5 papers
Clarify-Then-Search: A Clarification Benchmark for Deep Search with End-to-End Nugget Restoration
Deqiang Huang, Jingbo Zhou, Xinjiang Lu +3
Deep search is brittle on underspecified user queries: missing constraints such as time, location, scope, or definitions can lead to retrieval drift and incomplete answers. We intr…
Position: Beyond Model-Centric Prediction -- Agentic Time Series Forecasting
Mingyue Cheng, Xiaoyu Tao, Qi Liu +2
Time series forecasting has traditionally been formulated as a model-centric, static, and single-pass prediction problem that maps historical observations to future values. While t…
Hierarchical Multimodal LLMs with Semantic Space Alignment for Enhanced Time Series Classification
Xiaoyu Tao, Tingyue Pan, Mingyue Cheng +3
Time series classification plays a fundamental role in a wide range of real-world applications. Recently, large language models (LLMs) have demonstrated strong generalization and r…
Multi-Source Knowledge Pruning for Retrieval-Augmented Generation: A Benchmark and Empirical Study
Shuo Yu, Mingyue Cheng, Qi Liu +6
Retrieval-augmented generation (RAG) is increasingly recognized as an effective approach to mitigating the hallucination of large language models (LLMs) through the integration of…
DASKT: A Dynamic Affect Simulation Method for Knowledge Tracing
Xinjie Sun, Kai Zhang, Qi Liu +4
Knowledge Tracing (KT) predicts future performance by modeling students' historical interactions, and understanding students' affective states can enhance the effectiveness of KT,…