6 papers · 1 filter
Can Vision Replace Text in Working Memory? Evidence from Spatial n-Back in Vision-Language Models
Sichu Liang, Hongyu Zhu, Wenwen Wang +1
Working memory is a central component of intelligent behavior, providing a dynamic workspace for maintaining and updating task-relevant information. Recent work has used n-back tas…
Large Language Models Have Intrinsic Meta-Cognition, but Need a Good Lens
Ziyang Ma, Qingyue Yuan, Zhenglin Wang +1
Previous research has primarily focused on the cognitive error detection capabilities of Large Language Models (LLMs), often prompting them to analyze mistakes in reasoning chains.…
AdaRewriter: Unleashing the Power of Prompting-based Conversational Query Reformulation via Test-Time Adaptation
Yilong Lai, Jialong Wu, Zhenglin Wang +1
Prompting-based conversational query reformulation has emerged as a powerful approach for conversational search, refining ambiguous user queries into standalone search queries. Bes…
Benchmarking Temporal Reasoning and Alignment Across Chinese Dynasties
Zhenglin Wang, Jialong Wu, Pengfei LI +2
Temporal reasoning is fundamental to human cognition and is crucial for various real-world applications. While recent advances in Large Language Models have demonstrated promising…
WebWalker: Benchmarking LLMs in Web Traversal
Jialong Wu, Wenbiao Yin, Yong Jiang +8
Retrieval-augmented generation (RAG) demonstrates remarkable performance across tasks in open-domain question-answering. However, traditional search engines may retrieve shallow co…
SCOPE: Optimizing Key-Value Cache Compression in Long-context Generation
Jialong Wu, Zhenglin Wang, Linhai Zhang +3
Key-Value (KV) cache has become a bottleneck of LLMs for long-context generation. Despite the numerous efforts in this area, the optimization for the decoding phase is generally ig…