作者位次 #4/4ICLR 2026Poster· Applications / Language, Speech and Dialog
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Zirui Wu · Lin Zheng · Zhihui Xie · Jiacheng Ye · Jiahui Gao · Shansan Gong · Yansong Feng · Zhenguo Li · Wei BI · Guorui Zhou · Lingpeng Kong
Chen Zhang · Jiuheng Lin · Zhiyuan Liao · Yansong Feng
Adapting large language models (LLMs) to low-resource languages (LRLs) is constrained by the scarcity of task data and computational resources. Although Proxy Tuning offers a logit-level strategy for introducing scaling effects, it often fails in LRL settings because the large model’s weak LRL co...
Kangcheng Luo · Tinglang Wu · Yansong Feng
Recent search-augmented LLMs trained with reinforcement learning (RL) can interleave searching and reasoning for multi-hop reasoning tasks. However, they face two critical failure modes as the accumulating context becomes flooded with both crucial evidence and irrelevant information: (1) ineffect...
Jiuheng Lin · Cong Jiang · Zirui Wu · Jiarui Sun · Yansong Feng
Training expert LLMs in domains with scarce fine-grained annotated data is admittedly challenging, often relying on multiple-choice questions (MCQs). However, standard outcome-based reinforcement learning (RL) on MCQs is risky. While outcome-based RL may improve accuracy, it frequently compromise...