Theme of inquiry
How should retrieval systems combine and rank diverse sources?
A question within its area, explored through 4 lines of inquiry below — each a family of specific questions the research asks.
62 specific questions
- How do vector embeddings fail to capture task-relevant document relationships?
- Why do embedding-based retrieval systems fail on vocabulary mismatch?
- Can vector embeddings measure task relevance instead of semantic similarity?
- Why do semantic similarity and task relevance diverge in vector search results?
- What makes vector embeddings fail on single-hop semantic relevance queries?
- What mathematical limits constrain embedding-based retrieval systems?
- Do multi-vector or cross-encoder models escape these dimensional constraints?
67 specific questions
- Can knowledge graph structure be exploited for efficient multi-hop retrieval?
- Can graph-based retrieval with knowledge graphs scale to multi-hop reasoning?
- How do community-based summaries differ from retrieval-based traversal in knowledge graph RAG?
- How do taxonomy-based retrieval scaffolds improve model performance at inference time?
- How do graph databases address the relational query failures that LLMs encounter?
- How can knowledge graphs improve over pure embedding retrieval?
- When should you use knowledge graphs instead of semantic vector retrieval systems?
104 specific questions
- Why do different language models succeed on different queries?
- Why do NLP benchmarks exclude ambiguous instances from evaluation?
- How do human annotators disagree systematically on ambiguous examples?
- What makes a clarifying question aligned with user interests versus structurally sound?
- Why do NLP benchmarks treat annotation disagreement as noise rather than signal?
- How do static benchmarks fail to capture human preference alignment?
- Why do benchmarks measuring string quality fail to capture communicative success?
120 specific questions
- Can adaptive per-step decisions outperform uniform retrieval policies across different reasoning tasks?
- How should retrieval systems decide when to fetch new information?
- Should retrieval be triggered always or only for difficult questions?
- What causes the retrieval-augmented generation to fail in practice?
- How should retrieval systems handle multi-hop reasoning and iterative information needs?
- How does uncertainty-gated retrieval compare to continuous retrieval efficiency?
- Does parallel retrieval outperform sequential search chains at test time?