Tag
This comprehensive survey systematically reviews graph neural network-based methods across the entire knowledge graph pipeline, proposing a novel two-level taxonomy and discussing challenges and future research directions.
This paper introduces Preference Delta Aggregation (PDA) and Geometric Alignment Merging (GAM) to aggregate multiple 'weak' preference signals from weaker model pairs via LoRA merging, improving strong LLMs on knowledge reasoning and agentic search tasks by over 6% on average.