Liu Yixin
YOU?
Author Swipe
View article: On Evaluating LLM Alignment by Evaluating LLMs as Judges
On Evaluating LLM Alignment by Evaluating LLMs as Judges Open
Alignment with human preferences is an important evaluation aspect of LLMs, requiring them to be helpful, honest, safe, and to precisely follow human instructions. Evaluating large language models' (LLMs) alignment typically involves direc…
View article: On Evaluating LLM Alignment by Evaluating LLMs as Judges
On Evaluating LLM Alignment by Evaluating LLMs as Judges Open
Alignment with human preferences is an important evaluation aspect of LLMs, requiring them to be helpful, honest, safe, and to precisely follow human instructions. Evaluating large language models' (LLMs) alignment typically involves direc…
View article: Signatures of magnetism in zigzag graphene nanoribbon embedded in h-BN lattice
Signatures of magnetism in zigzag graphene nanoribbon embedded in h-BN lattice Open
Zigzag edges of graphene have long been predicted to exhibit magnetic electronic state near the Fermi level, which can cause spin-related phenomena and offer unique potentials for graphene-based spintronics. However, the magnetic conductio…
View article: Correcting False Alarms from Unseen: Adapting Graph Anomaly Detectors at Test Time
Correcting False Alarms from Unseen: Adapting Graph Anomaly Detectors at Test Time Open
Graph anomaly detection (GAD), which aims to detect outliers in graph-structured data, has received increasing research attention recently. However, existing GAD methods assume identical training and testing distributions, which is rarely …
View article: Correcting False Alarms from Unseen: Adapting Graph Anomaly Detectors at Test Time
Correcting False Alarms from Unseen: Adapting Graph Anomaly Detectors at Test Time Open
Graph anomaly detection (GAD), which aims to detect outliers in graph-structured data, has received increasing research attention recently. However, existing GAD methods assume identical training and testing distributions, which is rarely …
View article: Correcting False Alarms from Unseen: Adapting Graph Anomaly Detectors at Test Time
Correcting False Alarms from Unseen: Adapting Graph Anomaly Detectors at Test Time Open
Graph anomaly detection (GAD), which aims to detect outliers in graph-structured data, has received increasing research attention recently. However, existing GAD methods assume identical training and testing distributions, which is rarely …
View article: Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems
Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems Open
The communication topology in large language model-based multi-agent systems fundamentally governs inter-agent collaboration patterns, critically shaping both the efficiency and effectiveness of collective decision-making. While recent stu…
View article: CourtReasoner: Can LLM Agents Reason Like Judges?
CourtReasoner: Can LLM Agents Reason Like Judges? Open
LLMs are increasingly applied in the legal domain in tasks such as summarizing legal texts and providing basic legal advice. Yet, their capacity to draft full judicial analyses in U.S. court opinions is still largely uncharted, such as gen…
View article: Agentic AutoSurvey: Let LLMs Survey LLMs
Agentic AutoSurvey: Let LLMs Survey LLMs Open
The exponential growth of scientific literature poses unprecedented challenges for researchers attempting to synthesize knowledge across rapidly evolving fields. We present \textbf{Agentic AutoSurvey}, a multi-agent framework for automated…
View article: BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks
BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks Open
The security of LLM-based multi-agent systems (MAS) is critically threatened by propagation vulnerability, where malicious agents can distort collective decision-making through inter-agent message interactions. While existing supervised de…
View article: Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems
Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems Open
The communication topology in large language model-based multi-agent systems fundamentally governs inter-agent collaboration patterns, critically shaping both the efficiency and effectiveness of collective decision-making. While recent stu…
View article: NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes
NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes Open
Retrieval-augmented generation (RAG) empowers large language models to access external and private corpus, enabling factually consistent responses in specific domains. By exploiting the inherent structure of the corpus, graph-based RAG met…
View article: Could AI Trace and Explain the Origins of AI-Generated Images and Text?
Could AI Trace and Explain the Origins of AI-Generated Images and Text? Open
AI-generated content is becoming increasingly prevalent in the real world, leading to serious ethical and societal concerns. For instance, adversaries might exploit large multimodal models (LMMs) to create images that violate ethical or le…
View article: PHYSICS: Benchmarking Foundation Models on University-Level Physics Problem Solving
PHYSICS: Benchmarking Foundation Models on University-Level Physics Problem Solving Open
We introduce PHYSICS, a comprehensive benchmark for university-level physics problem solving. It contains 1297 expert-annotated problems covering six core areas: classical mechanics, quantum mechanics, thermodynamics and statistical mechan…