# Suboptimal Shapley Value Explanations

arXiv: https://arxiv.org/abs/2502.12209 · HTML: https://mlsanity.com/paper/2502.12209/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 29 references that are in the map.
- First posted on arXiv 17 Feb 2025.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [Estimating Training Data Influence by Tracing Gradient Descent](https://mlsanity.com/paper/2002.08484/) (2020)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces](https://mlsanity.com/paper/1805.10190/) (2018)
- [Problems with Shapley-value-based explanations as feature importance measures](https://mlsanity.com/paper/2002.11097/) (2020)
- [Feature relevance quantification in explainable AI: A causal problem](https://mlsanity.com/paper/1910.13413/) (2019)
- [L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data](https://mlsanity.com/paper/1808.02610/) (2018)
- [ChatGPT-4 Outperforms Experts and Crowd Workers in Annotating Political Twitter Messages with Zero-Shot Learning](https://mlsanity.com/paper/2304.06588/) (2023)
- [Shapley explainability on the data manifold](https://mlsanity.com/paper/2006.01272/) (2020)
- [Unrestricted Permutation forces Extrapolation: Variable Importance Requires at least One More Model, or There Is No Free Variable Importance](https://mlsanity.com/paper/1905.03151/) (2019)
- [WeightedSHAP: analyzing and improving Shapley based feature attributions](https://mlsanity.com/paper/2209.13429/) (2022)
- [Rational Shapley Values](https://mlsanity.com/paper/2106.10191/) (2021)
- [Mind the Gap! Bridging Explainable Artificial Intelligence and Human Understanding with Luhmann's Functional Theory of Communication](https://mlsanity.com/paper/2302.03460/) (2023)

## Abstract (arXiv)

Deep Neural Networks (DNNs) have demonstrated strong capacity in supporting a wide variety of applications. Shapley value has emerged as a prominent tool to analyze feature importance to help people understand the inference process of deep neural models. Computing Shapley value function requires choosing a baseline to represent feature's missingness. However, existing random and conditional baselines could negatively influence the explanation. In this paper, by analyzing the suboptimality of different baselines, we identify the problematic baseline where the asymmetric interaction between bmx'i (the replacement of the faithful influential feature) and other features has significant directional bias toward the model's output, and conclude that p(y|bmx'i) = p(y) potentially minimizes the asymmetric interaction involving bmx'i. We further generalize the uninformativeness of bmx'i toward the label space L to avoid estimating p(y) and design a simple uncertainty-based reweighting mechanism to accelerate the computation process. We conduct experiments on various NLP tasks and our quantitative analysis demonstrates the effectiveness of the proposed uncertainty-based reweighting mechanism. Furthermore, by measuring the consistency of explanations generated by explainable methods and human, we highlight the disparity between model inference and human understanding.