SLP-P56: LLM Reasoning and Planning II
Poster
Fri, 8 May, 14:00 - 16:00
Location: Poster Area 30
Session Type: Poster
Track: Speech and Language Processing [SL]
Click the to view the manuscript on IEEE Xplore Open Preview

SLP-P56.1: LEVERAGING MULTI-SOURCE RETRIEVAL AND EXPERT FILTERING FOR LLM-BASED KNOWLEDGE GRAPH COMPLETION
Wenhui Tian, Yang Cui, Weiqin Zou, Qun Yang, Nanjing University of Aeronautics and Astronautics, China

SLP-P56.2: TWO-STAGE GRID OPTIMIZATION FOR GROUP-WISE QUANTIZATION OF LLMS
Junhan Kim, Gukryeol Lee, Seungwoo Son, Jeewook Kim, Yongkweon Jeon, Samsung Research, Korea, Republic of

SLP-P56.3: ARCHAGENT: SCALABLE LEGACY SOFTWARE ARCHITECTURE RECOVERY WITH LLMS
Rusheng Pan, Bingcheng Mao, Tianyi Ma, HiThink Research, China; Zhenhua Ling, University of Science and Technology of China, China

SLP-P56.4: KAME: TANDEM ARCHITECTURE FOR ENHANCING KNOWLEDGE IN REAL-TIME SPEECH-TO-SPEECH CONVERSATIONAL AI
So Kuroki, Yotaro Kubo, Takuya Akiba, Yujin Tang, Sakana AI, Japan

SLP-P56.5: GRAPHEME: GRAPH NEURAL NETWORKS WITH MULTI-EXPERT FUSION FOR EMOTION-CAUSE PAIR EXTRACTION
Xue Gu, Ziyao Meng, University of Minho and Jilin University, Portugal; Adriano Tavares, Tiago Gomes, University of Minho, Portugal; Hao Xu, Jilin University, China

SLP-P56.6: TRACE: A TRIPLET-BASED ROBUSTNESS-AUGMENTED CAUSAL ENCODER FOR CAUSALITY GRAPH EVENT PREDICTION
Ziwei Zheng, Qing Zhang, Chuanhong Zhan, Bang Wang, Huazhong University of Science and Technology, China

SLP-P56.7: Can LLMs Beat Humans in Debating? A Dynamic Multi-agent Framework for Competitive Debate
Yiqun Zhang, Xiaocui Yang, Shi Feng, Daling Wang, Yifei Zhang, Northeastern University, China; Kaisong Song, Alibaba Group, China

SLP-P56.8: EPO: Enhanced Preference Optimization with Multi-Response Data for LLMs via Stochastic Softmax
Taoyu Wu, iFLYTEK Co., Ltd., Canada; Yuheng Li, Johns Hopkins University, Hong Kong; Jiechao Gao, Center for SDGC, Stanford University, Hong Kong; Wei Zhu, Ming Tan, Hui Yi Leong, University of Hong Kong, Hong Kong

SLP-P56.9: DSPC: Dual-Stage Progressive Compression Framework for Efficient Long-Context Reasoning
Yaxin Gao, Yao Lu, Zhejiang University of Technology, China; Zongfei Zhang, Amazon, United States of America; Jiaqi Nie, Shanqing Yu, Qi Xuan, Zhejiang University of Technology, China