Similar Items: When More Reformulations Hurt: Avoiding Drift using Ranker Feedback
- A Reproducibility Study of LLM-Based Query Reformulation
- Nautilus Compass: Black-box Persona Drift Detection for Production LLM Agents
- NeocorRAG: Less Irrelevant Information, More Explicit Evidence, and More Effective Recall via Evidence Chains
- When to Retrieve During Reasoning: Adaptive Retrieval for Large Reasoning Models
- Understanding DNNs in Feature Interaction Models: A Dimensional Collapse Perspective
- Efficient Listwise Reranking with Compressed Document Representations