Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.10426 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908957278208000 |
|---|---|
| author | Li, Cheng-Yen Chen, Xuanjun Lin, Claire Chen, Wei-Yu Nie, Wenhua Lee, Hung-Yi Jang, Jyh-Shing Roger |
| author_facet | Li, Cheng-Yen Chen, Xuanjun Lin, Claire Chen, Wei-Yu Nie, Wenhua Lee, Hung-Yi Jang, Jyh-Shing Roger |
| contents | Large Language Models (LLMs) struggle with knowledge-intensive tasks due to hallucinations and fragmented reasoning over dispersed information. While Retrieval-Augmented Generation (RAG) grounds generation in external sources, existing methods often treat evidence as isolated units, failing to reconstruct the logical chains that connect these dots. Inspired by Complementary Learning Systems (CLS), we propose CodaRAG, a framework that evolves retrieval from passive lookup into active associative discovery. CodaRAG operates via a three-stage pipeline: (1) Knowledge Consolidation to unify fragmented extractions into a stable memory substrate; (2) Associative Navigation to traverse the graph via multi-dimensional pathways-semantic, contextualized, and functional-explicitly recovering dispersed evidence chains; and (3) Interference Elimination to prune hyper-associative noise, ensuring a coherent, high-precision reasoning context. On GraphRAG-Bench, CodaRAG achieves absolute gains of 7-10% in retrieval recall and 3-11% in generation accuracy. These results demonstrate CodaRAG's superior ability to systematically robustify associative evidence retrieval for factual, reasoning, and creative tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_10426 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CodaRAG: Connecting the Dots with Associativity Inspired by Complementary Learning Li, Cheng-Yen Chen, Xuanjun Lin, Claire Chen, Wei-Yu Nie, Wenhua Lee, Hung-Yi Jang, Jyh-Shing Roger Computation and Language Artificial Intelligence Large Language Models (LLMs) struggle with knowledge-intensive tasks due to hallucinations and fragmented reasoning over dispersed information. While Retrieval-Augmented Generation (RAG) grounds generation in external sources, existing methods often treat evidence as isolated units, failing to reconstruct the logical chains that connect these dots. Inspired by Complementary Learning Systems (CLS), we propose CodaRAG, a framework that evolves retrieval from passive lookup into active associative discovery. CodaRAG operates via a three-stage pipeline: (1) Knowledge Consolidation to unify fragmented extractions into a stable memory substrate; (2) Associative Navigation to traverse the graph via multi-dimensional pathways-semantic, contextualized, and functional-explicitly recovering dispersed evidence chains; and (3) Interference Elimination to prune hyper-associative noise, ensuring a coherent, high-precision reasoning context. On GraphRAG-Bench, CodaRAG achieves absolute gains of 7-10% in retrieval recall and 3-11% in generation accuracy. These results demonstrate CodaRAG's superior ability to systematically robustify associative evidence retrieval for factual, reasoning, and creative tasks. |
| title | CodaRAG: Connecting the Dots with Associativity Inspired by Complementary Learning |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2604.10426 |