51 citations · 87 across the 16 of their papers we have counts for
10 papers · 1 filter
Explore Theory of Mind: Program-guided adversarial data generation for theory of mind reasoning
Melanie Sclar, Jane Yu, Maryam Fazel-Zarandi +4
Do large language models (LLMs) have theory of mind? A plethora of papers and benchmarks have been introduced to evaluate if current models have been able to develop this key abili…
Negative Token Merging: Image-based Adversarial Feature Guidance
Jaskirat Singh, Lindsey Li, Weijia Shi +7
Text-based adversarial guidance using a negative prompt has emerged as a widely adopted approach to steer diffusion models away from producing undesired concepts. While useful, per…
Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
Shangbin Feng, Zifeng Wang, Yike Wang +9
We propose Model Swarms, a collaborative search algorithm to adapt LLMs via swarm intelligence, the collective behavior guiding individual systems. Specifically, Model Swarms start…
Biased AI can Influence Political Decision-Making
Jillian Fisher, Shangbin Feng, Robert Aron +6
As modern large language models (LLMs) become integral to everyday tasks, concerns about their inherent biases and their potential impact on human decision-making have emerged. Whi…
The Art of Saying No: Contextual Noncompliance in Language Models
Faeze Brahman, Sachin Kumar, Vidhisha Balachandran +11
Chat-based language models are designed to be helpful, yet they should not comply with every user request. While most existing work primarily focuses on refusal of "unsafe" queries…
Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration
Shangbin Feng, Taylor Sorensen, Yuhan Liu +4
While existing alignment paradigms have been integral in developing large language models (LLMs), LLMs often learn an averaged human preference and struggle to model diverse prefer…
CulturalTeaming: AI-Assisted Interactive Red-Teaming for Challenging LLMs' (Lack of) Multicultural Knowledge
Yu Ying Chiu, Liwei Jiang, Maria Antoniak +7
Frontier large language models (LLMs) are developed by researchers and practitioners with skewed cultural backgrounds and on datasets with skewed sources. However, LLMs' (lack of)…
Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs
Aly M. Kassem, Omar Mahmoud, Niloofar Mireshghallah +5
In this paper, we introduce a black-box prompt optimization method that uses an attacker LLM agent to uncover higher levels of memorization in a victim agent, compared to what is r…
Do Membership Inference Attacks Work on Large Language Models?
Michael Duan, Anshuman Suri, Niloofar Mireshghallah +7
Membership inference attacks (MIAs) attempt to predict whether a particular datapoint is a member of a target model's training data. Despite extensive research on traditional machi…
Tuning Language Models by Proxy
Alisa Liu, Xiaochuang Han, Yizhong Wang +3
Despite the general capabilities of large pretrained language models, they consistently benefit from further adaptation to better achieve desired behaviors. However, tuning these m…