CAuSE: Decoding Multimodal Classifiers using Faithful Natural Language Explanation

• URL: http://arxiv.org/abs/2512.06814v1
• Date: Sun, 07 Dec 2025 12:15:21 GMT
• Title: CAuSE: Decoding Multimodal Classifiers using Faithful Natural Language Explanation
• Authors: Dibyanayan Bandyopadhyay, Soham Bhattacharjee, Mohammed Hasanuzzaman, Asif Ekbal,
• Abstract summary: We propose CAuSE (Causal Abstraction under Simulated Explanations), a novel framework to generate faithful NLEs for any pretrained multimodal classifier.<n>We demonstrate that CAuSE generalizes across datasets and models through extensive empirical evaluations.<n>We further validate this through a redesigned metric for measuring causal faithfulness in multimodal settings.
• Score: 46.9286703847151
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal classifiers function as opaque black box models. While several techniques exist to interpret their predictions, very few of them are as intuitive and accessible as natural language explanations (NLEs). To build trust, such explanations must faithfully capture the classifier's internal decision making behavior, a property known as faithfulness. In this paper, we propose CAuSE (Causal Abstraction under Simulated Explanations), a novel framework to generate faithful NLEs for any pretrained multimodal classifier. We demonstrate that CAuSE generalizes across datasets and models through extensive empirical evaluations. Theoretically, we show that CAuSE, trained via interchange intervention, forms a causal abstraction of the underlying classifier. We further validate this through a redesigned metric for measuring causal faithfulness in multimodal settings. CAuSE surpasses other methods on this metric, with qualitative analysis reinforcing its advantages. We perform detailed error analysis to pinpoint the failure cases of CAuSE. For replicability, we make the codes available at https://github.com/newcodevelop/CAuSE

Related papers

• Using Small Language Models to Reverse-Engineer Machine Learning Pipelines Structures [0.38180404292108383]
  Existing approaches either depend on non-scalable, manual labeling, or on ML classifiers that do not properly support the diversity of the domain.<n>We evaluate whether Small Language Models (SLMs) can leverage their code understanding and classification abilities to address these limitations.
  arXiv  Detail & Related papers  (2026-01-07T15:00:22Z)
• SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models [88.29990536278167]
  We introduce SPaR, a self-play framework integrating tree-search self-refinement to yield valid and comparable preference pairs.<n>Our experiments show that a LLaMA3-8B model, trained over three iterations guided by SPaR, surpasses GPT-4-Turbo on the IFEval benchmark without losing general capabilities.
  arXiv  Detail & Related papers  (2024-12-16T09:47:43Z)
• Cycles of Thought: Measuring LLM Confidence through Stable Explanations [53.15438489398938]
  Large language models (LLMs) can reach and even surpass human-level accuracy on a variety of benchmarks, but their overconfidence in incorrect responses is still a well-documented failure mode. We propose a framework for measuring an LLM's uncertainty with respect to the distribution of generated explanations for an answer.
  arXiv  Detail & Related papers  (2024-06-05T16:35:30Z)
• FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning [21.088762527081883]
  Exemplar-free class-incremental learning (CIL) poses several challenges since it prohibits the rehearsal of data from previous tasks. Recent approaches to incrementally learning the classifier by freezing the feature extractor after the first task have gained much attention. We explore prototypical networks for CIL, which generate new class prototypes using the frozen feature extractor and classify the features based on the Euclidean distance to the prototypes.
  arXiv  Detail & Related papers  (2023-09-25T11:54:33Z)
• Understanding Emergent In-Context Learning from a Kernel Regression Perspective [55.95455089638838]
  Large language models (LLMs) have initiated a paradigm shift in transfer learning.<n>This paper proposes a kernel-regression perspective of understanding LLMs' ICL bahaviors when faced with in-context examples.<n>We find that during ICL, the attention and hidden features in LLMs match the behaviors of a kernel regression.
  arXiv  Detail & Related papers  (2023-05-22T06:45:02Z)
• Interpretability at Scale: Identifying Causal Mechanisms in Alpaca [62.65877150123775]
  We use Boundless DAS to efficiently search for interpretable causal structure in large language models while they follow instructions. Our findings mark a first step toward faithfully understanding the inner-workings of our ever-growing and most widely deployed language models.
  arXiv  Detail & Related papers  (2023-05-15T17:15:40Z)
• Toward a Theory of Causation for Interpreting Neural Code Models [49.906221295459275]
  This paper introduces $do_code$, a post hoc interpretability method specific to Neural Code Models (NCMs) $do_code$ is based upon causal inference to enable language-oriented explanations. Results show that our studied NCMs are sensitive to changes in code syntax.
  arXiv  Detail & Related papers  (2023-02-07T22:56:58Z)
• An Additive Instance-Wise Approach to Multi-class Model Interpretation [53.87578024052922]
  Interpretable machine learning offers insights into what factors drive a certain prediction of a black-box system. Existing methods mainly focus on selecting explanatory input features, which follow either locally additive or instance-wise approaches. This work exploits the strengths of both methods and proposes a global framework for learning local explanations simultaneously for multiple target classes.
  arXiv  Detail & Related papers  (2022-07-07T06:50:27Z)
• Zero-shot Commonsense Question Answering with Cloze Translation and Consistency Optimization [20.14487209460865]
  We investigate four translation methods that can translate natural questions into cloze-style sentences. We show that our methods are complementary datasets to a knowledge base improved model, and combining them can lead to state-of-the-art zero-shot performance.
  arXiv  Detail & Related papers  (2022-01-01T07:12:49Z)
• A Convolutional Deep Markov Model for Unsupervised Speech Representation Learning [32.59760685342343]
  Probabilistic Latent Variable Models provide an alternative to self-supervised learning approaches for linguistic representation learning from speech. In this work, we propose ConvDMM, a Gaussian state-space model with non-linear emission and transition functions modelled by deep neural networks. When trained on a large scale speech dataset (LibriSpeech), ConvDMM produces features that significantly outperform multiple self-supervised feature extracting methods.
  arXiv  Detail & Related papers  (2020-06-03T21:50:20Z)
• Bayes-TrEx: a Bayesian Sampling Approach to Model Transparency by Example [9.978961706999833]
  We introduce a flexible model inspection framework: Bayes-TrEx. Given a data distribution, Bayes-TrEx finds in-distribution examples with a specified prediction confidence. We show that this framework enables more flexible holistic model analysis than just inspecting the test set.
  arXiv  Detail & Related papers  (2020-02-19T15:49:00Z)

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.