Reversal of Thought: Enhancing Large Language Models with Preference-Guided Reverse Reasoning Warm-up ACL

Jiahao Yuan | Dehui Du | Hao Zhang | Zixiang Di | Usman Naseem |

ReflectDiffu: Reflect between Emotion-intent Contagion and Mimicry for Empathetic Response Generation via a RL-Diffusion Framework ACL

Jiahao Yuan | Zixiang Di | Zhiqing Cui | Guisong Yang | Usman Naseem |

LLMSR@XLLM25: Less is More: Enhancing Structured Multi-Agent Reasoning via Quality-Guided Distillation XLLM WS

Jiahao Yuan | Xingzhe Sun | Xing Yu | Jingwen Wang | Dehui Du | Zhiqing Cui | Zixiang Di |