Cover Image

Interpretable Probability Estimation with LLMs via Shapley Reconstruction

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Nan, Yang, Wen, Qihao, Wang, Jiahao, He, Pengfei, Tandon, Ravi, Ge, Yong, Xu, Han
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Embedding Perturbation may Better Reflect Intermediate-Step Uncertainty in LLM Reasoning
by: Wen, Qihao, et al.
Published: (2026)

FW-Shapley: Real-time Estimation of Weighted Shapley Values
by: Panda, Pranoy, et al.
Published: (2025)

Prompt Fairness: Sub-group Disparities in LLMs
by: Zhong, Meiyu, et al.
Published: (2025)

SPLITZ: Certifiable Robustness via Split Lipschitz Randomized Smoothing
by: Zhong, Meiyu, et al.
Published: (2024)

Learning Fair Robustness via Domain Mixup
by: Zhong, Meiyu, et al.
Published: (2024)

Speeding up Speculative Decoding via Sequential Approximate Verification
by: Zhong, Meiyu, et al.
Published: (2025)

Fine-Grained Uncertainty Quantification via Collisions
by: Friedbaum, Jesse, et al.
Published: (2024)

Intrinsic Fairness-Accuracy Tradeoffs under Equalized Odds
by: Zhong, Meiyu, et al.
Published: (2024)

Inference Privacy: Properties and Mechanisms
by: Tian, Fengwei, et al.
Published: (2024)

Can Multiple Responses from an LLM Reveal the Sources of Its Uncertainty?
by: Nan, Yang, et al.
Published: (2025)

CURATE: Scaling-up Differentially Private Causal Graph Discovery
by: Bhattacharjee, Payel, et al.
Published: (2024)

Interpretable Enzyme Function Prediction via Residue-Level Detection
by: Yang, Zhao, et al.
Published: (2025)

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs
by: Yang, Zhihe, et al.
Published: (2025)

Functional Decomposition and Shapley Interactions for Interpreting Survival Models
by: Langbein, Sophie Hanna, et al.
Published: (2026)

SIM-Shapley: A Stable and Computationally Efficient Approach to Shapley Value Approximation
by: Fan, Wangxuan, et al.
Published: (2025)

Shift-Invariant Attribute Scoring for Kolmogorov-Arnold Networks via Shapley Value
by: Fan, Wangxuan, et al.
Published: (2025)

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

Stabilizing Estimates of Shapley Values with Control Variates
by: Goldwasser, Jeremy, et al.
Published: (2023)

On the Inflation of KNN-Shapley Value
by: Yang, Ziao, et al.
Published: (2024)

InstaSHAP: Interpretable Additive Models Explain Shapley Values Instantly
by: Enouen, James, et al.
Published: (2025)

MARS: Margin and Semantic-Aware Data Augmentation for Reward Modeling
by: Bhattacharjee, Payel, et al.
Published: (2026)

Trustworthy Actionable Perturbations
by: Friedbaum, Jesse, et al.
Published: (2024)

Provably Accurate Shapley Value Estimation via Leverage Score Sampling
by: Musco, Christopher, et al.
Published: (2024)

TrafPS: A Shapley-based Visual Analytics Approach to Interpret Traffic
by: Feng, Zezheng, et al.
Published: (2024)

Dynamic Shapley Computation
by: Yang, Xuan, et al.
Published: (2026)

Latency-Distortion Tradeoffs in Communicating Classification Results over Noisy Channels
by: Teku, Noel, et al.
Published: (2024)

Prediction via Shapley Value Regression
by: Alkhatib, Amr, et al.
Published: (2025)

Towards Data Valuation via Asymmetric Data Shapley
by: Zheng, Xi, et al.
Published: (2024)

Fine-Tuning Flow Matching via Maximum Likelihood Estimation of Reconstructions
by: Li, Zhaoyi, et al.
Published: (2025)

Beyond Shapley Values: Cooperative Games for the Interpretation of Machine Learning Models
by: Idrissi, Marouane Il, et al.
Published: (2025)

Energy-Based Model for Accurate Estimation of Shapley Values in Feature Attribution
by: Lu, Cheng, et al.
Published: (2024)

TokenShapley: Token Level Context Attribution with Shapley Value
by: Xiao, Yingtai, et al.
Published: (2025)

Unifying Prediction and Explanation in Time-Series Transformers via Shapley-based Pretraining
by: Cheng, Qisen, et al.
Published: (2025)

Enhance GNNs with Reliable Confidence Estimation via Adversarial Calibration Learning
by: Wang, Yilong, et al.
Published: (2025)

Disentangled Representation via Variational AutoEncoder for Continuous Treatment Effect Estimation
by: Cui, Ruijing, et al.
Published: (2024)

Refined Differentially Private Linear Regression via Extension of a Free Lunch Result
by: S, Sasmita Harini, et al.
Published: (2026)

Uncertainty Quantification of Data Shapley via Statistical Inference
by: Wu, Mengmeng, et al.
Published: (2024)

Tractable Shapley Values and Interactions via Tensor Networks
by: Heidari, Farzaneh, et al.
Published: (2025)

Shapley-Guided Neural Repair Approach via Derivative-Free Optimization
by: Sun, Xinyu, et al.
Published: (2026)

Skip the Benchmark: Generating System-Level High-Level Synthesis Data using Generative Machine Learning
by: Liao, Yuchao, et al.
Published: (2024)