English
Related papers

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

200 papers

Understanding why a neural network model makes certain decisions can be as important as the inference performance. Various methods have been proposed to help practitioners explain the prediction of a neural network model, of which Shapley…

Machine Learning · Computer Science 2023-10-04 Yong Zhao , Runxin He , Nicholas Kersting , Can Liu , Shubham Agrawal , Chiranjeet Chetia , Yu Gu

Attribution-based explanation techniques capture key patterns to enhance visual interpretability; however, these patterns often lack the granularity needed for insight in fine-grained tasks, particularly in cases of model misclassification,…

Artificial Intelligence · Computer Science 2025-11-12 Lintong Zhang , Kang Yin , Seong-Whan Lee

In this paper, we propose ShapTST, a framework that enables time-series transformers to efficiently generate Shapley-value-based explanations alongside predictions in a single forward pass. Shapley values are widely used to evaluate the…

Machine Learning · Computer Science 2025-01-28 Qisen Cheng , Jinming Xing , Chang Xue , Xiaoran Yang

In healthcare, making the best possible predictions with complex models (e.g., neural networks, ensembles/stacks of different models) can impact patient welfare. In order to make these complex models explainable, we present DeepSHAP for…

Machine Learning · Computer Science 2019-11-28 Hugh Chen , Scott Lundberg , Su-In Lee

In recent years, the Shapley value and SHAP explanations have emerged as one of the most dominant paradigms for providing post-hoc explanations of black-box models. Despite their well-founded theoretical properties, many recent works have…

Machine Learning · Computer Science 2025-02-21 James Enouen , Yan Liu

Recently introduced instruction-paradigm empowers non-expert users to leverage NLP resources by defining a new task in natural language. Instruction-tuned models have significantly outperformed multitask learning models (without…

Computation and Language · Computer Science 2023-02-15 Ravsehaj Singh Puri , Swaroop Mishra , Mihir Parmar , Chitta Baral

Note that a newer expanded version of this paper is now available at: arXiv:1802.03888 It is critical in many applications to understand what features are important for a model, and why individual predictions were made. For tree ensemble…

Artificial Intelligence · Computer Science 2018-02-20 Scott M. Lundberg , Su-In Lee

In many settings it is important for one to be able to understand why a model made a particular prediction. In NLP this often entails extracting snippets of an input text `responsible for' corresponding model output; when such a snippet…

Computation and Language · Computer Science 2020-05-04 Sarthak Jain , Sarah Wiegreffe , Yuval Pinter , Byron C. Wallace

Dropout has been demonstrated as a simple and effective module to not only regularize the training process of deep neural networks, but also provide the uncertainty estimation for prediction. However, the quality of uncertainty estimation…

Machine Learning · Computer Science 2021-03-09 Xinjie Fan , Shujian Zhang , Korawat Tanwisuth , Xiaoning Qian , Mingyuan Zhou

Shapley values have become a cornerstone of explainable AI, but they are computationally expensive to use, especially when features are dependent. Evaluating them requires approximating a large number of conditional expectations, either via…

Artificial Intelligence · Computer Science 2026-02-11 Lars Henry Berge Olsen , Dennis Christensen

Efficient data annotation stands as a significant bottleneck in training contemporary machine learning models. The Programmatic Weak Supervision (PWS) pipeline presents a solution by utilizing multiple weak supervision sources to…

Machine Learning · Computer Science 2025-03-18 Naiqing Guan , Nick Koudas

Many existing approaches for estimating feature importance are problematic because they ignore or hide dependencies among features. A causal graph, which encodes the relationships among input variables, can aid in assigning feature…

Machine Learning · Computer Science 2021-03-01 Jiaxuan Wang , Jenna Wiens , Scott Lundberg

For machine learning models to be reliable and trustworthy, their decisions must be interpretable. As these models find increasing use in safety-critical applications, it is important that not just the model predictions but also their…

Machine Learning · Computer Science 2023-12-19 Sandesh Kamath , Sankalp Mittal , Amit Deshpande , Vineeth N Balasubramanian

Large Language Models (LLMs) increasingly rely on Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) to align model responses with human preferences. While RLHF employs a reinforcement learning approach with…

Human-Computer Interaction · Computer Science 2025-06-05 Alex Sotiropoulos , Sulyab Thottungal Valapu , Linus Lei , Jared Coleman , Bhaskar Krishnamachari

Variable selection or importance measurement of input variables to a machine learning model has become the focus of much research. It is no longer enough to have a good model, one also must explain its decisions. This is why there are so…

Machine Learning · Computer Science 2023-08-01 Vincent Lemaire , Fabrice Clérot , Marc Boullé

Data valuation has wide use cases in machine learning, including improving data quality and creating economic incentives for data sharing. This paper studies the robustness of data valuation to noisy model performance scores. Particularly,…

Machine Learning · Computer Science 2023-12-19 Jiachen T. Wang , Ruoxi Jia

Shapley values provide model agnostic feature attributions for model outcome at a particular instance by simulating feature absence under a global population distribution. The use of a global population can lead to potentially misleading…

Machine Learning · Computer Science 2021-06-29 Sahra Ghalebikesabi , Lucile Ter-Minassian , Karla Diaz-Ordaz , Chris Holmes

Transfer learning that adapts a model trained on data-rich sources to low-resource targets has been widely applied in natural language processing (NLP). However, when training a transfer model over multiple sources, not every source is…

Computation and Language · Computer Science 2021-04-27 Md Rizwan Parvez , Kai-Wei Chang

SHAP is one of the most popular local feature-attribution methods. Given a function f and an input x, it quantifies each feature's contribution to f(x). Recently, SHAP has been increasingly used for global insights: practitioners average…

Machine Learning · Computer Science 2025-04-01 Robi Bhattacharjee , Karolin Frohnapfel , Ulrike von Luxburg

Numerous offline and model-based reinforcement learning systems incorporate world models to emulate the inherent environments. A world model is particularly important in scenarios where direct interactions with the real environment is…

Machine Learning · Computer Science 2026-01-19 Rajat Ghosh , Debojyoti Dutta