LogitLens4LLMs: Extending Logit Lens Analysis to Modern Large Language Models

• URL: http://arxiv.org/abs/2503.11667v1
• Date: Mon, 24 Feb 2025 03:37:44 GMT
• Title: LogitLens4LLMs: Extending Logit Lens Analysis to Modern Large Language Models
• Authors: Zhenyu Wang,
• Abstract summary: LogitLens4LLMs is a toolkit that extends the Logit Lens technique to modern large language models.<n>Our work overcomes the limitations of existing implementations, enabling the technique to be applied to state-of-the-art architectures.
• Score: 6.002736042809241
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper introduces LogitLens4LLMs, a toolkit that extends the Logit Lens technique to modern large language models. While Logit Lens has been a crucial method for understanding internal representations of language models, it was previously limited to earlier model architectures. Our work overcomes the limitations of existing implementations, enabling the technique to be applied to state-of-the-art architectures (such as Qwen-2.5 and Llama-3.1) while automating key analytical workflows. By developing component-specific hooks to capture both attention mechanisms and MLP outputs, our implementation achieves full compatibility with the HuggingFace transformer library while maintaining low inference overhead. The toolkit provides both interactive exploration and batch processing capabilities, supporting large-scale layer-wise analyses. Through open-sourcing our implementation, we aim to facilitate deeper investigations into the internal mechanisms of large-scale language models. The toolkit is openly available at https://github.com/zhenyu-02/LogitLens4LLMs.

Related papers

• Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger [49.81945268343162]
  We propose MeCo, an adaptive decision-making strategy for external tool use.<n>MeCo captures high-level cognitive signals in the representation space, guiding when to invoke tools.<n>Our experiments show that MeCo accurately detects LLMs' internal cognitive signals and significantly improves tool-use decision-making.
  arXiv  Detail & Related papers  (2025-02-18T15:45:01Z)
• Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agents [56.822238860147024]
  Augmenting large language models with external tools has emerged as a promising approach to extend their utility. Previous methods manually parse tool documentation and create in-context demonstrations, transforming tools into structured formats for LLMs to use in their step-by-step reasoning. We propose AutoTools, a framework that enables LLMs to automate the tool-use workflow.
  arXiv  Detail & Related papers  (2024-05-26T11:40:58Z)
• Towards Completeness-Oriented Tool Retrieval for Large Language Models [60.733557487886635]
  Real-world systems often incorporate a wide array of tools, making it impractical to input all tools into Large Language Models. Existing tool retrieval methods primarily focus on semantic matching between user queries and tool descriptions. We propose a novel modelagnostic COllaborative Learning-based Tool Retrieval approach, COLT, which captures not only the semantic similarities between user queries and tool descriptions but also takes into account the collaborative information of tools.
  arXiv  Detail & Related papers  (2024-05-25T06:41:23Z)
• LVLM-Interpret: An Interpretability Tool for Large Vision-Language Models [50.259006481656094]
  We present a novel interactive application aimed towards understanding the internal mechanisms of large vision-language models. Our interface is designed to enhance the interpretability of the image patches, which are instrumental in generating an answer. We present a case study of how our application can aid in understanding failure mechanisms in a popular large multi-modal model: LLaVA.
  arXiv  Detail & Related papers  (2024-04-03T23:57:34Z)
• CMULAB: An Open-Source Framework for Training and Deployment of Natural Language Processing Models [59.91221728187576]
  This paper introduces the CMU Linguistic Linguistic Backend, an open-source framework that simplifies model deployment and continuous human-in-the-loop fine-tuning of NLP models. CMULAB enables users to leverage the power of multilingual models to quickly adapt and extend existing tools for speech recognition, OCR, translation, and syntactic analysis to new languages.
  arXiv  Detail & Related papers  (2024-04-03T02:21:46Z)
• DeepDecipher: Accessing and Investigating Neuron Activation in Large Language Models [2.992602379681373]
  DeepDecipher is an API and interface for probing neurons in transformer models' layers. This paper outlines DeepDecipher's design and capabilities. We demonstrate how to analyze neurons, compare models, and gain insights into model behavior.
  arXiv  Detail & Related papers  (2023-10-03T08:15:20Z)
• Augmented Language Models: a Survey [55.965967655575454]
  This survey reviews works in which language models (LMs) are augmented with reasoning skills and the ability to use tools. We refer to them as Augmented Language Models (ALMs) The missing token objective allows ALMs to learn to reason, use tools, and even act, while still performing standard natural language tasks.
  arXiv  Detail & Related papers  (2023-02-15T18:25:52Z)
• The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models [17.423179212411263]
  Language Interpretability Tool (LIT) is an open-source platform for visualization and understanding of NLP models. LIT integrates local explanations, aggregate analysis, and counterfactual generation into a streamlined, browser-based interface.
  arXiv  Detail & Related papers  (2020-08-12T06:07:44Z)

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.