3 citations · 7 across the 16 of their papers we have counts for
14 papers · 1 filter
Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption
Yepeng Liu, Xuandong Zhao, Dawn Song +2
Despite progress in watermarking algorithms for large language models (LLMs), real-world deployment remains limited. We argue that this gap stems from misaligned incentives among L…
PromptArmor: Simple yet Effective Prompt Injection Defenses
Tianneng Shi, Kaijie Zhu, Zhun Wang +13
Despite their potential, recent research has demonstrated that LLM agents are vulnerable to prompt injection attacks, where malicious prompts are injected into the agent's input, c…
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…
The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation
Alexander Xiong, Xuandong Zhao, Aneesh Pappu +1
Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet they also exhibit memorization of their training data. This phenomenon rais…
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…
OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models
Ziheng Cheng, Yixiao Huang, Hui Xu +4
Text-to-Image (T2I) models have achieved remarkable success in generating visual content from text inputs. Although multiple safety alignment strategies have been proposed to preve…
Learning to Reason without External Rewards
Xuandong Zhao, Zhewei Kang, Aosong Feng +2
Training large language models (LLMs) for complex reasoning via Reinforcement Learning with Verifiable Rewards (RLVR) is effective but limited by reliance on costly, domain-specifi…
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…
SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning
Kaiwen Zhou, Xuandong Zhao, Gaowen Liu +4
Large Reasoning Models (LRMs) introduce a new generation paradigm of explicitly reasoning before answering, leading to remarkable improvements in complex tasks. However, they pose…
Assessing Judging Bias in Large Reasoning Models: An Empirical Study
Qian Wang, Zhanzhi Lou, Zhenheng Tang +5
Large Reasoning Models (LRMs) like DeepSeek-R1 and OpenAI-o1 have demonstrated remarkable reasoning capabilities, raising important questions about their biases in LLM-as-a-judge s…
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…
The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1
Kaiwen Zhou, Chengzhi Liu, Xuandong Zhao +5
The rapid development of large reasoning models (LRMs), such as OpenAI-o3 and DeepSeek-R1, has led to significant improvements in complex reasoning over non-reasoning large languag…
Dataset Protection via Watermarked Canaries in Retrieval-Augmented LLMs
Yepeng Liu, Xuandong Zhao, Dawn Song +1
Retrieval-Augmented Generation (RAG) has become an effective method for enhancing large language models (LLMs) with up-to-date knowledge. However, it may pose a risk of copyright i…