Researcher — paper.dinq.me

2026 顶会论文

作者位次 #4/9ICLR 2026Poster· Applications / Language, Speech and Dialog

DeepRAG: Thinking to Retrieve Step by Step for Large Language Models

Xinyan Guan · Jiali Zeng · Fandong Meng · Chunlei Xin · Yaojie Lu · Hongyu Lin · Xianpei Han · Le Sun · Jie Zhou

多模态检索与知识OpenReview

作者位次 #3/8ACL 2026Findings· Findings of ACL

Knowing When to Quit: Diagnosing and Training LLM s to Abort Futile Reasoning

Xinyan Guan · Jiali Zeng · Chunlei Xin · Yaojie Lu · Hongyu Lin · Xianpei Han · Le Sun · Fandong Meng

摘要

Large language models generate computationally expensive yet semantically void reasoning on beyond-capability tasks, creating safety risks where plausible-sounding but incorrect derivations mislead users. We characterize this futile reasoning phenomenon through systematic analysis, revealing univ...

安全推理对齐与偏好OpenReview 项目页

作者位次 #2/10AAAI 2026Poster· Artificial Intelligence

AI-Salesman: Towards Reliable Large Language Model Driven Telemarketing

Qingyu Zhang · Chunlei Xin · Xuanang Chen · Yaojie Lu · Hongyu Lin · Xianpei Han · Le Sun · Qing Ye · Qianlong Xie · Xingxing Wang

OpenReview

Chunlei Xin

获取完整研究档案

联系方式

2026 顶会论文

DeepRAG: Thinking to Retrieve Step by Step for Large Language Models

Knowing When to Quit: Diagnosing and Training LLM s to Abort Futile Reasoning

AI-Salesman: Towards Reliable Large Language Model Driven Telemarketing

常见合作者