69 citations · 235 across the 60 of their papers we have counts for
26 papers · 1 filter
Auditing Agent Harness Safety
Chengzhi Liu, Yichen Guo, Yepeng Liu +8
LLM agents increasingly run inside execution harnesses that dispatch tools, allocate resources, and route messages between specialized components. However, a harness can return a c…
InfoSynth: Information-Guided Benchmark Synthesis for LLMs
Ishir Garg, Neel Kolhe, Xuandong Zhao +1
Large language models (LLMs) have demonstrated significant advancements in reasoning and code generation, but efficiently creating new benchmarks to evaluate these capabilities rem…
Machine Bullshit: Characterizing the Emergent Disregard for Truth in Large Language Models
Kaiqu Liang, Haimin Hu, Xuandong Zhao +3
Bullshit, as conceptualized by philosopher Harry Frankfurt, refers to statements made without regard to their truth value. While previous work has explored large language model (LL…
AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents
Jingxu Xie, Dylan Xu, Xuandong Zhao +1
We introduce AgentSynth, a scalable and cost-efficient pipeline for automatically synthesizing high-quality tasks and trajectory datasets for generalist computer-use agents. Levera…
In-Context Watermarks for Large Language Models
Yepeng Liu, Xuandong Zhao, Christopher Kruegel +2
The growing use of large language models (LLMs) for sensitive applications has highlighted the need for effective watermarking techniques to ensure the provenance and accountabilit…
Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs
Will Cai, Tianneng Shi, Xuandong Zhao +1
Commercial Large Language Model (LLM) APIs create a fundamental trust problem: users pay for specific models but have no guarantee that providers deliver them faithfully. Providers…
MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
Chejian Xu, Jiawei Zhang, Zhaorun Chen +22
Multimodal foundation models (MMFMs) play a crucial role in various applications, including autonomous driving, healthcare, and virtual assistants. However, several studies have re…
Improving LLM Safety Alignment with Dual-Objective Optimization
Xuandong Zhao, Will Cai, Tianneng Shi +4
Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks. Direct preference optimization (DPO), a widely deployed…
Scalable Best-of-N Selection for Large Language Models via Self-Certainty
Zhewei Kang, Xuandong Zhao, Dawn Song
Best-of-N selection is a key technique for improving the reasoning performance of Large Language Models (LLMs) through increased test-time computation. Current state-of-the-art met…
A Practical Examination of AI-Generated Text Detectors for Large Language Models
Brian Tufts, Xuandong Zhao, Lei Li
The proliferation of large language models has raised growing concerns about their misuse, particularly in cases where AI-generated text is falsely attributed to human authors. Mac…
Efficiently Identifying Watermarked Segments in Mixed-Source Texts
Xuandong Zhao, Chenwen Liao, Yu-Xiang Wang +1
Text watermarks in large language models (LLMs) are increasingly used to detect synthetic text, mitigating misuse cases like fake news and academic dishonesty. While existing water…
ClinicalLab: Aligning Agents for Multi-Departmental Clinical Diagnostics in the Real World
Weixiang Yan, Haitian Liu, Tengxiao Wu +9
LLMs have achieved significant performance progress in various NLP applications. However, LLMs still struggle to meet the strict requirements for accuracy and reliability in the me…
CodeHalu: Investigating Code Hallucinations in LLMs via Execution-based Verification
Yuchen Tian, Weixiang Yan, Qian Yang +6
Large Language Models (LLMs) have made significant progress in code generation, offering developers groundbreaking automated programming support. However, LLMs often generate code…
Mapping the Increasing Use of LLMs in Scientific Papers
Weixin Liang, Yaohui Zhang, Zhengxuan Wu +11
Scientific publishing lays the foundation of science by disseminating research findings, fostering collaboration, encouraging reproducibility, and ensuring that scientific knowledg…
Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews
Weixin Liang, Zachary Izzo, Yaohui Zhang +9
We present an approach for estimating the fraction of text in a large corpus which is likely to be substantially modified or produced by a large language model (LLM). Our maximum l…
GumbelSoft: Diversified Language Model Watermarking via the GumbelMax-trick
Jiayi Fu, Xuandong Zhao, Ruihan Yang +3
Large language models (LLMs) excellently generate human-like text, but also raise concerns about misuse in fake news and academic dishonesty. Decoding-based watermark, particularly…
Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement
Wenda Xu, Guanglei Zhu, Xuandong Zhao +3
Recent studies show that large language models (LLMs) improve their performance through self-feedback on certain tasks while degrade on others. We discovered that such a contrary i…
DE-COP: Detecting Copyrighted Content in Language Models Training Data
André V. Duarte, Xuandong Zhao, Arlindo L. Oliveira +1
How can we detect if copyrighted content was used in the training process of a language model, considering that the training data is typically undisclosed? We are motivated by the…
Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs
Xuandong Zhao, Lei Li, Yu-Xiang Wang
In this paper, we propose a new decoding method called Permute-and-Flip (PF) decoder. It enjoys stability properties similar to the standard sampling decoder, but is provably up to…
Weak-to-Strong Jailbreaking on Large Language Models
Xuandong Zhao, Xianjun Yang, Tianyu Pang +4
Large language models (LLMs) are vulnerable to jailbreak attacks - resulting in harmful, unethical, or biased text generations. However, existing jailbreaking methods are computati…
A Survey on Detection of LLMs-Generated Content
Xianjun Yang, Liangming Pan, Xuandong Zhao +4
The burgeoning capabilities of advanced large language models (LLMs) such as ChatGPT have led to an increase in synthetic content generation with implications across a variety of s…
Provable Robust Watermarking for AI-Generated Text
Xuandong Zhao, Prabhanjan Ananth, Lei Li +1
We study the problem of watermarking large language models (LLMs) generated text -- one of the most promising approaches for addressing the safety challenges of LLM usage. In this…
Pre-trained Language Models Can be Fully Zero-Shot Learners
Xuandong Zhao, Siqi Ouyang, Zhiguo Yu +2
How can we extend a pre-trained model to many language understanding tasks, without labeled or additional unlabeled data? Pre-trained language models (PLMs) have been effective for…
Distillation-Resistant Watermarking for Model Protection in NLP
Xuandong Zhao, Lei Li, Yu-Xiang Wang
How can we protect the intellectual property of trained NLP models? Modern NLP models are prone to stealing by querying and distilling from their publicly exposed APIs. However, ex…