SLP-P8.9
UA-TTRL: Uncertainty-Aware Test-Time Reinforcement Learning
Zixuan Liu, Tulane University, United States of America; Siavash Khajavi, Aalto University, Finland; Guangkai Jiang, Norwegian University of Science and Technology, Finland; Xinru Liu, Aalto University, Finland
Session:
SLP-P8: Question Answering: Reasoning and Agents Poster
Track:
Speech and Language Processing [SL]
Location:
Poster Area 28
Presentation Time:
Tue, 5 May, 16:30 - 18:30
Presentation
Discussion
Resources
No resources available.
Session SLP-P8
SLP-P8.1: Read Before You Think: Mitigating LLM Comprehension Failures with Step-by-Step Reading
Feijiang Han, Hengtao Cui, Licheng Guo, Zelong Wang, Zhiyuan Lyu, University of Pennsylvania, United States of America
SLP-P8.2: DUALAST: AST-GUIDED EXEMPLAR RETRIEVAL FOR IN-CONTEXT LEARNING IN MULTI-STEP REASONING
Hejing Huang, Chuang Liu, Mengting Yuan, Wuhan University, China
SLP-P8.3: Exploiting Latent and Implicit chain of thought for Efficient multi-hop question answering
Hassan Shakil, University of Colorado, Colorado Springs, United States of America; Vijay Srinivasan, Haris Jeelani, Kalpa Gunaratna, Srinivas Chappidi, AI Center-Mountain View, Samsung Electronics, United States of America
SLP-P8.4: PATHFINDER: MCTS AND LLM FEEDBACK-BASED PATH SELECTION FOR MULTI-HOP QUESTION ANSWERING
Durga Prasad Maram, University of Massachusetts Amherst, United States of America; Kalpa Gunaratna, Vijay Srinivasan, Haris Jeelani, Srinivas Chappidi, AI Center-Mountain View, Samsung Electronics, United States of America
SLP-P8.5: TRACE: OPTIMIZING MULTI-HOP QUESTION ANSWERING VIA CONFIDENCE-GUIDED RETRIEVAL ASSIMILATION
Yuantao Han, Yingxin Pei, Haibo Luo, Binquan Ji, Jiaqi Wang, Yifei Lu, Feiliang Ren, Northeastern University, China
SLP-P8.6: SEARAG: SEMANTIC ENTROPY-GUIDED ADAPTIVE RETRIEVAL FOR MULTI-HOP QUESTION ANSWERING
Dingfu Yu, Qinhong Lin, Beijing University of Posts and Telecommunications, China; Zhongliang Yang, Quan Cheng Laboratory, Beijing University of Posts and Telecommunications, China; Linna Zhou, Beijing University of Posts and Telecommunications, Quan Cheng Laboratory, China
SLP-P8.7: Consensus-Awarded Multi-Agent Debate via Adversarial Interaction
Hao Zheng, Ying Zhang, Northwest Polytechnical University, China; Rajiv Ratn Shah, Indraprastha Institute of Information Technology Delhi, India; Bin Guo, Northwestern Polytechnical University, China; Zhiwen Yu, Harbin Engineering University, China
SLP-P8.8: RELIABLE DATABASE QUESTION ANSWERING WITH COLLABORATIVE AGENTS
Meng Zhang, Xiyue Wang, Yuanxi Peng, Wenjing Yang, Silin Yang, Ruochun Jin, National University of Defense Technology, China
SLP-P8.9: UA-TTRL: Uncertainty-Aware Test-Time Reinforcement Learning
Zixuan Liu, Tulane University, United States of America; Siavash Khajavi, Aalto University, Finland; Guangkai Jiang, Norwegian University of Science and Technology, Finland; Xinru Liu, Aalto University, Finland
SLP-P8.10: TCC: USING TOPIC CHAINS TO COMPRESS PROMPTS FOR LONG DOCUMENT QUESTION ANSWERING
Shiwei Chen, Harbin Institute of Technology (Shen Zhen), China; Bin Liang, The Chinese University of Hong Kong, China; Jianzhi Yan, Le Liu, Harbin Institute of Technology (Shen Zhen), China; Hui Wang, Yue Yu, Peng Cheng Laboratory, China; Kam-Fai Wong, The Chinese University of Hong Kong, China; Ruifeng Xu, Harbin Institute of Technology (Shen Zhen), China
Contacts