CacheGraft: Enhancing Retrieval-Augmented Generation via Latent-Space Document Enrichment
cs.IR, cs.LG
Submitted: 2026-11-05
Updated: 2026-11-06
Code: https://github.com/vihan-lakshman/CacheGraft
Terminology
Sources
- Phi-4 Technical Report
- EnrichIndex: Using LLMs to Enrich Retrieval Indices Offline
- Latent Space Communication via K-V Cache Alignment
- RL-Index: Reinforcement Learning for Retrieval Index Reasoning
- AutoIndex: Learning Representation Programs for Retrieval
- Latent Cache Flow: Model-to-Model Communication Without Text
- Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption
- Gemma 2: Improving Open Language Models at a Practical Size
- Document Optimization for Black-Box Retrieval via Reinforcement Learning
- Qwen3 Technical Report
Related papers
- UniRank: Benchmarking Ranking Models for Unified Sequential Modeling and Feature Interaction
- Revisiting Text Ranking in Deep Research
- GateSID: One Gate to Balance Semantic and Collaborative Signals across the Item Lifecycle
- SAM-D2Q: Aligning Multimodal Doc2Query with Search Demand and Conversion for E-commerce
- GINGER: Spicing Up Graph-Based Vector Search
- Subtraction Gets You More: Gap-Aware Retrieval for Multimodal Multi-Hop QA