Structure-Guided Memory Consolidation for Mitigating Compounding Errors in Literature Review Generation
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_ | 1866915768043569152 |
|---|---|
| author | Zhang, Zhi Liu, Yan Hu, Zhejing Chen, Gong Zhong, Shenghua Fontaine, Sean Cao, Jiannong |
| author_facet | Zhang, Zhi Liu, Yan Hu, Zhejing Chen, Gong Zhong, Shenghua Fontaine, Sean Cao, Jiannong |
| contents | Compounding errors pose a significant challenge in automatic literature review generation, as inaccuracies can cascade across multi-stage retrieval and generation workflows. Existing self-correction strategies often lack mechanisms to effectively track and consolidate verified information throughout the process, making it difficult to prevent error accumulation and propagation. In this paper, we propose Structure-Guided Memory Consolidation (SGMC), a novel framework that incrementally consolidates and verifies information using structured representations at each stage of the literature review pipeline. SGMC consists of three key modules: Tree-Guided Memory for hierarchical literature retrieval and outline generation, Hub-Guided Memory for evidence extraction and iterative content refinement, and Self-Loop Memory for proactive error correction via historical feedback. Extensive experiments on public benchmarks and a newly constructed large-scale dataset demonstrate that SGMC achieves state-of-the-art performance in citation accuracy and content quality, significantly mitigating compounding errors in long-form literature review generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_04306 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Structure-Guided Memory Consolidation for Mitigating Compounding Errors in Literature Review Generation Zhang, Zhi Liu, Yan Hu, Zhejing Chen, Gong Zhong, Shenghua Fontaine, Sean Cao, Jiannong Computational Engineering, Finance, and Science Compounding errors pose a significant challenge in automatic literature review generation, as inaccuracies can cascade across multi-stage retrieval and generation workflows. Existing self-correction strategies often lack mechanisms to effectively track and consolidate verified information throughout the process, making it difficult to prevent error accumulation and propagation. In this paper, we propose Structure-Guided Memory Consolidation (SGMC), a novel framework that incrementally consolidates and verifies information using structured representations at each stage of the literature review pipeline. SGMC consists of three key modules: Tree-Guided Memory for hierarchical literature retrieval and outline generation, Hub-Guided Memory for evidence extraction and iterative content refinement, and Self-Loop Memory for proactive error correction via historical feedback. Extensive experiments on public benchmarks and a newly constructed large-scale dataset demonstrate that SGMC achieves state-of-the-art performance in citation accuracy and content quality, significantly mitigating compounding errors in long-form literature review generation. |
| title | Structure-Guided Memory Consolidation for Mitigating Compounding Errors in Literature Review Generation |
| topic | Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2508.04306 |