Are Your Explanations Reliable? Investigating the Stability of LIME in Explaining Text Classifiers by Marrying XAI and Adversarial Attack

• URL: http://arxiv.org/abs/2305.12351v2
• Date: Sun, 15 Oct 2023 13:19:44 GMT
• Title: Are Your Explanations Reliable? Investigating the Stability of LIME in Explaining Text Classifiers by Marrying XAI and Adversarial Attack
• Authors: Christopher Burger, Lingwei Chen, Thai Le
• Abstract summary: LIME has emerged as one of the most commonly referenced tools in explainable AI (XAI) frameworks. In this paper, we first evaluate the inherent instability of LIME on text data to establish a baseline. We then propose a novel algorithm XAIFooler to perturb text inputs and manipulate explanations that casts investigation on the stability of LIME as a text perturbation optimization problem.
• Score: 11.437660523661338
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LIME has emerged as one of the most commonly referenced tools in explainable AI (XAI) frameworks that is integrated into critical machine learning applications--e.g., healthcare and finance. However, its stability remains little explored, especially in the context of text data, due to the unique text-space constraints. To address these challenges, in this paper, we first evaluate the inherent instability of LIME on text data to establish a baseline, and then propose a novel algorithm XAIFooler to perturb text inputs and manipulate explanations that casts investigation on the stability of LIME as a text perturbation optimization problem. XAIFooler conforms to the constraints to preserve text semantics and original prediction with small perturbations, and introduces Rank-biased Overlap (RBO) as a key part to guide the optimization of XAIFooler that satisfies all the requirements for explanation similarity measure. Extensive experiments on real-world text datasets demonstrate that XAIFooler significantly outperforms all baselines by large margins in its ability to manipulate LIME's explanations with high semantic preservability.

Related papers

• Vulnerability of LLMs to Vertically Aligned Text Manipulations [108.6908427615402]
  Large language models (LLMs) have become highly effective at performing text classification tasks. modifying input formats, such as vertically aligning words for encoder-based models, can substantially lower accuracy in text classification tasks. Do decoder-based LLMs exhibit similar vulnerabilities to vertically formatted text input?
  arXiv  Detail & Related papers  (2024-10-26T00:16:08Z)
• SCENE: Evaluating Explainable AI Techniques Using Soft Counterfactuals [0.0]
  This paper introduces SCENE (Soft Counterfactual Evaluation for Natural language Explainability), a novel evaluation method. By focusing on token-based substitutions, SCENE creates contextually appropriate and semantically meaningful Soft Counterfactuals. SCENE provides valuable insights into the strengths and limitations of various XAI techniques.
  arXiv  Detail & Related papers  (2024-08-08T16:36:24Z)
• CLAIM Your Data: Enhancing Imputation Accuracy with Contextual Large Language Models [0.18416014644193068]
  This paper introduces the Contextual Language model for Accurate Imputation Method (CLAIM) Unlike traditional imputation methods, CLAIM utilizes contextually relevant natural language descriptors to fill missing values. Our evaluations across diverse datasets and missingness patterns reveal CLAIM's superior performance over existing imputation techniques.
  arXiv  Detail & Related papers  (2024-05-28T00:08:29Z)
• LLM-Assisted Content Conditional Debiasing for Fair Text Embedding [37.92120550031469]
  This paper proposes a novel method for learning fair text embeddings. We define a novel content-conditional equal distance (CCED) fairness for text embeddings. We also introduce a content-conditional debiasing (CCD) loss to ensure that embeddings of texts with different sensitive attributes but identical content maintain the same distance from the embedding of their corresponding neutral text.
  arXiv  Detail & Related papers  (2024-02-22T01:20:51Z)
• How Well Do Text Embedding Models Understand Syntax? [50.440590035493074]
  The ability of text embedding models to generalize across a wide range of syntactic contexts remains under-explored. Our findings reveal that existing text embedding models have not sufficiently addressed these syntactic understanding challenges. We propose strategies to augment the generalization ability of text embedding models in diverse syntactic scenarios.
  arXiv  Detail & Related papers  (2023-11-14T08:51:00Z)
• An xAI Approach for Data-to-Text Processing with ASP [39.58317527488534]
  This paper presents a framework that is compliant with xAI requirements. The text description is hierarchically organized, in a top-down structure where text is enriched with further details. The generation of natural language descriptions' structure is also managed by logic rules.
  arXiv  Detail & Related papers  (2023-08-30T09:09:09Z)
• Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy [52.765898203824975]
  We introduce a semantic-aware watermarking algorithm that considers the characteristics of conditional text generation and the input context. Experimental results demonstrate that our proposed method yields substantial improvements across various text generation models.
  arXiv  Detail & Related papers  (2023-07-25T20:24:22Z)
• Revisiting the Roles of "Text" in Text Games [102.22750109468652]
  This paper investigates the roles of text in the face of different reinforcement learning challenges. We propose a simple scheme to extract relevant contextual information into an approximate state hash. Such a lightweight plug-in achieves competitive performance with state-of-the-art text agents.
  arXiv  Detail & Related papers  (2022-10-15T21:52:39Z)
• Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQA [85.17249272519626]
  An optimized OpenQA Table-Text Retriever (OTTeR) is proposed. We conduct retrieval-centric mixed-modality synthetic pre-training. OTTeR substantially improves the performance of table-and-text retrieval on the OTT-QA dataset.
  arXiv  Detail & Related papers  (2022-10-11T07:04:39Z)
• SUN: Exploring Intrinsic Uncertainties in Text-to-SQL Parsers [61.48159785138462]
  This paper aims to improve the performance of text-to-dependence by exploring the intrinsic uncertainties in the neural network based approaches (called SUN) Extensive experiments on five benchmark datasets demonstrate that our method significantly outperforms competitors and achieves new state-of-the-art results.
  arXiv  Detail & Related papers  (2022-09-14T06:27:51Z)
• Why model why? Assessing the strengths and limitations of LIME [0.0]
  This paper examines the effectiveness of the Local Interpretable Model-Agnostic Explanations (LIME) xAI framework. LIME is one of the most popular model agnostic frameworks found in the literature. We show how LIME can be used to supplement conventional performance assessment methods.
  arXiv  Detail & Related papers  (2020-11-30T21:08:07Z)

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.