Explanation Bias is a Product: Revealing the Hidden Lexical and Position Preferences in Post-Hoc Feature Attribution

• URL: http://arxiv.org/abs/2512.11108v1
• Date: Thu, 11 Dec 2025 20:48:22 GMT
• Title: Explanation Bias is a Product: Revealing the Hidden Lexical and Position Preferences in Post-Hoc Feature Attribution
• Authors: Jonathan Kamp, Roos Bakker, Dominique Blok,
• Abstract summary: We find that explanations on the same input may vary greatly due to underlying biases of different methods.<n>We structure their biases through a model- and method-agnostic framework of three evaluation metrics.<n>We find signs that methods producing anomalous explanations are more likely to be biased themselves.
• Score: 0.3568466510804538
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Good quality explanations strengthen the understanding of language models and data. Feature attribution methods, such as Integrated Gradient, are a type of post-hoc explainer that can provide token-level insights. However, explanations on the same input may vary greatly due to underlying biases of different methods. Users may be aware of this issue and mistrust their utility, while unaware users may trust them inadequately. In this work, we delve beyond the superficial inconsistencies between attribution methods, structuring their biases through a model- and method-agnostic framework of three evaluation metrics. We systematically assess both the lexical and position bias (what and where in the input) for two transformers; first, in a controlled, pseudo-random classification task on artificial data; then, in a semi-controlled causal relation detection task on natural data. We find that lexical and position biases are structurally unbalanced in our model comparison, with models that score high on one type score low on the other. We also find signs that methods producing anomalous explanations are more likely to be biased themselves.

Related papers

• Looking at Model Debiasing through the Lens of Anomaly Detection [11.113718994341733]
  Deep neural networks are sensitive to bias in the data.<n>In this work, we show the importance of accurately predicting the bias-conflicting and bias-aligned samples.<n>We propose a new bias identification method based on anomaly detection.
  arXiv  Detail & Related papers  (2024-07-24T17:30:21Z)
• Common-Sense Bias Modeling for Classification Tasks [15.683471433842492]
  We propose a novel framework to extract comprehensive biases in image datasets based on textual descriptions.<n>Our method uncovers novel model biases in multiple image benchmark datasets.<n>The discovered bias can be mitigated by simple data re-weighting to de-correlate the features.
  arXiv  Detail & Related papers  (2024-01-24T03:56:07Z)
• NBIAS: A Natural Language Processing Framework for Bias Identification in Text [9.486702261615166]
  Bias in textual data can lead to skewed interpretations and outcomes when the data is used. An algorithm trained on biased data may end up making decisions that disproportionately impact a certain group of people. We develop a comprehensive framework NBIAS that consists of four main layers: data, corpus construction, model development and an evaluation layer.
  arXiv  Detail & Related papers  (2023-08-03T10:48:30Z)
• Stubborn Lexical Bias in Data and Models [50.79738900885665]
  We use a new statistical method to examine whether spurious patterns in data appear in models trained on the data. We apply an optimization approach to *reweight* the training data, reducing thousands of spurious correlations. Surprisingly, though this method can successfully reduce lexical biases in the training data, we still find strong evidence of corresponding bias in the trained models.
  arXiv  Detail & Related papers  (2023-06-03T20:12:27Z)
• Towards Fine-Grained Information: Identifying the Type and Location of Translation Errors [80.22825549235556]
  Existing approaches can not synchronously consider error position and type. We build an FG-TED model to predict the textbf addition and textbfomission errors. Experiments show that our model can identify both error type and position concurrently, and gives state-of-the-art results.
  arXiv  Detail & Related papers  (2023-02-17T16:20:33Z)
• Interpretable Data-Based Explanations for Fairness Debugging [7.266116143672294]
  Gopher is a system that produces compact, interpretable, and causal explanations for bias or unexpected model behavior. We introduce the concept of causal responsibility that quantifies the extent to which intervening on training data by removing or updating subsets of it can resolve the bias. Building on this concept, we develop an efficient approach for generating the top-k patterns that explain model bias.
  arXiv  Detail & Related papers  (2021-12-17T20:10:00Z)
• Balancing out Bias: Achieving Fairness Through Training Reweighting [58.201275105195485]
  Bias in natural language processing arises from models learning characteristics of the author such as gender and race. Existing methods for mitigating and measuring bias do not directly account for correlations between author demographics and linguistic variables. This paper introduces a very simple but highly effective method for countering bias using instance reweighting.
  arXiv  Detail & Related papers  (2021-09-16T23:40:28Z)
• Counterfactual Evaluation for Explainable AI [21.055319253405603]
  We propose a new methodology to evaluate the faithfulness of explanations from the textitcounterfactual reasoning perspective. We introduce two algorithms to find the proper counterfactuals in both discrete and continuous scenarios and then use the acquired counterfactuals to measure faithfulness.
  arXiv  Detail & Related papers  (2021-09-05T01:38:49Z)
• Contrastive Explanations for Model Interpretability [77.92370750072831]
  We propose a methodology to produce contrastive explanations for classification models. Our method is based on projecting model representation to a latent space. Our findings shed light on the ability of label-contrastive explanations to provide a more accurate and finer-grained interpretability of a model's decision.
  arXiv  Detail & Related papers  (2021-03-02T00:36:45Z)
• Investigating Bias in Image Classification using Model Explanations [0.0]
  We evaluate whether model explanations could efficiently detect bias in image classification by highlighting discriminating features. We formulated important characteristics for bias detection and observed how explanations change as the degree of bias in models change.
  arXiv  Detail & Related papers  (2020-12-10T05:27:49Z)
• LOGAN: Local Group Bias Detection by Clustering [86.38331353310114]
  We argue that evaluating bias at the corpus level is not enough for understanding how biases are embedded in a model. We propose LOGAN, a new bias detection technique based on clustering. Experiments on toxicity classification and object classification tasks show that LOGAN identifies bias in a local region.
  arXiv  Detail & Related papers  (2020-10-06T16:42:51Z)
• Towards Robustifying NLI Models Against Lexical Dataset Biases [94.79704960296108]
  This paper explores both data-level and model-level debiasing methods to robustify models against lexical dataset biases. First, we debias the dataset through data augmentation and enhancement, but show that the model bias cannot be fully removed via this method. The second approach employs a bag-of-words sub-model to capture the features that are likely to exploit the bias and prevents the original model from learning these biased features.
  arXiv  Detail & Related papers  (2020-05-10T17:56:10Z)

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.