Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding
cs.CL
Submitted: 2025-12-19
Updated: 2026-11-03
Terminology
Sources
- LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding
- Titans: Learning to Memorize at Test Time
- BooookScore: A systematic exploration of book-length summarization in the era of LLMs
- M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- Retrieval-Augmented Generation for Large Language Models: A Survey
- NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models
- Towards General Text Embeddings with Multi-stage Contrastive Learning
- Nomic Embed: Training a Reproducible Long Context Text Embedder
- CLIPPER: Compression enables long-context synthetic data generation
- jina-embeddings-v3: Multilingual Embeddings With Task LoRA
- Representation Learning with Contrastive Predictive Coding
- CodeRAG-Bench: Can Retrieval Augment Code Generation?
- SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension
- Efficient Streaming Language Models with Attention Sinks
- PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference
- HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly
- A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data