Beyond Words: A Latent Memory Approach to Internal Reasoning in LLMs
This work addresses the computational inefficiency of explicit reasoning methods like chain-of-thought for LLMs, offering a potential improvement in model training and robustness, though it appears incremental as it builds on existing paradigms.
The paper tackles the problem of inefficient internal reasoning in large language models by proposing a framework that integrates implicit mental representations, resulting in a 35% to 57% reduction in training loss compared to a baseline GPT model.
Recent advances in large language models (LLMs) have popularized the chain-of-thought (CoT) paradigm, in which models produce explicit reasoning steps in natural language. Although this approach improves interpretability and facilitates external auditing, it may not represent the most computationally efficient method for internal reasoning. In contrast, human cognition relies on implicit mental representations that recall past sensory and episodic information without requiring complete verbalization. In this paper, we propose a framework that integrates implicit mental representations into the internal reasoning processes of LLMs. Preliminary experiments indicate that incorporating an Implicit Memory Module (IMM) into a simple GPT model yields a reduction of between 35% and 57% in final training loss compared to a regular GPT baseline. The addition of an explicit interpretability channel (e.g., a chain-of-thought decoder) is straightforward to implement within this approach. We outline theoretical foundations, propose technical mechanisms to scale the memory module, and discuss how these ideas may lead to more efficient and robust reasoning, with optional future extensions for explicit auditability.