24 citations · 46 across the 13 of their papers we have counts for
13 papers
Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations
Jianfeng Chi, Ujjwal Karn, Hongyuan Zhan +7
We introduce Llama Guard 3 Vision, a multimodal LLM-based safeguard for human-AI conversations that involves image understanding: it can be used to safeguard content for both multi…
Persistent Pre-Training Poisoning of LLMs
Yiming Zhang, Javier Rando, Ivan Evtimov +5
Large language models are pre-trained on uncurated text datasets consisting of trillions of tokens scraped from the Web. Prior work has shown that: (1) web-scraped pre-training dat…
Human-aligned Chess with a Bit of Search
Yiming Zhang, Athul Paul Jacob, Vivian Lai +2
Chess has long been a testbed for AI's quest to match human intelligence, and in recent years, chess AI systems have surpassed the strongest humans at the game. However, these syst…
Backtracking Improves Generation Safety
Yiming Zhang, Jianfeng Chi, Hailey Nguyen +4
Text generation has a fundamental limitation almost by definition: there is no taking back tokens that have been generated, even when they are clearly problematic. In the context o…
Forcing Diffuse Distributions out of Language Models
Yiming Zhang, Avi Schwarzschild, Nicholas Carlini +2
Despite being trained specifically to follow user instructions, today's instructiontuned language models perform poorly when instructed to produce random outputs. For example, when…
OpenHEXAI: An Open-Source Framework for Human-Centered Evaluation of Explainable Machine Learning
Jiaqi Ma, Vivian Lai, Yiming Zhang +5
Recently, there has been a surge of explainable AI (XAI) methods driven by the need for understanding machine learning model behaviors in high-stakes scenarios. However, properly e…
Effective Prompt Extraction from Language Models
Yiming Zhang, Nicholas Carlini, Daphne Ippolito
The text generated by large language models is commonly controlled by prompting, where a prompt prepended to a user's query guides the model's output. The prompts used by companies…
FLamE: Few-shot Learning from Natural Language Explanations
Yangqiaoyu Zhou, Yiming Zhang, Chenhao Tan
Natural language explanations have the potential to provide rich information that in principle guides model reasoning. Yet, recent work by Lampinen et al. (2022) has shown limited…
BiasX: "Thinking Slow" in Toxic Content Moderation with Explanations of Implied Social Biases
Yiming Zhang, Sravani Nanduri, Liwei Jiang +2
Toxicity annotators and content moderators often default to mental shortcuts when making decisions. This can lead to subtle toxicity being missed, and seemingly toxic but harmless…
Selective Explanations: Leveraging Human Input to Align Explainable AI
Vivian Lai, Yiming Zhang, Chacha Chen +2
While a vast collection of explainable AI (XAI) algorithms have been developed in recent years, they are often criticized for significant gaps with how humans produce and consume e…
Active Example Selection for In-Context Learning
Yiming Zhang, Shi Feng, Chenhao Tan
With a handful of demonstration examples, large-scale language models show strong capability to perform various tasks by in-context learning from these examples, without any fine-t…
Learning to Ignore Adversarial Attacks
Yiming Zhang, Yangqiaoyu Zhou, Samuel Carton +1
Despite the strong performance of current NLP models, they can be brittle against adversarial attacks. To enable effective learning against adversarial inputs, we introduce the use…
Conversations Gone Alright: Quantifying and Predicting Prosocial Outcomes in Online Conversations
Jiajun Bao, Junjie Wu, Yiming Zhang +2
Online conversations can go in many directions: some turn out poorly due to antisocial behavior, while others turn out positively to the benefit of all. Research on improving onlin…