Cover Image

Jacobian Scopes: token-level causal attributions in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Toni J. B., Zadeoğlu, Baran, Boullé, Nicolas, Sarfati, Raphaël, Earls, Christopher J.
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LLMs learn governing principles of dynamical systems, revealing an in-context neural scaling law
by: Liu, Toni J. B., et al.
Published: (2024)

Density estimation with LLMs: a geometric investigation of in-context learning trajectories
by: Liu, Toni J. B., et al.
Published: (2024)

What's in a prompt? Language models encode literary style in prompt embeddings
by: Sarfati, Raphaël, et al.
Published: (2025)

Lines of Thought in Large Language Models
by: Sarfati, Raphaël, et al.
Published: (2024)

Text-Trained LLMs Can Zero-Shot Extrapolate PDE Dynamics, Revealing a Three-Stage In-Context Learning Mechanism
by: Bao, Jiajun, et al.
Published: (2025)

Fine-Tuning Discrete Diffusion Models with Policy Gradient Methods
by: Zekri, Oussama, et al.
Published: (2025)

AnomaLLMy -- Detecting anomalous tokens in black-box LLMs through low-confidence single-token predictions
by: Witold, Waligóra
Published: (2024)

Prediction hubs are context-informed frequent tokens in LLMs
by: Nielsen, Beatrix M. G., et al.
Published: (2025)

Towards Nepali-language LLMs: Efficient GPT training with a Nepali BPE tokenizer
by: Shrestha, Adarsha, et al.
Published: (2025)

Looking beyond the next token
by: Thankaraj, Abitha, et al.
Published: (2025)

Shaping capabilities with token-level data filtering
by: Rathi, Neil, et al.
Published: (2026)

Generalized Discrete Diffusion from Snapshots
by: Zekri, Oussama, et al.
Published: (2026)

You only need 4 extra tokens: Synergistic Test-time Adaptation for LLMs
by: Xu, Yijie, et al.
Published: (2025)

Argumentation for Explainable and Globally Contestable Decision Support with LLMs
by: Dejl, Adam, et al.
Published: (2026)

The pitfalls of next-token prediction
by: Bachmann, Gregor, et al.
Published: (2024)

On the token distance modeling ability of higher RoPE attention dimension
by: Hong, Xiangyu, et al.
Published: (2024)

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
by: Gemini Team, et al.
Published: (2024)

Large Language Models as Markov Chains
by: Zekri, Oussama, et al.
Published: (2024)

CultureScope: A Dimensional Lens for Probing Cultural Understanding in LLMs
by: Zhang, Jinghao, et al.
Published: (2025)

Scaled and Inter-token Relation Enhanced Transformer for Sample-restricted Residential NILM
by: Rahman, Minhajur, et al.
Published: (2024)

Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought
by: Boppana, Siddharth, et al.
Published: (2026)

Enabling Scalable Evaluation of Bias Patterns in Medical LLMs
by: Fayyaz, Hamed, et al.
Published: (2024)

SubTokenTest: A Practical Benchmark for Real-World Sub-token Understanding
by: Hou, Shuyang, et al.
Published: (2026)

DeepMLF: Multimodal language model with learnable tokens for deep fusion in sentiment analysis
by: Georgiou, Efthymios, et al.
Published: (2025)

On the attribution of confidence to large language models
by: Keeling, Geoff, et al.
Published: (2024)

Not all tokens are created equal: Perplexity Attention Weighted Networks for AI generated text detection
by: Miralles-González, Pablo, et al.
Published: (2025)

Scaling Transformer to 1M tokens and beyond with RMT
by: Bulatov, Aydar, et al.
Published: (2023)

Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space
by: Bigelow, Eric, et al.
Published: (2026)

Interpretable Next-token Prediction via the Generalized Induction Head
by: Kim, Eunji, et al.
Published: (2024)

Language models are better than humans at next-token prediction
by: Shlegeris, Buck, et al.
Published: (2022)

LLMs left, right, and center: Assessing GPT's capabilities to label political bias from web domains
by: Hernandes, Raphael, et al.
Published: (2024)

Essential-Web v1.0: 24T tokens of organized web data
by: AI, Essential, et al.
Published: (2025)

Mixture-of-Experts as Soft Clustering: A Dual Jacobian-PCA Spectral Geometry Perspective
by: Liu, Feilong
Published: (2026)

Exploring the Potential for Large Language Models to Demonstrate Rational Probabilistic Beliefs
by: Freedman, Gabriel, et al.
Published: (2025)

Generative Adversarial Reviews: When LLMs Become the Critic
by: Bougie, Nicolas, et al.
Published: (2024)

Unused information in token probability distribution of generative LLM: improving LLM reading comprehension through calculation of expected values
by: Zawistowski, Krystian
Published: (2024)

Automatic Posology Structuration : What role for LLMs?
by: Bobkova, Natalia, et al.
Published: (2025)

COMPACT: Common-token Optimized Model Pruning Across Channels and Tokens
by: Kwek, Eugene, et al.
Published: (2025)

Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations
by: Farnik, Lucy, et al.
Published: (2025)

All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling
by: Marconato, Emanuele, et al.
Published: (2024)