan Ryan Kan, Tommy Tran, Vedant Yadav +4
Defending LLMs against adversarial jailbreak attacks remains an open challenge. Existing defenses rely on binary classifiers that fail when adversarial input falls outside the lear…
MiSCHiEF: A Benchmark in Minimal-Pairs of Safety and Culture for Holistic Evaluation of Fine-Grained Image-Caption Alignment
Sagarika Banerjee, Tangatar Madi, Advait Swaminathan +4
Fine-grained image-caption alignment is crucial for vision-language models (VLMs), especially in socially critical contexts such as identifying real-world risk scenarios or disting…
Visualizing and Benchmarking LLM Factual Hallucination Tendencies via Internal State Analysis and Clustering
Nathan Mao, Varun Kaushik, Shreya Shivkumar +3
Large Language Models (LLMs) often hallucinate, generating nonsensical or false information that can be especially harmful in sensitive fields such as medicine or law. To study thi…
Zero-Shot Embedding Drift Detection: A Lightweight Defense Against Prompt Injections in LLMs
Anirudh Sekar, Mrinal Agarwal, Rachel Sharma +4
Prompt injection attacks have become an increasing vulnerability for LLM applications, where adversarial prompts exploit indirect input channels such as emails or user-generated co…
AMVICC: A Novel Benchmark for Cross-Modal Failure Mode Profiling for VLMs and IGMs
Aahana Basappa, Pranay Goel, Anusri Karra +3
We investigate visual reasoning limitations of both multimodal large language models (MLLMs) and image generation models (IGMs) by creating a novel benchmark to systematically comp…
Interpretable Perturbation Modeling Through Biomedical Knowledge Graphs
Pascal Passigan, Kevin Zhu, Angelina Ning
Understanding how small molecules perturb gene expression is essential for uncovering drug mechanisms, predicting off-target effects, and identifying repurposing opportunities. Whi…
AutoAdv: Automated Adversarial Prompting for Multi-Turn Jailbreaking of Large Language Models
Aashray Reddy, Andrew Zagula, Nicholas Saban
Large Language Models (LLMs) remain vulnerable to jailbreaking attacks where adversarial prompts elicit harmful outputs. Yet most evaluations focus on single-turn interactions whil…
Emergent World Beliefs: Exploring Transformers in Stochastic Games
Adam Kamel, Tanish Rastogi, Michael Ma +2
Transformer-based large language models (LLMs) have demonstrated strong reasoning abilities across diverse fields, from solving programming challenges to competing in strategy-inte…
Factor(U,T): Controlling Untrusted AI by Monitoring their Plans
Edward Lue Chee Lip, Anthony Channg, Diana Kim +2
As AI capabilities advance, we increasingly rely on powerful models to decompose complex tasks $\unicode{x2013}$ but what if the decomposer itself is malicious? Factored cognition…
ASCIIBench: Evaluating Language-Model-Based Understanding of Visually-Oriented Text
Kerry Luo, Michael Fu, Joshua Peguero +6
Large language models (LLMs) have demonstrated several emergent behaviors with scale, including reasoning and fluency in long-form text generation. However, they continue to strugg…
Don't Think of the White Bear: Ironic Negation in Transformer Models Under Cognitive Load
Logan Mann, Nayan Saxena, Sarah Tandon +3
Negation instructions such as 'do not mention ' can paradoxically increase the accessibility of in human thought, a phenomenon known as ironic rebound. Large language models…
Optimizing Chain-of-Thought Confidence via Topological and Dirichlet Risk Analysis
Abhishek More, Anthony Zhang, Nicole Bonilla +4
Chain-of-thought (CoT) prompting enables Large Language Models to solve complex problems, but deploying these models safely requires reliable confidence estimates, a capability whe…
Reliable Weak-to-Strong Monitoring of LLM Agents
Neil Kale, Chen Bo Calvin Zhang, Kevin Zhu +5
We stress test monitoring systems for detecting covert misbehavior in autonomous LLM agents (e.g., secretly sharing private information). To this end, we systematize a monitor red…
AutoAdv: Automated Adversarial Prompting for Multi-Turn Jailbreaking of Large Language Models
Aashray Reddy, Andrew Zagula, Nicholas Saban
Large Language Models (LLMs) continue to exhibit vulnerabilities to jailbreaking attacks: carefully crafted malicious inputs intended to circumvent safety guardrails and elicit har…
UniToMBench: Integrating Perspective-Taking to Improve Theory of Mind in LLMs
Prameshwar Thiyagarajan, Vaishnavi Parimi, Shamant Sai +5
Theory of Mind (ToM), the ability to understand the mental states of oneself and others, remains a challenging area for large language models (LLMs), which often fail to predict hu…
QIANets: Quantum-Integrated Adaptive Networks for Reduced Latency and Improved Inference Times in CNN Models
Zhumazhan Balapanov, Vanessa Matvei, Olivia Holmberg +3
Convolutional neural networks (CNNs) have made significant advances in computer vision tasks, yet their high inference times and latency often limit real-world applicability. While…
NusaMT-7B: Machine Translation for Low-Resource Indonesian Languages with Large Language Models
William Tan, Kevin Zhu
Large Language Models (LLMs) have demonstrated exceptional promise in translation tasks for high-resource languages. However, their performance in low-resource languages is limited…
Evaluating K-Fold Cross Validation for Transformer Based Symbolic Regression Models
Kaustubh Kislay, Shlok Singh, Soham Joshi +4
Symbolic Regression remains an NP-Hard problem, with extensive research focusing on AI models for this task. Transformer models have shown promise in Symbolic Regression, but perfo…
Enhancing Robustness of Human Detection Algorithms in Maritime SAR through Augmented Aerial Images to Simulate Weather Conditions
Miguel Tjia, Artem Kim, Elaine Wynette Wijaya +2
7,651 cases of Search and Rescue Missions (SAR) were reported by the United States Coast Guard in 2024, with over 1322 SAR helicopters deployed in the 6 first months alone. Through…