10 papers
Persuasion Should be Double-Blind: A Multi-Domain Dialogue Dataset With Faithfulness Based on Causal Theory of Mind
Dingyi Zhang, Linhai Zhang, Fanglei Qu +2
Persuasive dialogue is central to human communication, yet existing datasets often rely on a single language model generating both roles, producing unrealistic interactions that vi…
The Pensieve Paradigm: Stateful Language Models Mastering Their Own Context
Xiaoyuan Liu, Tian Liang, Dongyang Ma +4
In the world of Harry Potter, when Dumbledore's mind is overburdened, he extracts memories into a Pensieve to be revisited later. In the world of AI, while we possess the Pensieve-…
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…
When KV Cache Reuse Fails in Multi-Agent Systems: Cross-Candidate Interaction is Crucial for LLM Judges
Sichu Liang, Zhenglin Wang, Jiajia Chu +3
Multi-agent LLM systems routinely generate multiple candidate responses that are aggregated by an LLM judge. To reduce the dominant prefill cost in such pipelines, recent work advo…
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…