PromptDistill: Query-based Selective Token Retention in Intermediate Layers for Efficient Large Language Model Inference.
CoRR, March, 2025
Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025
M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework.
CoRR, 2024
Anti-Attack Intrusion Detection Model Based on MPNN and Traffic Spatiotemporal Characteristics.
J. Grid Comput., December, 2023