11 citations · 24 across the 19 of their papers we have counts for
20 papers
AwarenessBench: Assessing Cognitive Capabilities of Language Models
Xiaojian Li, Rongwu Xu, Tianyun Zhang +9
As language models (LMs) exhibit increasingly consciousness-like behaviors, evaluating their cognitive abilities becomes essential. We introduce AwarenessBench, the first comprehen…
Detecting LLM-Generated Spam Reviews by Integrating Language Model Embeddings and Graph Neural Network
Xin Liu, Rongwu Xu, Xinyi Jia +4
The rise of large language models (LLMs) has enabled the generation of highly persuasive spam reviews that closely mimic human writing. These reviews pose significant challenges fo…
Difficulty-Based Preference Data Selection by DPO Implicit Reward Gap
Xuan Qi, Rongwu Xu, Zhijing Jin
Aligning large language models (LLMs) with human preferences is a critical challenge in AI research. While methods like Reinforcement Learning from Human Feedback (RLHF) and Direct…
AICrypto: Evaluating Cryptography Capabilities of Large Language Models
Yu Wang, Yijian Liu, Liheng Ji +11
We build \textbf{AICrypto}, a comprehensive benchmark designed to evaluate the cryptography capabilities of large language models (LLMs). The benchmark comprises 135 multiple-choic…
The Singapore Consensus on Global AI Safety Research Priorities
Yoshua Bengio, Tegan Maharaj, Luke Ong +84
Rapidly improving AI capabilities and autonomy hold significant promise of transformation, but are also driving vigorous debate on how to ensure that AI is safe, i.e., trustworthy,…
Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?
Chengda Lu, Xiaoyu Fan, Yu Huang +3
Jailbreak attacks have been observed to largely fail against recent reasoning models enhanced by Chain-of-Thought (CoT) reasoning. However, the underlying mechanism remains underex…
AI Awareness
Xiaojian Li, Haoyuan Shi, Rongwu Xu +1
Recent breakthroughs in artificial intelligence (AI) have brought about increasingly capable systems that demonstrate remarkable abilities in reasoning, language understanding, and…
Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents
Rongwu Xu, Xiaojian Li, Shuo Chen +1
Large language models (LLMs) are evolving into autonomous decision-makers, raising concerns about catastrophic risks in high-stakes scenarios, particularly in Chemical, Biological,…
LongRAG: Evaluating Long-Context & Long-Form Retrieval-Augmented Generation with Key Point Recall
Zehan Qi, Rongwu Xu, Zhijiang Guo +3
Retrieval-augmented generation (RAG) is a promising approach to address the limitations of fixed knowledge in large language models (LLMs). However, current benchmarks for evaluati…
DebateQA: Evaluating Question Answering on Debatable Knowledge
Rongwu Xu, Xuan Qi, Zehan Qi +2
The rise of large language models (LLMs) has enabled us to seek answers to inherently debatable questions on LLM chatbots, necessitating a reliable way to evaluate their ability. H…
Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias
Rongwu Xu, Zi'an Zhou, Tianwei Zhang +5
The common toxicity and societal bias in contents generated by large language models (LLMs) necessitate strategies to reduce harm. Present solutions often demand white-box access t…
Course-Correction: Safety Alignment Using Synthetic Preferences
Rongwu Xu, Yishuo Cai, Zhenhong Zhou +6
The risk of harmful content generated by large language models (LLMs) becomes a critical concern. This paper presents a systematic study on assessing and improving LLMs' capability…
How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States
Zhenhong Zhou, Haiyang Yu, Xinghua Zhang +3
Large language models (LLMs) rely on safety alignment to avoid responding to malicious user inputs. Unfortunately, jailbreak can circumvent safety guardrails, resulting in LLMs gen…
MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs
Zhongshen Zeng, Yinhong Liu, Yingjia Wan +16
Large language models (LLMs) have shown increasing capability in problem-solving and decision-making, largely based on the step-by-step chain-of-thought reasoning processes. Howeve…
Preemptive Answer "Attacks" on Chain-of-Thought Reasoning
Rongwu Xu, Zehan Qi, Wei Xu
Large language models (LLMs) showcase impressive reasoning capabilities when coupled with Chain-of-Thought (CoT) prompting. However, the robustness of this approach warrants furthe…
Exploring Chinese Humor Generation: A Study on Two-Part Allegorical Sayings
Rongwu Xu
Humor, a culturally nuanced aspect of human language, poses challenges for computational understanding and generation, especially in Chinese humor, which remains relatively unexplo…
Knowledge Conflicts for LLMs: A Survey
Rongwu Xu, Zehan Qi, Zhijiang Guo +4
This survey provides an in-depth analysis of knowledge conflicts for large language models (LLMs), highlighting the complex challenges they encounter when blending contextual and p…
Tempo: Confidentiality Preservation in Cloud-Based Neural Network Training
Rongwu Xu, Zhixuan Fang
Cloud deep learning platforms provide cost-effective deep neural network (DNN) training for customers who lack computation resources. However, cloud systems are often untrustworthy…
The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation
Rongwu Xu, Brian S. Lin, Shujian Yang +6
Large language models (LLMs) encapsulate vast amounts of knowledge but still remain vulnerable to external misinformation. Existing research mainly studied this susceptibility beha…
MISO: Legacy-compatible Privacy-preserving Single Sign-on using Trusted Execution Environments
Rongwu Xu, Sen Yang, Fan Zhang +1
Single sign-on (SSO) allows users to authenticate to third-party applications through a central identity provider. Despite their wide adoption, deployed SSO systems suffer from pri…