作者位次 #3/4ACL 2026Poster· Natural Language Processing
Beyond Majority Voting: Towards Fine-grained and More Reliable Reward Signal for Test-Time Reinforcement Learning
Weiqin Wang · Yile Wang · Kehao Chen · Hui Huang
摘要
Test-time reinforcement learning mitigates the reliance on annotated data by using majority voting results as pseudo-labels, emerging as a complementary direction to reinforcement learning with verifiable rewards (RLVR) for improving reasoning ability of large language models (LLMs). However, thi...