ExplicitLM: Decoupling Knowledge from Parameters via Explicit Memory Banks

Chengzhang Yu, Zening Lu, Chenyang Zheng, Chiyue Wang, Yiming Zhang, Zhanpeng Jin

Keywords: Interpretability of Large Language Models, Large Model Memory, Large Model Architecture

Abstract: Large language models (LLMs) universally suffer from knowledge staleness and lack of interpretability due to their implicit knowledge storage paradigm, where information is distributed across network parameters in an entangled, non-addressable manner. This fundamental limitation prevents targeted knowledge updates, verification of stored information, and understanding of model reasoning processes. We propose ExplicitLM, a novel architecture that fundamentally reimagines knowledge storage in language models through an explicit, interpretable memory bank system. Our key innovation introduces a million-scale external memory bank where each entry stores human-readable knowledge as token sequences, enabling direct inspection and modification of the model's knowledge base. To efficiently access this massive repository, we design a \textbf{differentiable two-stage retrieval mechanism that enables end-to-end training while maintaining discrete knowledge selection}, combining efficient coarse-grained filtering with product key decomposition (reducing computational complexity from $\mathcal{O}(N \cdot |I|)$ to $\mathcal{O}(\sqrt{N} \cdot |I|)$) and fine-grained similarity matching through Gumbel-Softmax. Drawing inspiration from dual-system cognitive theory, we partition knowledge into frozen explicit facts (20\%) and learnable implicit patterns (80\%), maintained through an Exponential Moving Average update strategy that ensures training stability. Extensive experiments demonstrate that ExplicitLM achieves up to 43.67\% improvement in knowledge-intensive tasks compared to standard Transformers, with particularly pronounced gains in low-data regimes (3.62$\times$ improvement with 10k samples). Our analysis reveals strong correlations between memory retrieval success and task performance, with correctly predicted samples achieving 49\% higher memory hit rates. Unlike traditional RAG systems with frozen retrieval components, our jointly optimized architecture demonstrates that interpretable, updatable language models can maintain competitive performance while providing unprecedented transparency into their knowledge utilization.

Primary Area: foundation or frontier models, including LLMs

Submission Number: 11628