4 papers
ConsistRM: Improving Generative Reward Models via Consistency-Aware Self-Training
Yu Liang, Liangxin Liu, Longzheng Wang +5
Generative reward models (GRMs) have emerged as a promising approach for aligning Large Language Models (LLMs) with human preferences by offering greater representational capacity…
ReflectRM: Boosting Generative Reward Models via Self-Reflection within a Unified Judgment Framework
Kai Qin, Liangxin Liu, Yu Liang +7
Reward Models (RMs) are critical components in the Reinforcement Learning from Human Feedback (RLHF) pipeline, directly determining the alignment quality of Large Language Models (…
Graph Optimization Foundation Model: Tokenizing Graph via A Language-Model Paradigm
Yunhao Liang, Pujun Zhang, Yuan Qu +3
The pretrain-transfer paradigm, which underpins the success of large language models (LLMs), has demonstrated the immense power of creating foundation models that learn generalizab…
Everyone Contributes! Incentivizing Strategic Cooperation in Multi-LLM Systems via Sequential Public Goods Games
Yunhao Liang, Yuan Qu, Jingyuan Yang +2
Coordinating multiple large language models (LLMs) to solve complex tasks collaboratively poses a fundamental trade-off between the computation costs and collective performance com…