mlsanityData to 7 Oct 2026

The Weighted M"obius Score: A Unified Framework for Feature Attribution

arXiv 2305.09204 ↗First posted 16 May 2023cs.LG cs.AI cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

Feature attribution aims to explain the reasoning behind a black-box model's prediction by identifying the impact of each feature on the prediction. Recent work has extended feature attribution to interactions between multiple features. However, the lack of a unified framework has led to a proliferation of methods that are often not directly comparable. This paper introduces a parameterized attribution framework -- the Weighted M"obius Score -- and (i) shows that many different attribution methods for both individual features and feature interactions are special cases and (ii) identifies some new methods. By studying the vector space of attribution methods, our framework utilizes standard linear algebra tools and provides interpretations in various fields, including cooperative game theory and causal mediation analysis. We empirically demonstrate the framework's versatility and effectiveness by applying these attribution methods to feature interactions in sentiment analysis and chain-of-thought prompting.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 19 of its 34 references that are in the map. First posted on arXiv 16 May 2023.

Builds on

19 of 34 references.

References · 19

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  5. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  6. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  7. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  8. 2013Direct and Indirect Effectscited by 276
  9. 2015Explaining NonLinear Classification Decisions with Deep Taylor Decompositioncited by 248
  10. 2022Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matterscited by 221
  11. 2020Explaining by Removing: A Unified Framework for Model Explanationcited by 218
  12. 2019The Shapley Taylor Interaction Indexcited by 143
7 more
  1. 2021Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Modelscited by 127
  2. 2020Explaining Explanations: Axiomatic Feature Interactions for Deep Networkscited by 103
  3. 2017Detecting Statistical Interactions from Neural Network Weightscited by 80
  4. 2020How does this interaction affect me? Interpretable attribution for feature interactionscited by 73
  5. 2023Understanding and Unifying Fourteen Attribution Methods with Taylor Interactionscited by 11
  6. 2021Axiomatic Explanations for Visual Search, Retrieval, and Similarity Learningcited by 6
  7. 2022Testing Pre-trained Language Models' Understanding of Distributivity via Causal Mediation Analysiscited by 3

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Feature Interactions Reveal Linguistic Structure in Language Modelscited by 8

Similar, not cited

Close in wording, no citation either way

  1. 2026The Metagame of Interpretability and Meta-Attributions
  2. 2025Explanation Bias is a Product: Revealing the Hidden Lexical and Position Preferences in Post-Hoc Feature Attribution
  3. 2024Explaining Time Series Classification Predictions via Causal Attributions
  4. 2024Do LLMs Think Fast and Slow? A Causal Study on Sentiment Analysis
  5. 2026Assessing Alignment and Stability of Feature Importance Explanations via Weight of Evidence
  6. 2023Incorporating Attribution Importance for Improving Faithfulness Metrics
  7. 2025Explaining the Reasoning of Large Language Models Using Attribution Graphs
  8. 2024RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals