Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913169196187648 |
|---|---|
| author | Li, Yuqing Li, Jiangnan Lin, Zheng Zhou, Ziyan Wu, Junjie Wang, Weiping Zhou, Jie Yu, Mo |
| author_facet | Li, Yuqing Li, Jiangnan Lin, Zheng Zhou, Ziyan Wu, Junjie Wang, Weiping Zhou, Jie Yu, Mo |
| contents | Humans understand long and complex texts by relying on a holistic semantic representation of the content. This global view helps organize prior knowledge, interpret new information, and integrate evidence dispersed across a document, as revealed by the Mindscape-Aware Capability of humans in psychology. Current Retrieval-Augmented Generation (RAG) systems lack such guidance and therefore struggle with long-context tasks. In this paper, we propose Mindscape-Aware RAG (MiA-RAG), the first framework to formulate mindscape-aware retrieval and generation as a unified conditioning paradigm for LLM-based RAG. MiA-RAG builds a mindscape through hierarchical summarization and conditions both retrieval and generation on this global semantic representation. This enables the retriever to form enriched query embeddings and the generator to reason over retrieved evidence within a coherent global context. We evaluate MiA-RAG across diverse long-context and bilingual benchmarks for evidence-based understanding and global sense-making. It consistently surpasses baselines, and further analysis shows that it aligns local details with a coherent global representation, enabling more human-like long-context retrieval and reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_17220 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding Li, Yuqing Li, Jiangnan Lin, Zheng Zhou, Ziyan Wu, Junjie Wang, Weiping Zhou, Jie Yu, Mo Computation and Language Humans understand long and complex texts by relying on a holistic semantic representation of the content. This global view helps organize prior knowledge, interpret new information, and integrate evidence dispersed across a document, as revealed by the Mindscape-Aware Capability of humans in psychology. Current Retrieval-Augmented Generation (RAG) systems lack such guidance and therefore struggle with long-context tasks. In this paper, we propose Mindscape-Aware RAG (MiA-RAG), the first framework to formulate mindscape-aware retrieval and generation as a unified conditioning paradigm for LLM-based RAG. MiA-RAG builds a mindscape through hierarchical summarization and conditions both retrieval and generation on this global semantic representation. This enables the retriever to form enriched query embeddings and the generator to reason over retrieved evidence within a coherent global context. We evaluate MiA-RAG across diverse long-context and bilingual benchmarks for evidence-based understanding and global sense-making. It consistently surpasses baselines, and further analysis shows that it aligns local details with a coherent global representation, enabling more human-like long-context retrieval and reasoning. |
| title | Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2512.17220 |