Jacobian Scopes: token-level causal attributions in LLMs

• URL: http://arxiv.org/abs/2601.16407v1
• Date: Fri, 23 Jan 2026 02:36:38 GMT
• Title: Jacobian Scopes: token-level causal attributions in LLMs
• Authors: Toni J. B. Liu, Baran Zadeoğlu, Nicolas Boullé, Raphaël Sarfati, Christopher J. Earls,
• Abstract summary: Jacobian Scopes is a suite of gradient-based, token-level causal attribution methods for interpreting large language models.<n>Our proposed methods shed light on recently debated mechanisms underlying in-context time-series forecasting.
• Score: 10.472535430038759
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) make next-token predictions based on clues present in their context, such as semantic descriptions and in-context examples. Yet, elucidating which prior tokens most strongly influence a given prediction remains challenging due to the proliferation of layers and attention heads in modern architectures. We propose Jacobian Scopes, a suite of gradient-based, token-level causal attribution methods for interpreting LLM predictions. By analyzing the linearized relations of final hidden state with respect to inputs, Jacobian Scopes quantify how input tokens influence a model's prediction. We introduce three variants - Semantic, Fisher, and Temperature Scopes - which respectively target sensitivity of specific logits, the full predictive distribution, and model confidence (inverse temperature). Through case studies spanning instruction understanding, translation and in-context learning (ICL), we uncover interesting findings, such as when Jacobian Scopes point to implicit political biases. We believe that our proposed methods also shed light on recently debated mechanisms underlying in-context time-series forecasting. Our code and interactive demonstrations are publicly available at https://github.com/AntonioLiu97/JacobianScopes.

Related papers

• Farther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs [100.02824137397464]
  We investigate how Large Language Models adapt their internal representations when encountering inputs of increasing difficulty.<n>We reveal a consistent and quantifiable phenomenon: as task difficulty increases, the last hidden states of LLMs become substantially sparser.<n>This sparsity--difficulty relation is observable across diverse models and domains.
  arXiv  Detail & Related papers  (2026-03-03T18:48:15Z)
• Framework for Machine Evaluation of Reasoning Completeness in Large Language Models For Classification Tasks [0.0]
  This paper introduces RACE-Reasoning Alignment for Completeness of Explanations.<n>We analyze four widely used text classification datasets-WIKI ONTOLOGY, AG NEWS, IMDB, and GOEMOTIONS.<n>We show that correct predictions exhibit higher coverage of supporting features, while incorrect predictions are associated with elevated coverage of contradicting features.
  arXiv  Detail & Related papers  (2025-10-23T20:22:22Z)
• Context-level Language Modeling by Learning Predictive Context Embeddings [79.00607069677393]
  We introduce textbfContextLM, a framework that augments standard pretraining with an inherent textbfnext-context prediction objective.<n>This mechanism trains the model to learn predictive representations of multi-token contexts, leveraging error signals derived from future token chunks.<n>Experiments on the GPT2 and Pythia model families, scaled up to $1.5$B parameters, show that ContextLM delivers consistent improvements in both perplexity and downstream task performance.
  arXiv  Detail & Related papers  (2025-10-23T07:09:45Z)
• Towards Auto-Regressive Next-Token Prediction: In-Context Learning Emerges from Generalization [26.9153121765435]
  Large language models (LLMs) have demonstrated remarkable in-context learning abilities.<n>This paper investigates how ICL emerges and the impact of pre-training phase on ICL.<n>Our theory is supported by experiments on numerical linear dynamic systems, synthetic GINC and real-world language datasets.
  arXiv  Detail & Related papers  (2025-02-24T10:26:29Z)
• Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models [0.0]
  This research aims to unravel how large language models (LLMs) iteratively refine token predictions through internal processing.<n>We focused on how LLMs access and utilize information from input contexts, and how positioning of relevant information affects the model's token prediction refinement process.
  arXiv  Detail & Related papers  (2025-01-25T03:34:15Z)
• A Law of Next-Token Prediction in Large Language Models [26.240524947579118]
  Large language models (LLMs) have been widely employed across various application domains.<n>We introduce a precise and quantitative law that governs the learning of contextualized token embeddings.<n>Our findings reveal that each layer contributes equally to enhancing prediction accuracy.
  arXiv  Detail & Related papers  (2024-08-24T02:48:40Z)
• Uncertainty Quantification for In-Context Learning of Large Language Models [52.891205009620364]
  In-context learning has emerged as a groundbreaking ability of Large Language Models (LLMs) We propose a novel formulation and corresponding estimation method to quantify both types of uncertainties. The proposed method offers an unsupervised way to understand the prediction of in-context learning in a plug-and-play fashion.
  arXiv  Detail & Related papers  (2024-02-15T18:46:24Z)
• Explanation-aware Soft Ensemble Empowers Large Language Model In-context Learning [50.00090601424348]
  Large language models (LLMs) have shown remarkable capabilities in various natural language understanding tasks. We propose EASE, an Explanation-Aware Soft Ensemble framework to empower in-context learning with LLMs.
  arXiv  Detail & Related papers  (2023-11-13T06:13:38Z)
• Evaluating and Explaining Large Language Models for Code Using Syntactic Structures [74.93762031957883]
  This paper introduces ASTxplainer, an explainability method specific to Large Language Models for code. At its core, ASTxplainer provides an automated method for aligning token predictions with AST nodes. We perform an empirical evaluation on 12 popular LLMs for code using a curated dataset of the most popular GitHub projects.
  arXiv  Detail & Related papers  (2023-08-07T18:50:57Z)
• CUE: An Uncertainty Interpretation Framework for Text Classifiers Built on Pre-Trained Language Models [28.750894873827068]
  We propose a novel framework, called CUE, which aims to interpret uncertainties inherent in the predictions of PLM-based models. By comparing the difference in predictive uncertainty between the perturbed and the original text representations, we are able to identify the latent dimensions responsible for uncertainty.
  arXiv  Detail & Related papers  (2023-06-06T11:37:46Z)
• Understanding Emergent In-Context Learning from a Kernel Regression Perspective [55.95455089638838]
  Large language models (LLMs) have initiated a paradigm shift in transfer learning.<n>This paper proposes a kernel-regression perspective of understanding LLMs' ICL bahaviors when faced with in-context examples.<n>We find that during ICL, the attention and hidden features in LLMs match the behaviors of a kernel regression.
  arXiv  Detail & Related papers  (2023-05-22T06:45:02Z)

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.