5 papers
Hallucination Self-Play: Bootstrapping Reinforced Detector via Evolved Generator
Shiping Yang, Shining Liang, Weihao Liu +4
Identifying faithfulness hallucinations in LLM-generated outputs remains challenging due to the scarcity of high-quality annotated data. Recent work relies on advanced LLMs to synt…
RustMizan: A Compilable, Contamination-Aware Benchmarking Framework for Rust Vulnerabilities
Tarek Elsayed, Shiping Yang, Eunsong Koh +13
LLM agents are increasingly applied to vulnerability analysis, but existing benchmarks have not kept pace. They typically rely on small non-compilable snippets, focus on binary cla…
Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning
Zhao Yang, Yuxuan Jiang, Ting-Chih Chen +18
Reinforcement learning (RL) has become central to LLM post-training, yet the methods that dominate current pipelines, PPO and GRPO, represent only a narrow slice of what RL offers.…
Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation
Hengyuan Zhang, Shiping Yang, Xiao Liang +8
Training student models on synthetic data generated by strong teacher models is a promising way to distilling the capabilities of teachers. However, recent studies show that strong…
VISOR: VIsual Spatial Object Reasoning for Language-driven Object Navigation
Francesco Taioli, Shiping Yang, Sonia Raychaudhuri +3
Language-driven object navigation requires agents to interpret natural language descriptions of target objects, which combine intrinsic and extrinsic attributes for instance recogn…