收藏切换
Dentate Gyrus of Large Language Models: A Scenario Cognition Diagnosis and Enhancement Framework Based on Pattern Separation
收藏切换
Boxiang Ma1, Ru Li1, *, Shaoru Guo1, Yinghao Li1, Gutiérrez-Basulto Víctor2
Journal of Computer Research and Development | 2026, 63(9) : 2187 - 2201
Less
收藏切换
Journal of Computer Research and Development | 2026, 63(9): 2187-2201
• Special Issue on Frontier Technologies and Applications of Knowledge-Enhanced Artificial Intelligence •
Dentate Gyrus of Large Language Models: A Scenario Cognition Diagnosis and Enhancement Framework Based on Pattern Separation
Full
Boxiang Ma1, Ru Li1, *, Shaoru Guo1, Yinghao Li1, Gutiérrez-Basulto Víctor2
Affiliations
  • 1School of Computer Science and Technology, Shanxi University, Taiyuan 030006
  • 2School of Computer Science and Informatics, Cardiff University, Cardiff, Wales CF24 4AG
  • born in 2000. PhD candidate. His main research interests include natural language processing and language cognition

    born in 1963. Professor, PhD supervisor. Her main research interests include natural language processing and information retrieval

    born in 1990. Lecturer, master supervisor. Her main research interests include natural language processing and knowledge engineering

    born in 1994. Lecturer. His main research interests include in-context learning and large language model reasoning

    born in 1981. Associate professor, PhD supervisor. His main research interests include knowledge representation and reasoning, representation learning, natural language processing and data management

About Author:

born in 2000. PhD candidate. His main research interests include natural language processing and language cognition

born in 1963. Professor, PhD supervisor. Her main research interests include natural language processing and information retrieval

born in 1990. Lecturer, master supervisor. Her main research interests include natural language processing and knowledge engineering

born in 1994. Lecturer. His main research interests include in-context learning and large language model reasoning

born in 1981. Associate professor, PhD supervisor. His main research interests include knowledge representation and reasoning, representation learning, natural language processing and data management

Published: 2026-09-01 doi: 10.7544/issn1000-1239.202660437
Outline
收藏切换

Large language models (LLMs) exhibit systematic generalization limitations in scenario cognition tasks, revealing potential functional deficiencies in their knowledge memorization processes. Inspired by the pattern separation mechanism of the dentate gyrus in the human hippocampus, we hypothesize that failures in scenario cognition are associated with limitations in the internal pattern separation capability of LLMs. Based on this hypothesis, we first design a cross-entity representation diagnosis (CERD) method, which quantitatively measures entity representation confusion across different layers without additional training. Our analysis reveals that standard autoregressive training fails to induce sufficiently effective pattern separation capabilities, leaving substantial cross-entity correlation confusion within LLM representations. Building upon this observation, we further propose latent-space pattern separation (LPS), which explicitly incorporates pattern separation constraints into the training process by introducing a triplet-based contrastive regularization at target layers with severe entity confusion, thereby reducing correlations among easily confused knowledge representations. Extensive experiments across LLMs ranging from 0.8B to 9B parameters demonstrate that LPS consistently improves scenario cognition capabilities. Compared with standard autoregressive training, our method achieves up to 101.5% relative improvement in exact match (EM), providing a new perspective for understanding and enhancing scenario cognition and knowledge memorization mechanisms in LLMs.

large language models  /  scenario cognition  /  pattern separation  /  knowledge memorization  /  representation learning
马博翔, 李茹, 郭少茹, 李英豪, VíctorGutiérrez-Basulto. 大语言模型的齿状回:基于模式分离的场景认知能力诊断及增强框架. 计算机研究与发展, 2026 , 63 (9) : 2187 -2201 . DOI: 10.7544/issn1000-1239.202660437
Boxiang Ma, Ru Li, Shaoru Guo, Yinghao Li, Gutiérrez-Basulto Víctor. Dentate Gyrus of Large Language Models: A Scenario Cognition Diagnosis and Enhancement Framework Based on Pattern Separation[J]. Journal of Computer Research and Development, 2026 , 63 (9) : 2187 -2201 . DOI: 10.7544/issn1000-1239.202660437
Year 2026 volume 63 Issue 9
64
32
Cite this Article
BibTeX
Article Info
doi: 10.7544/issn1000-1239.202660437
  • Receive Date:2026-06-06
  • Online Date:2026-11-17
  • Published:2026-09-01
Article Data
Affiliations
History
  • Received:2026-06-06
  • Revised:2026-07-16
Affiliations
    1School of Computer Science and Technology, Shanxi University, Taiyuan 030006
    2School of Computer Science and Informatics, Cardiff University, Cardiff, Wales CF24 4AG
References
Share
https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202660437
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT