Discovering Decoupled Functional Modules in Large Language Models

• URL: http://arxiv.org/abs/2603.17823v1
• Date: Wed, 18 Mar 2026 15:13:02 GMT
• Title: Discovering Decoupled Functional Modules in Large Language Models
• Abstract summary: How Large Language Models organize different functions into modules remains highly unexplored.<n>We propose an Unsupervised LLM Cross-layer MOdule Discovery (ULCMOD) framework that simultaneously disentangles the large set of neurons in the entire LLM into modules.<n>Our framework introduces a novel objective function and an efficient Iterative Decoupling (IterD) algorithm.
• Score: 21.534639190745978
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Understanding the internal functional organization of Large Language Models (LLMs) is crucial for improving their trustworthiness and performance. However, how LLMs organize different functions into modules remains highly unexplored. To bridge this gap, we formulate a functional module discovery problem and propose an Unsupervised LLM Cross-layer MOdule Discovery (ULCMOD) framework that simultaneously disentangles the large set of neurons in the entire LLM into modules while discovering the topics of input samples related to these modules. Our framework introduces a novel objective function and an efficient Iterative Decoupling (IterD) algorithm. Extensive experiments show that our method discovers high-quality, disentangled modules that capture more meaningful semantic information and achieve superior performance in various downstream tasks. Moreover, our qualitative analysis reveals that the discovered modules show semantic coherence, correspond to interpretable specializations, and a clear spatial and hierarchical organization within the LLM. Our work provides a novel tool for interpreting the functional modules of LLMs, filling a critical blank in LLM's interpretability research.

Related papers

• EduMod-LLM: A Modular Approach for Designing Flexible and Transparent Educational Assistants [7.295547133368925]
  We present a comprehensive evaluation of Large Language Model (LLM)-based Question-Answering systems.<n>Our framework enables fine-grained analysis by isolating and assessing each component.<n>This modular approach reveals specific failure modes and performance patterns, supporting the development of interpretable and effective educational QA systems.
  arXiv  Detail & Related papers  (2025-11-21T23:05:46Z)
• Who Reasons in the Large Language Models? [18.521142439429635]
  We show that reasoning capabilities in well-trained large language models are primarily attributed to the output projection module (oproj) in the Transformer's multi-head self-attention mechanism.<n>We provide both circumstantial and empirical evidence suggesting that oproj plays a central role in enabling reasoning, whereas other modules contribute more to fluent dialogue.
  arXiv  Detail & Related papers  (2025-05-27T10:26:47Z)
• Modular Machine Learning: An Indispensable Path towards New-Generation Large Language Models [33.822930522694406]
  We overview a promising learning paradigm, i.e., Modular Machine Learning (MML), as an essential approach toward new-generation large language models (LLMs)<n>We propose a unified MML framework for LLMs, which decomposes the complex structure of LLMs into three interdependent components: modular representation, modular model, and modular reasoning.<n>Ultimately, we believe the integration of the MML with LLMs has the potential to bridge the gap between statistical (deep) learning and formal (logical) reasoning.
  arXiv  Detail & Related papers  (2025-04-28T17:42:02Z)
• Configurable Foundation Models: Building LLMs from a Modular Perspective [115.63847606634268]
  A growing tendency to decompose LLMs into numerous functional modules allows for inference with part of modules and dynamic assembly of modules to tackle complex tasks. We coin the term brick to represent each functional module, designating the modularized structure as customizable foundation models. We present four brick-oriented operations: retrieval and routing, merging, updating, and growing. We find that the FFN layers follow modular patterns with functional specialization of neurons and functional neuron partitions.
  arXiv  Detail & Related papers  (2024-09-04T17:01:02Z)
• LLM Inference Unveiled: Survey and Roofline Model Insights [62.92811060490876]
  Large Language Model (LLM) inference is rapidly evolving, presenting a unique blend of opportunities and challenges. Our survey stands out from traditional literature reviews by not only summarizing the current state of research but also by introducing a framework based on roofline model. This framework identifies the bottlenecks when deploying LLMs on hardware devices and provides a clear understanding of practical problems.
  arXiv  Detail & Related papers  (2024-02-26T07:33:05Z)
• Small LLMs Are Weak Tool Learners: A Multi-LLM Agent [73.54562551341454]
  Large Language Model (LLM) agents significantly extend the capabilities of standalone LLMs. We propose a novel approach that decomposes the aforementioned capabilities into a planner, caller, and summarizer. This modular framework facilitates individual updates and the potential use of smaller LLMs for building each capability.
  arXiv  Detail & Related papers  (2024-01-14T16:17:07Z)
• If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents [81.60906807941188]
  Large language models (LLMs) are trained on a combination of natural language and formal language (code) Code translates high-level goals into executable steps, featuring standard syntax, logical consistency, abstraction, and modularity.
  arXiv  Detail & Related papers  (2024-01-01T16:51:20Z)
• Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration [83.4031923134958]
  Corex is a suite of novel general-purpose strategies that transform Large Language Models into autonomous agents. Inspired by human behaviors, Corex is constituted by diverse collaboration paradigms including Debate, Review, and Retrieve modes. We demonstrate that orchestrating multiple LLMs to work in concert yields substantially better performance compared to existing methods.
  arXiv  Detail & Related papers  (2023-09-30T07:11:39Z)
• mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality [95.76661165594884]
  mPLUG-Owl is a training paradigm that equips large language models (LLMs) with multi-modal abilities. The training paradigm involves a two-stage method for aligning image and text, which learns visual knowledge with the assistance of LLM. Experimental results show that our model outperforms existing multi-modal models.
  arXiv  Detail & Related papers  (2023-04-27T13:27:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.