collaborators

9 papers

cs.SE2025

LogPurge: Log Data Purification for Anomaly Detection via Rule-Enhanced Filtering

Shenglin Zhang, Ziang Chen, Zijing Que +5

Log anomaly detection, which is critical for identifying system failures and preempting security breaches, detects irregular patterns within large volumes of log data, and impacts…

cs.AI2025

RationAnomaly: Log Anomaly Detection with Rationality via Chain-of-Thought and Reinforcement Learning

Song Xu, Yilun Liu, Minggui He +10

Logs constitute a form of evidence signaling the operational status of software systems. Automated log anomaly detection is crucial for ensuring the reliability of modern software…

cs.SE2025

R-Log: Incentivizing Log Analysis Capability in LLMs via Reasoning-based Reinforcement Learning

Yilun Liu, Ziang Chen, Song Xu +10

The growing complexity of log data in modern software systems has prompted the use of Large Language Models (LLMs) for automated log analysis. Current approaches typically rely on…

cs.LG2025

Parameter-Efficient Routed Fine-Tuning: Mixture-of-Experts Demands Mixture of Adaptation Modules

Yilun Liu, Yunpu Ma, Yuetian Lu +3

Mixture-of-Experts (MoE) benefits from a dynamic routing mechanism among their specialized experts, which existing Parameter- Efficient Fine-Tuning (PEFT) strategies fail to levera…

cs.CL2025

ELSPR: Evaluator LLM Training Data Self-Purification on Non-Transitive Preferences via Tournament Graph Reconstruction

Yan Yu, Yilun Liu, Minggui He +9

Pairwise evaluation of large language models (LLMs) has become the dominant paradigm for benchmarking open-ended tasks, yet non-transitive preferences, where evaluators prefer A ov…

cs.CL2025

MIDB: Multilingual Instruction Data Booster for Enhancing Cultural Equality in Multilingual Instruction Synthesis

Yilun Liu, Chunguang Zhao, Xinhua Yang +9

Despite doubts on data quality, instruction synthesis has been widely applied into instruction tuning (IT) of LLMs as an economic and rapid alternative. Recent endeavors focus on i…