Incorporating Attribution Importance for Improving Faithfulness Metrics

• URL: http://arxiv.org/abs/2305.10496v1
• Date: Wed, 17 May 2023 18:05:49 GMT
• Title: Incorporating Attribution Importance for Improving Faithfulness Metrics
• Authors: Zhixue Zhao, Nikolaos Aletras
• Abstract summary: Feature attribution methods (FAs) are popular approaches for providing insights into the model reasoning process of making predictions. We propose a simple yet effective soft erasure criterion. Our experiments show that our soft-sufficiency and soft-comprehensiveness metrics consistently prefer more faithful explanations.
• Score: 36.02988430743367
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Feature attribution methods (FAs) are popular approaches for providing insights into the model reasoning process of making predictions. The more faithful a FA is, the more accurately it reflects which parts of the input are more important for the prediction. Widely used faithfulness metrics, such as sufficiency and comprehensiveness use a hard erasure criterion, i.e. entirely removing or retaining the top most important tokens ranked by a given FA and observing the changes in predictive likelihood. However, this hard criterion ignores the importance of each individual token, treating them all equally for computing sufficiency and comprehensiveness. In this paper, we propose a simple yet effective soft erasure criterion. Instead of entirely removing or retaining tokens from the input, we randomly mask parts of the token vector representations proportionately to their FA importance. Extensive experiments across various natural language processing tasks and different FAs show that our soft-sufficiency and soft-comprehensiveness metrics consistently prefer more faithful explanations compared to hard sufficiency and comprehensiveness. Our code: https://github.com/casszhao/SoftFaith

Related papers

• The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learning [34.50562695587344]
  We adapt tools from causal sensitivity analysis to the FairML context. We analyze the sensitivity of the most common parity metrics under 3 varieties of classifier. We show that causal sensitivity analysis provides a powerful and necessary toolkit for gauging the informativeness of parity metric evaluations.
  arXiv  Detail & Related papers  (2024-10-12T17:28:49Z)
• Evaluating Human Alignment and Model Faithfulness of LLM Rationale [66.75309523854476]
  We study how well large language models (LLMs) explain their generations through rationales. We show that prompting-based methods are less "faithful" than attribution-based explanations.
  arXiv  Detail & Related papers  (2024-06-28T20:06:30Z)
• ReAGent: A Model-agnostic Feature Attribution Method for Generative Language Models [4.015810081063028]
  Feature attribution methods (FAs) are employed to derive the importance of all input features to the model predictions. It is unknown if it is faithful to use these FAs for decoder-only models on text generation. We present a model-agnostic FA for generative LMs called Recursive Attribution Generator (ReAGent)
  arXiv  Detail & Related papers  (2024-02-01T17:25:51Z)
• Faithfulness Measurable Masked Language Models [35.40666730867487]
  A common approach to explaining NLP models is to use importance measures that express which tokens are important for a prediction. One such metric is if tokens are truly important, then masking them should result in worse model performance. This work proposes an inherently faithfulness measurable model that addresses these challenges.
  arXiv  Detail & Related papers  (2023-10-11T19:00:40Z)
• Boosting Fair Classifier Generalization through Adaptive Priority Reweighing [59.801444556074394]
  A performance-promising fair algorithm with better generalizability is needed. This paper proposes a novel adaptive reweighing method to eliminate the impact of the distribution shifts between training and test data on model generalizability.
  arXiv  Detail & Related papers  (2023-09-15T13:04:55Z)
• Preserving Knowledge Invariance: Rethinking Robustness Evaluation of Open Information Extraction [50.62245481416744]
  We present the first benchmark that simulates the evaluation of open information extraction models in the real world. We design and annotate a large-scale testbed in which each example is a knowledge-invariant clique. By further elaborating the robustness metric, a model is judged to be robust if its performance is consistently accurate on the overall cliques.
  arXiv  Detail & Related papers  (2023-05-23T12:05:09Z)
• Practical Approaches for Fair Learning with Multitype and Multivariate Sensitive Attributes [70.6326967720747]
  It is important to guarantee that machine learning algorithms deployed in the real world do not result in unfairness or unintended social consequences. We introduce FairCOCCO, a fairness measure built on cross-covariance operators on reproducing kernel Hilbert Spaces. We empirically demonstrate consistent improvements against state-of-the-art techniques in balancing predictive power and fairness on real-world datasets.
  arXiv  Detail & Related papers  (2022-11-11T11:28:46Z)
• Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention [36.90363317158731]
  We propose an adaptive sparse token pruning framework with a minimal cost. Our method improves the throughput of DeiT-S by 50% and brings only 0.2% drop in top-1 accuracy.
  arXiv  Detail & Related papers  (2022-09-28T03:07:32Z)
• More Than Words: Towards Better Quality Interpretations of Text Classifiers [16.66535643383862]
  We show that token-based interpretability, while being a convenient first choice given the input interfaces of the ML models, is not the most effective one in all situations. We show that higher-level feature attributions offer several advantages: 1) they are more robust as measured by the randomization tests, 2) they lead to lower variability when using approximation-based methods like SHAP, and 3) they are more intelligible to humans in situations where the linguistic coherence resides at a higher level.
  arXiv  Detail & Related papers  (2021-12-23T10:18:50Z)
• MASKER: Masked Keyword Regularization for Reliable Text Classification [73.90326322794803]
  We propose a fine-tuning method, coined masked keyword regularization (MASKER), that facilitates context-based prediction. MASKER regularizes the model to reconstruct the keywords from the rest of the words and make low-confidence predictions without enough context. We demonstrate that MASKER improves OOD detection and cross-domain generalization without degrading classification accuracy.
  arXiv  Detail & Related papers  (2020-12-17T04:54:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.