English
Related papers

Related papers: Helpful or Harmful Data? Fine-tuning-free Shapley …

200 papers

Despite the popularity of Shapley Values in explaining neural text classification models, computing them is prohibitive for large pretrained models due to a large number of model evaluations. In practice, Shapley Values are often estimated…

Computation and Language · Computer Science 2023-06-01 Chenghao Yang , Fan Yin , He He , Kai-Wei Chang , Xiaofei Ma , Bing Xiang

The SHAP (short for Shapley additive explanation) framework has become an essential tool for attributing importance to variables in predictive tasks. In model-agnostic settings, SHAP uses the concept of Shapley values from cooperative game…

Machine Learning · Statistics 2026-02-12 Justin Whitehouse , Ayush Sawarni , Vasilis Syrgkanis

Numerous works propose post-hoc, model-agnostic explanations for learning to rank, focusing on ordering entities by their relevance to a query through feature attribution methods. However, these attributions often weakly correlate or…

Information Retrieval · Computer Science 2025-02-25 Tanya Chowdhury , Yair Zick , James Allan

Large language models (LLMs) demonstrate strong capabilities in in-context learning, but verifying the correctness of their generated responses remains a challenge. Prior work has explored attribution at the sentence level, but these…

Computation and Language · Computer Science 2025-07-10 Yingtai Xiao , Yuqing Zhu , Sirat Samyoun , Wanrong Zhang , Jiachen T. Wang , Jian Du

Shapley values are model-agnostic methods for explaining model predictions. Many commonly used methods of computing Shapley values, known as off-manifold methods, rely on model evaluations on out-of-distribution input samples. Consequently,…

Machine Learning · Statistics 2023-02-28 Muhammad Faaiz Taufiq , Patrick Blöbaum , Lenon Minorics

We consider the performance of a least-squares regression model, as judged by out-of-sample $R^2$. Shapley values give a fair attribution of the performance of a model to its input features, taking into account interdependencies between…

Computation · Statistics 2024-09-11 Logan Bell , Nikhil Devanathan , Stephen Boyd

Computing the importance of features in supervised classification tasks is critical for model interpretability. Shapley values are a widely used approach for explaining model predictions, but require direct access to the underlying model,…

Machine Learning · Computer Science 2026-05-18 Joao Fonseca , Julia Stoyanovich

When using machine learning techniques in decision-making processes, the interpretability of the models is important. In the present paper, we adopted the Shapley additive explanation (SHAP), which is based on fair profit allocation among…

Machine Learning · Computer Science 2022-03-03 Yasunobu Nohara , Koutarou Matsumoto , Hidehisa Soejima , Naoki Nakashima

Data Shapley has recently been proposed as a principled framework to quantify the contribution of individual datum in machine learning. It can effectively identify helpful or harmful data points for a learning algorithm. In this paper, we…

Machine Learning · Computer Science 2022-01-20 Yongchan Kwon , James Zou

Widespread adoption of deep models has motivated a pressing need for approaches to interpret network outputs and to facilitate model debugging. Instance attribution methods constitute one means of accomplishing these goals by retrieving…

Computation and Language · Computer Science 2021-04-12 Pouya Pezeshkpour , Sarthak Jain , Byron C. Wallace , Sameer Singh

Recent research on model interpretability in natural language processing extensively uses feature scoring methods for identifying which parts of the input are the most important for a model to make a prediction (i.e. explanation or…

Computation and Language · Computer Science 2021-12-07 George Chrysostomou , Nikolaos Aletras

Interpretable machine learning has been focusing on explaining final models that optimize performance. The current state-of-the-art is the Shapley additive explanations (SHAP) that locally explains variable impact on individual predictions,…

Originally introduced in cooperative game theory, Shapley values have become a very popular tool to explain machine learning predictions. Based on Shapley's fairness axioms, every input (feature component) gets a credit how it contributes…

Machine Learning · Statistics 2025-08-19 Michael Mayer , Mario V. Wüthrich

To harness the power of large language models in safety-critical domains, we need to ensure the explainability of their predictions. However, despite the significant attention to model interpretability, there remains an unexplored domain in…

Computation and Language · Computer Science 2024-06-04 Kenza Amara , Rita Sevastjanova , Mennatallah El-Assady

Shapley values have emerged as a critical tool for explaining which features impact the decisions made by machine learning models. However, computing exact Shapley values is difficult, generally requiring an exponential (in the feature…

Data attribution seeks to trace model behavior back to the training examples that shaped it, enabling debugging, auditing, and data valuation at scale. Classical influence-function methods offer a principled foundation but remain…

Machine Learning · Computer Science 2025-11-26 Sibo Ma , Julian Nyarko

Feature attribution analysis is critical for interpreting machine learning models and supporting reliable data-driven decisions. However, feature attribution measures often exhibit stochastic variation: different train--test splits, random…

Machine Learning · Statistics 2026-05-15 Lanxin Xiang , Liang Shi , Youhui Ye , Boyu Jiang , Dawei Zhou , Feng Guo

We discuss promising recent contributions on quantifying feature relevance using Shapley values, where we observed some confusion on which probability distribution is the right one for dropped features. We argue that the confusion is based…

Machine Learning · Statistics 2019-11-28 Dominik Janzing , Lenon Minorics , Patrick Blöbaum

Shapley values are widely used for model-agnostic data valuation and feature attribution, yet they implicitly assume contributors are interchangeable. This can be problematic when contributors are dependent (e.g., reused/augmented data or…

Machine Learning · Computer Science 2026-02-11 Kiljae Lee , Ziqi Liu , Weijing Tang , Yuan Zhang

Large language models (LLMs) excel on new tasks without additional training, simply by providing natural language prompts that demonstrate how the task should be performed. Prompt ensemble methods comprehensively harness the knowledge of…

Computation and Language · Computer Science 2024-12-17 Hanxi Liu , Xiaokai Mao , Haocheng Xia , Jian Lou , Jinfei Liu , Kui Ren