Imagen de Portada

SPEX: Scaling Feature Interaction Explanations for LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kang, Justin Singh, Butler, Landon, Agarwal, Abhineet, Erginbas, Yigit Efe, Pedarsani, Ramtin, Ramchandran, Kannan, Yu, Bin
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence Computation and Language Information Theory
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs
por: Butler, Landon, et al.
Publicado: (2025)

Learning to Understand: Identifying Interactions via the Möbius Transform
por: Kang, Justin S., et al.
Publicado: (2024)

The Fair Value of Data Under Heterogeneous Privacy Constraints in Federated Learning
por: Kang, Justin, et al.
Publicado: (2023)

Online Assortment and Price Optimization Under Contextual Choice Models
por: Erginbas, Yigit Efe, et al.
Publicado: (2025)

Adaptive Sparse Möbius Transforms for Learning Polynomials
por: Erginbas, Yigit Efe, et al.
Publicado: (2026)

Transformers on Markov Data: Constant Depth Suffices
por: Rajaraman, Nived, et al.
Publicado: (2024)

Quantifying Positional Biases in Text Embedding Models
por: Lee, Reagan J., et al.
Publicado: (2024)

Statistical Complexity and Optimal Algorithms for Non-linear Ridge Bandits
por: Rajaraman, Nived, et al.
Publicado: (2023)

Towards Optimal Statistical Watermarking
por: Huang, Baihe, et al.
Publicado: (2023)

An Odd Estimator for Shapley Values
por: Fumagalli, Fabian, et al.
Publicado: (2026)

Toward a Theory of Tokenization in LLMs
por: Rajaraman, Nived, et al.
Publicado: (2024)

SHAP zero Explains Biological Sequence Models with Near-zero Marginal Cost for Future Queries
por: Tsui, Darin, et al.
Publicado: (2024)

Fundamental Scaling Laws of Covert Communication in the Presence of Block Fading
por: Ramtin, Amir Reza, et al.
Publicado: (2024)

Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders
por: Kuznetsov, Kristian, et al.
Publicado: (2025)

HRGraph: Leveraging LLMs for HR Data Knowledge Graphs with Information Propagation-based Job Recommendation
por: Wasi, Azmine Toushik
Publicado: (2024)

The Rough Topology for Numerical Data
por: Yiğit, Uğur
Publicado: (2022)

From Markov to Laplace: How Mamba In-Context Learns Markov Chains
por: Bondaschi, Marco, et al.
Publicado: (2025)

Efficient Learned Data Compression via Dual-Stream Feature Decoupling
por: Ma, Huidong, et al.
Publicado: (2026)

From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning
por: Shani, Chen, et al.
Publicado: (2025)

What Makes the Preferred Thinking Direction for LLMs in Multiple-choice Questions?
por: Zhang, Yizhe, et al.
Publicado: (2025)

Multi-Bin Batching for Increasing LLM Inference Throughput
por: Guldogan, Ozgur, et al.
Publicado: (2024)

Optimal Multi-bit Generative Watermarking Schemes Under Worst-Case False-Alarm Constraints
por: Huang, Yu-Shin, et al.
Publicado: (2026)

Theoretical guarantees on the best-of-n alignment policy
por: Beirami, Ahmad, et al.
Publicado: (2024)

Filtering Beats Fine Tuning: A Bayesian Kalman View of In Context Learning in LLMs
por: Kiruluta, Andrew
Publicado: (2026)

MultiTok: Variable-Length Tokenization for Efficient LLMs Adapted from LZW Compression
por: Elias, Noel, et al.
Publicado: (2024)

Improving Robustness of Tabular Retrieval via Representational Stability
por: Bhandari, Kushal Raj, et al.
Publicado: (2026)

Speculative Decoding Scaling Laws (SDSL): Throughput Optimization Made Simple
por: Bozorgkhoo, Amirhossein, et al.
Publicado: (2026)

AgentSPEX: An Agent SPecification and EXecution Language
por: Wang, Pengcheng, et al.
Publicado: (2026)

Taming the Heavy Tail: Age-Optimal Preemption
por: Li, Aimin, et al.
Publicado: (2026)

Quickest Change Detection in Discrete-Time in Presence of a Covert Adversary
por: Ramtin, Amir Reza, et al.
Publicado: (2026)

Quickest Change Detection in Continuous-Time in Presence of a Covert Adversary
por: Ramtin, Amir Reza, et al.
Publicado: (2025)

Balancing Information Accuracy and Response Timeliness in Networked LLMs
por: Turkmen, Yigit, et al.
Publicado: (2025)

Hybrid STAR-RIS Enabled Integrated Sensing and Communication
por: Yigit, Zehra, et al.
Publicado: (2024)

Surprisal and Metaphor Novelty Judgments: Moderate Correlations and Divergent Scaling Effects Revealed by Corpus-Based and Synthetic Datasets
por: Momen, Omar, et al.
Publicado: (2026)

ED-Copilot: Reduce Emergency Department Wait Time with Language Model Diagnostic Assistance
por: Sun, Liwen, et al.
Publicado: (2024)

Measuring Grammatical Diversity from Small Corpora: Derivational Entropy Rates, Mean Length of Utterances, and Annotation Invariance
por: Martin, Fermin Moscoso del Prado
Publicado: (2024)

MEG-RAG: Quantifying Multi-modal Evidence Grounding for Evidence Selection in RAG
por: Wang, Xihang, et al.
Publicado: (2026)

The Stepwise Informativeness Assumption: Why are Entropy Dynamics and Reasoning Correlated in LLMs?
por: Català, Mar Gonzàlez I, et al.
Publicado: (2026)

Inverse Reinforcement Learning by Estimating Expertise of Demonstrators
por: Beliaev, Mark, et al.
Publicado: (2024)

AI-assisted Protocol Information Extraction For Improved Accuracy and Efficiency in Clinical Trial Workflows
por: Babaeipour, Ramtin, et al.
Publicado: (2026)