Deep semantic understanding of events requires recognizing related events and distinguishing why an event occurs from how it is carried out. 5W1H extraction provides a structured foundation for such understanding by organizing event information around six fundamental questions. However, single-event slot filling provid...
Hong-Yu Jiang, Che-Nang Cai, Lei Gao et al.· 0 citations
Large language model (LLM) agents increasingly operate over long Web interaction histories, making memory management critical for reliable and efficient decision making. Existing methods primarily optimize storage, retrieval, or compression, but the memories most semantically relevant to the current state are not neces...
Quan-Jiang Guo, Si-Jie Wang, Qian-Yang Zhu et al.· 0 citations
Knowledge Graphs (KGs) are fundamental for grounding Large Language Models (LLMs) in factually consistent reasoning across diverse data-mining tasks. However, when reasoning over complex graph topologies, LLMs can be brittle in maintaining structural consistency and may rely on spurious correlations. We propose SKILL (...
Lei Gao, Ben Zhang, Jin-Chuan Zhang et al.· Proceedings of the 35th ACM...· 0 citations
Knowledge Graphs (KGs) are fundamental for grounding Large Language Models (LLMs) in factually consistent reasoning across diverse data-mining tasks. However, when reasoning over complex graph topologies, LLMs can be brittle in maintaining structural consistency and may rely on spurious correlations. We propose SKILL (...
Lei Gao, Ben Zhang, Jin-Chuan Zhang et al.· Proceedings of the 35th ACM...· 0 citations
Terminal feedback in multi-turn agent training leaves both rollout allocation and local credit underdetermined. Dynamics-Predictive Sampling (DPS) [9] provides a task-level predictive sampling reference, but interactive agents also need to choose which visited states merit further continuations. We introduce TSBPO with...
STAIR separates semantic interpretation from precise temporal inference: an answer-free LLM adapter maps complex question formulations to normalized temporal intents, while a deterministic temporal automaton with finite control and guarded transitions executes the corresponding policies over canonicalized evidence.
Xin-Long Dai, Jin-Chuan Zhang, Lei Gao et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.