Image de couverture de livre

SPEX: Scaling Feature Interaction Explanations for LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kang, Justin Singh, Butler, Landon, Agarwal, Abhineet, Erginbas, Yigit Efe, Pedarsani, Ramtin, Ramchandran, Kannan, Yu, Bin
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence Computation and Language Information Theory
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs
par: Butler, Landon, et autres
Publié: (2025)

Learning to Understand: Identifying Interactions via the Möbius Transform
par: Kang, Justin S., et autres
Publié: (2024)

The Fair Value of Data Under Heterogeneous Privacy Constraints in Federated Learning
par: Kang, Justin, et autres
Publié: (2023)

Online Assortment and Price Optimization Under Contextual Choice Models
par: Erginbas, Yigit Efe, et autres
Publié: (2025)

Adaptive Sparse Möbius Transforms for Learning Polynomials
par: Erginbas, Yigit Efe, et autres
Publié: (2026)

Transformers on Markov Data: Constant Depth Suffices
par: Rajaraman, Nived, et autres
Publié: (2024)

Quantifying Positional Biases in Text Embedding Models
par: Lee, Reagan J., et autres
Publié: (2024)

Statistical Complexity and Optimal Algorithms for Non-linear Ridge Bandits
par: Rajaraman, Nived, et autres
Publié: (2023)

Towards Optimal Statistical Watermarking
par: Huang, Baihe, et autres
Publié: (2023)

An Odd Estimator for Shapley Values
par: Fumagalli, Fabian, et autres
Publié: (2026)

Toward a Theory of Tokenization in LLMs
par: Rajaraman, Nived, et autres
Publié: (2024)

SHAP zero Explains Biological Sequence Models with Near-zero Marginal Cost for Future Queries
par: Tsui, Darin, et autres
Publié: (2024)

Fundamental Scaling Laws of Covert Communication in the Presence of Block Fading
par: Ramtin, Amir Reza, et autres
Publié: (2024)

Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders
par: Kuznetsov, Kristian, et autres
Publié: (2025)

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

The Rough Topology for Numerical Data
par: Yiğit, Uğur
Publié: (2022)

From Markov to Laplace: How Mamba In-Context Learns Markov Chains
par: Bondaschi, Marco, et autres
Publié: (2025)

Efficient Learned Data Compression via Dual-Stream Feature Decoupling
par: Ma, Huidong, et autres
Publié: (2026)

From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning
par: Shani, Chen, et autres
Publié: (2025)

What Makes the Preferred Thinking Direction for LLMs in Multiple-choice Questions?
par: Zhang, Yizhe, et autres
Publié: (2025)

Multi-Bin Batching for Increasing LLM Inference Throughput
par: Guldogan, Ozgur, et autres
Publié: (2024)

Optimal Multi-bit Generative Watermarking Schemes Under Worst-Case False-Alarm Constraints
par: Huang, Yu-Shin, et autres
Publié: (2026)

Theoretical guarantees on the best-of-n alignment policy
par: Beirami, Ahmad, et autres
Publié: (2024)

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

MultiTok: Variable-Length Tokenization for Efficient LLMs Adapted from LZW Compression
par: Elias, Noel, et autres
Publié: (2024)

Improving Robustness of Tabular Retrieval via Representational Stability
par: Bhandari, Kushal Raj, et autres
Publié: (2026)

Speculative Decoding Scaling Laws (SDSL): Throughput Optimization Made Simple
par: Bozorgkhoo, Amirhossein, et autres
Publié: (2026)

AgentSPEX: An Agent SPecification and EXecution Language
par: Wang, Pengcheng, et autres
Publié: (2026)

Taming the Heavy Tail: Age-Optimal Preemption
par: Li, Aimin, et autres
Publié: (2026)

Quickest Change Detection in Discrete-Time in Presence of a Covert Adversary
par: Ramtin, Amir Reza, et autres
Publié: (2026)

Quickest Change Detection in Continuous-Time in Presence of a Covert Adversary
par: Ramtin, Amir Reza, et autres
Publié: (2025)

Balancing Information Accuracy and Response Timeliness in Networked LLMs
par: Turkmen, Yigit, et autres
Publié: (2025)

Hybrid STAR-RIS Enabled Integrated Sensing and Communication
par: Yigit, Zehra, et autres
Publié: (2024)

Surprisal and Metaphor Novelty Judgments: Moderate Correlations and Divergent Scaling Effects Revealed by Corpus-Based and Synthetic Datasets
par: Momen, Omar, et autres
Publié: (2026)

ED-Copilot: Reduce Emergency Department Wait Time with Language Model Diagnostic Assistance
par: Sun, Liwen, et autres
Publié: (2024)

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

MEG-RAG: Quantifying Multi-modal Evidence Grounding for Evidence Selection in RAG
par: Wang, Xihang, et autres
Publié: (2026)

The Stepwise Informativeness Assumption: Why are Entropy Dynamics and Reasoning Correlated in LLMs?
par: Català, Mar Gonzàlez I, et autres
Publié: (2026)

Inverse Reinforcement Learning by Estimating Expertise of Demonstrators
par: Beliaev, Mark, et autres
Publié: (2024)

AI-assisted Protocol Information Extraction For Improved Accuracy and Efficiency in Clinical Trial Workflows
par: Babaeipour, Ramtin, et autres
Publié: (2026)