2 papers
cs.CL2026
Decoupling Strategy and Execution in Task-Focused Dialogue via Goal-Oriented Preference Optimization
Jingyi Xu, Xingyu Ren, Zhoupeng Shou +2
Large language models show potential in task-oriented dialogue systems, yet existing training methods often rely on token-level likelihood or preference optimization, which poorly…
cs.AI2025
CogGuide: Human-Like Guidance for Zero-Shot Omni-Modal Reasoning
Zhou-Peng Shou, Zhi-Qiang You, Fang Wang +1
Targeting the issues of "shortcuts" and insufficient contextual understanding in complex cross-modal reasoning of multimodal large models, this paper proposes a zero-shot multimoda…