5 papers
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…
Taming Text-to-Image Synthesis for Novices: User-centric Prompt Generation via Multi-turn Guidance
Yilun Liu, Minggui He, Feiyu Yao +9
The emergence of text-to-image synthesis (TIS) models has significantly influenced digital image creation by producing high-quality visuals from written descriptions. Yet these mod…
R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning
Minggui He, Yilun Liu, Shimin Tao +10
Despite recent breakthroughs in reasoning-enhanced large language models (LLMs) like DeepSeek-R1, incorporating inference-time reasoning into machine translation (MT), where human…
LogLM: From Task-based to Instruction-based Automated Log Analysis
Yilun Liu, Yuhe Ji, Shimin Tao +7
Automatic log analysis is essential for the efficient Operation and Maintenance (O&M) of software systems, providing critical insights into system behaviors. However, existing appr…
Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation
Yuan Ge, Yilun Liu, Chi Hu +10
With contributions from the open-source community, a vast amount of instruction tuning (IT) data has emerged. Given the significant resource allocation required for training and ev…