Cover Image

Visualizing token importance for black-box language models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Rauba, Paulius, Wei, Qiyao, van der Schaar, Mihaela
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Quantifying perturbation impacts for large language models
by: Rauba, Paulius, et al.
Published: (2024)

Statistical Hypothesis Testing for Auditing Robustness in Language Models
by: Rauba, Paulius, et al.
Published: (2025)

Deep Hierarchical Learning with Nested Subspace Networks for Large Language Models
by: Rauba, Paulius, et al.
Published: (2025)

Redefining Digital Health Interfaces with Large Language Models
by: Imrie, Fergus, et al.
Published: (2023)

Tiny Autoregressive Recursive Models
by: Rauba, Paulius, et al.
Published: (2026)

No More, No Less: Least-Privilege Language Models
by: Rauba, Paulius, et al.
Published: (2026)

Self-Healing Machine Learning: A Framework for Autonomous Adaptation in Real-World Environments
by: Rauba, Paulius, et al.
Published: (2024)

Context-Aware Testing: A New Paradigm for Model Testing with Large Language Models
by: Rauba, Paulius, et al.
Published: (2024)

Language Bottleneck Models for Qualitative Knowledge State Modeling
by: Berthon, Antonin, et al.
Published: (2025)

Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities
by: Sun, Hao, et al.
Published: (2025)

Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL
by: Sun, Hao, et al.
Published: (2023)

Multi-Agent Systems Should be Treated as Principal-Agent Problems
by: Rauba, Paulius, et al.
Published: (2026)

Active Task Disambiguation with LLMs
by: Kobalczyk, Katarzyna, et al.
Published: (2025)

Do language models plan ahead for future tokens?
by: Wu, Wilson, et al.
Published: (2024)

Reusing Embeddings: Reproducible Reward Model Research in Large Language Model Alignment without GPUs
by: Sun, Hao, et al.
Published: (2025)

GameTalk: Training LLMs for Strategic Conversation
by: Vendrell, Victor Conchello, et al.
Published: (2026)

Defining Expertise: Applications to Treatment Effect Estimation
by: Hüyük, Alihan, et al.
Published: (2024)

On Error Propagation of Diffusion Models
by: Li, Yangming, et al.
Published: (2023)

Large language model-enabled automated data extraction for concrete materials informatics
by: Li, Zhanzhao, et al.
Published: (2026)

No Equations Needed: Learning System Dynamics Without Relying on Closed-Form ODEs
by: Kacprzyk, Krzysztof, et al.
Published: (2025)

Shape Arithmetic Expressions: Advancing Scientific Discovery Beyond Closed-Form Equations
by: Kacprzyk, Krzysztof, et al.
Published: (2024)

Towards Automated Knowledge Integration From Human-Interpretable Representations
by: Kobalczyk, Katarzyna, et al.
Published: (2024)

Matchmaker: Self-Improving Large Language Model Programs for Schema Matching
by: Seedat, Nabeel, et al.
Published: (2024)

Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion Models
by: Li, Yangming, et al.
Published: (2023)

Surrogate modeling for interpreting black-box LLMs in medical predictions
by: Han, Changho, et al.
Published: (2026)

Where is the signal in tokenization space?
by: Geh, Renato Lui, et al.
Published: (2024)

Why Tabular Foundation Models Should Be a Research Priority
by: van Breugel, Boris, et al.
Published: (2024)

Cascaded Language Models for Cost-effective Human-AI Decision-Making
by: Fanconi, Claudio, et al.
Published: (2025)

Event-Aware Sentiment Factors from LLM-Augmented Financial Tweets: A Transparent Framework for Interpretable Quant Trading
by: Wang, Yueyi, et al.
Published: (2025)

Not All Explanations for Deep Learning Phenomena Are Equally Valuable
by: Jeffares, Alan, et al.
Published: (2025)

Preference Learning for AI Alignment: a Causal Perspective
by: Kobalczyk, Katarzyna, et al.
Published: (2025)

Active Timepoint Selection for Learning Measure-Valued Trajectories
by: Huynh, Nicolas, et al.
Published: (2026)

Inverse-RLignment: Large Language Model Alignment from Demonstrations through Inverse Reinforcement Learning
by: Sun, Hao, et al.
Published: (2024)

Hyperparameter Trajectory Inference with Conditional Lagrangian Optimal Transport
by: Amad, Harry, et al.
Published: (2026)

DC-Check: A Data-Centric AI checklist to guide the development of reliable machine learning systems
by: Seedat, Nabeel, et al.
Published: (2022)

On multi-token prediction for efficient LLM inference
by: Mehra, Somesh, et al.
Published: (2025)

Discovery of Hidden Miscalibration Regimes
by: Kobalczyk, Katarzyna, et al.
Published: (2026)

Is Sanskrit the most token-efficient language? A quantitative study using GPT, Gemini, and SentencePiece
by: Kumar, Anshul
Published: (2026)

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

Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs
by: Singh, Aaditya K., et al.
Published: (2024)