12 papers
Measuring and Detecting Harmful AI Sycophancy
Bohan Jiang, Dawei Li, Yasin Silva +1
Sycophantic responses are becoming pervasive in large language models (LLMs), and prior work has pointed out that some of them could be harmful. This paper focuses on one harmful s…
TextCloak: Thwarting Unauthorized LLM Exploitation via RL-Driven Unlearnable Text
Chengshuai Zhao, Pingchuan Ma, Dawei Li +4
The rapid development of Large Language Models (LLMs) has led to significant advances across a wide range of language tasks, while simultaneously raising growing concerns about una…
Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens
Chengshuai Zhao, Zhen Tan, Pingchuan Ma +5
Chain-of-Thought (CoT) prompting has been shown to be effective in eliciting structured reasoning (i.e., CoT reasoning) from large language models (LLMs). Regardless of its popular…
Multimodal Large Language Models as Synthetic Participants in Video-Based Studies: An Evaluation
Prabal Shrestha, Bohan Jiang, Haoning Xue +2
Multimodal large language models (MLLMs) have shown strong performance on objective tasks such as video understanding and reasoning. However, it remains unclear whether they can ap…
Preference Leakage: A Contamination Problem in LLM-as-a-judge
Dawei Li, Renliang Sun, Yue Huang +6
Large Language Models (LLMs) as judges and LLM-based data synthesis have emerged as two fundamental LLM-driven data annotation methods in model development. While their combination…
CAMO: Causality-Guided Adversarial Multimodal Domain Generalization for Crisis Classification
Pingchuan Ma, Chengshuai Zhao, Bohan Jiang +5
Crisis classification in social media aims to extract actionable disaster-related information from multimodal posts, which is a crucial task for enhancing situational awareness and…