"knowledge-intensive tasks" Papers

10 papers found

Boosting Knowledge Utilization in Multimodal Large Language Models via Adaptive Logits Fusion and Attention Reallocation

Wenbin An, Jiahao Nie, Feng Tian et al.

NEURIPS 2025oral

Chain-of-Retrieval Augmented Generation

Liang Wang, Haonan Chen, Nan Yang et al.

NEURIPS 2025arXiv:2501.14342
28
citations

DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation

Jiashuo Sun, Xianrui Zhong, Sizhe Zhou et al.

NEURIPS 2025arXiv:2505.07233
6
citations

EAReranker: Efficient Embedding Adequacy Assessment for Retrieval Augmented Generation

Dongyang Zeng, Yaping Liu, Wei Zhang et al.

NEURIPS 2025

Inference Scaling for Long-Context Retrieval Augmented Generation

Zhenrui Yue, Honglei Zhuang, Aijun Bai et al.

ICLR 2025arXiv:2410.04343
54
citations

Mixture of Parrots: Experts improve memorization more than reasoning

Samy Jelassi, Clara Mohri, David Brandfonbrener et al.

ICLR 2025arXiv:2410.19034
14
citations

MMVU: Measuring Expert-Level Multi-Discipline Video Understanding

Yilun Zhao, Lujing Xie, Haowei Zhang et al.

CVPR 2025arXiv:2501.12380
78
citations

RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language Models

Jiarui Zhang, Xiangyu Liu, Yong Hu et al.

NEURIPS 2025arXiv:2505.23052
4
citations

Reinforcement Learning for Out-of-Distribution Reasoning in LLMs: An Empirical Study on Diagnosis-Related Group Coding

Hanyin Wang, Zhenbang Wu, Gururaj Kolar et al.

NEURIPS 2025spotlightarXiv:2505.21908
5
citations

Understanding Finetuning for Factual Knowledge Extraction

Gaurav Ghosal, Tatsunori Hashimoto, Aditi Raghunathan

ICML 2024arXiv:2406.14785
28
citations