Aligning Large Language Models via Self-Steering Optimization Paper • 2410.17131 • Published 15 days ago • 19
A Unified View of Delta Parameter Editing in Post-Trained Large-Scale Models Paper • 2410.13841 • Published 20 days ago • 14
StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization Paper • 2410.08815 • Published 26 days ago • 39
StructEval: Deepen and Broaden Large Language Model Assessment via Structured Evaluation Paper • 2408.03281 • Published Aug 6 • 9
ShortGPT: Layers in Large Language Models are More Redundant Than You Expect Paper • 2403.03853 • Published Mar 6 • 62
