ARK adaptively retrieves from knowledge graphs using global lexical search and one-hop neighborhood exploration, reaching 59.1% Hit@1 on STaRK with up to 31.4% gains over training-free baselines and enabling distillation to 8B models.
Multi-field adaptive retrieval.arXiv preprint arXiv:2410.20056
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
AF-Retriever delivers state-of-the-art zero- and one-shot results on three STaRK QA benchmarks by using LLM extraction, vector similarity, incremental scope expansion, and hybrid retrieval.
citing papers explorer
-
Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrieval
ARK adaptively retrieves from knowledge graphs using global lexical search and one-hop neighborhood exploration, reaching 59.1% Hit@1 on STaRK with up to 31.4% gains over training-free baselines and enabling distillation to 8B models.
-
Autofocus Retrieval: An Effective Pipeline for Multi-Hop Question Answering With Semi-Structured Knowledge
AF-Retriever delivers state-of-the-art zero- and one-shot results on three STaRK QA benchmarks by using LLM extraction, vector similarity, incremental scope expansion, and hybrid retrieval.