Theme of inquiry
How should AI systems organize and retrieve knowledge for improved reasoning?
A question within its area, explored through 5 lines of inquiry below — each a family of specific questions the research asks.
59 specific questions
- How do retrieved documents in RAG systems compound input length problems?
- What causes the retrieval-augmented generation to fail in practice?
- Why do retrieval-augmented generation systems fail to detect knowledge conflicts?
- Can long-context models replace retrieval-augmented generation systems?
- Can retrieval augmented generation systems defend against corpus poisoning without retraining?
- How does retrieval-augmented generation create topically redundant content patterns?
- Does retrieval quality depend more on access structure or write gating?
64 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?
- Can embedding-based retrieval alone solve the causal relevance problem?
- What mathematical limits constrain embedding-based retrieval systems?
73 specific questions
- Can adaptive per-step decisions outperform uniform retrieval policies across different reasoning tasks?
- How should retrieval systems handle multi-hop reasoning and iterative information needs?
- How does query decomposition reduce retrieval costs at inference?
- Does parallel retrieval outperform sequential search chains at test time?
- Do different network layers specialize in retrieval versus reasoning tasks?
- When does long-context LLM reasoning fail where structured retrieval succeeds?
- What is the optimal balance between search rounds and reasoning depth per round?
43 specific questions
- How does uncertainty-gated retrieval compare to continuous retrieval efficiency?
- Can adaptive retrieval triggered by model uncertainty improve RAG reliability?
- How should retrieval systems decide when to fetch new information?
- Are uncertainty estimation and external feature signals complementary for retrieval?
- Should retrieval be triggered by model uncertainty or fixed intervals?
- How do confidence thresholds compare to learned policies for triggering retrieval?
- How much does retrieval budget improve when triggered by dual signals instead of fixed intervals?
57 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 graph databases address the relational query failures that LLMs encounter?
- Can inference-time query decomposition replace pre-built knowledge graph structures?
- Can query-time logic graphs match the efficiency of pre-built knowledge graph indexing?
- How do taxonomy-based retrieval scaffolds improve model performance at inference time?