大模型推理能力

TOOL4POI: A Tool-Augmented LLM Framework for Next POI Recommendation

TOOL4POI: 一种增强工具的LLM框架用于下一步POI推荐

Dongsheng Wang, Shen Gao, Chengrui Huang, Yuxi Huang, Ruixiang Feng, Shuo Shang

专题命中 其他推理 ：reasoning(abstract)

AI总结 Tool4POI通过外部检索和推理提升POI推荐性能，无需微调即可兼容现成LLM，实现对OOH场景的显著改进。

Comments A critical technical error was discovered during our internal review, leading to unreliable experimental results. The issue cannot be resolved, and the paper has also been formally withdrawn from AAAI 2026. We therefore request withdrawal of the arXiv version to maintain scientific accuracy

Prompt Tuning as User Inherent Profile Inference Machine

提示调优作为用户固有属性推断机器

Yusheng Lu, Zhaocheng Du, Xiangyang Li, Pengyue Jia, Yejing Wang, Weiwen Liu, Yichao Wang, Huifeng Guo, Ruiming Tang, Zhenhua Dong, Yongrui Duan, Xiangyu Zhao

专题命中 其他推理 ：reasoning(abstract)

AI总结 UserIP-Tuning通过提示调优推断用户档案，结合因果关系和EM算法减少噪声，提升推荐系统效率与效果。

Comments This paper has been accepted by CIKM 2025

CLIP-UP: CLIP-Based Unanswerable Problem Detection for Visual Question Answering

CLIP-UP: 基于CLIP的视觉问答中不可回答问题检测

Ben Vardi, Oron Nir, Ariel Shamir

专题命中 其他推理 ：reasoning(abstract)

AI总结 CLIP-UP通过基于CLIP的相似性度量，为视觉问答模型提供检测不可回答问题的能力，提升模型在不可回答问题上的识别性能。

Comments Revised version. Improvements include support for open-ended VQA and an alternative injection method