1 citations · 1 across the 10 of their papers we have counts for
13 papers
MixDetect: Word-Level Localization and Quantification of AI Editing
Hongrui Bao, Yubing Ren, Zhendong Pan +3
Large language models are increasingly used to edit human-written text rather than generate entire texts from scratch. Conventional AI-text detectors mainly distinguish human-writt…
Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration
Hongrui Bao, Yubing Ren, Yanan Cao +3
Large language models (LLMs) can generate fluent and convincing text at scale, creating growing risks for misinformation dissemination, educational misuse, and platform governance.…
EA-Agent: A Structured Multi-Step Reasoning Agent for Entity Alignment
Yixuan Nan, Xixun Lin, Yanmin Shang +4
Entity alignment (EA) aims to identify entities across different knowledge graphs (KGs) that refer to the same real-world object and plays a critical role in knowledge fusion and i…
Do LLMs Know Tool Irrelevance? Demystifying Structural Alignment Bias in Tool Invocations
Yilong Liu, Xixun Lin, Pengfei Cao +3
Large language models (LLMs) have demonstrated impressive capabilities in utilizing external tools. In practice, however, LLMs are often exposed to tools that are irrelevant to the…
Rethinking LLM Watermark Detection in Black-Box Settings: A Non-Intrusive Third-Party Framework
Zhuoshang Wang, Yubing Ren, Yanan Cao +3
While watermarking serves as a critical mechanism for LLM provenance, existing secret-key schemes tightly couple detection with injection, requiring access to keys or provider-side…
Exons-Detect: Identifying and Amplifying Exonic Tokens via Hidden-State Discrepancy for Robust AI-Generated Text Detection
Xiaowei Zhu, Yubing Ren, Fang Fang +3
The rapid advancement of large language models has increasingly blurred the boundary between human-written and AI-generated text, raising societal risks such as misinformation diss…
From Essence to Defense: Adaptive Semantic-aware Watermarking for Embedding-as-a-Service Copyright Protection
Hao Li, Yubing Ren, Yanan Cao +3
Benefiting from the superior capabilities of large language models in natural language understanding and generation, Embeddings-as-a-Service (EaaS) has emerged as a successful comm…
DualGuard: Dual-stream Large Language Model Watermarking Defense against Paraphrase and Spoofing Attack
Hao Li, Yubing Ren, Yanan Cao +4
With the rapid development of cloud-based services, large language models have become increasingly accessible through various web platforms. However, this accessibility has also le…
MetaGDPO: Alleviating Catastrophic Forgetting with Metacognitive Knowledge through Group Direct Preference Optimization
Lanxue Zhang, Yuqiang Xie, Fang Fang +3
Large Language Models demonstrate strong reasoning capabilities, which can be effectively compressed into smaller models. However, existing datasets and fine-tuning approaches stil…
MAD-Fact: A Multi-Agent Debate Framework for Long-Form Factuality Evaluation in LLMs
Yucheng Ning, Xixun Lin, Fang Fang +1
The widespread adoption of Large Language Models (LLMs) raises critical concerns about the factual accuracy of their outputs, especially in high-risk domains such as biomedicine, l…
DNA-DetectLLM: Unveiling AI-Generated Text via a DNA-Inspired Mutation-Repair Paradigm
Xiaowei Zhu, Yubing Ren, Fang Fang +3
The rapid advancement of large language models (LLMs) has blurred the line between AI-generated and human-written text. This progress brings societal risks such as misinformation,…
PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization
Yidan Wang, Yanan Cao, Yubing Ren +3
Large Language Models (LLMs) excel in various domains but pose inherent privacy risks. Existing methods to evaluate privacy leakage in LLMs often use memorized prefixes or simple i…
Reliably Bounding False Positives: A Zero-Shot Machine-Generated Text Detection Framework via Multiscaled Conformal Prediction
Xiaowei Zhu, Yubing Ren, Yanan Cao +3
The rapid advancement of large language models has raised significant concerns regarding their potential misuse by malicious actors. As a result, developing effective detectors to…