Unmasking Causal Representations: A Novel Masking Paradigm for Explainable Language Models

Fuente: Zenodo
Guardado en:
Detalles Bibliográficos
Autores principales: Revista, Zen, IA, 10
Formato: Recurso digital
Publicado: Zenodo 2025
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866901933897285632
author Revista, Zen
IA, 10
author_facet Revista, Zen
IA, 10
contents The opaque nature of large language models (LLMs) presents a significant challenge to their widespread adoption in critical applications. While traditional interpretability methods offer insights into model behavior, they often fall short in identifying the underlying causal mechanisms driving predictions, instead focusing on correlations or feature importance. This paper introduces a novel masking paradigm designed to unmask and explicitly identify causal representations within pre-trained language models, thereby enhancing their explainability and trustworthiness. Our approach posits that by systematically intervening on and observing the resulting changes in model output, we can isolate textual segments or latent features that act as direct causal factors for a given prediction. This paradigm involves a sequence of structured masking operations coupled with counterfactual analysis, allowing for the distinction between merely correlated input features and truly causal ones. We demonstrate how this method can be applied to dissect model decisions across various natural language processing tasks, revealing not only which parts of the input are most influential but also how they causally contribute to the final outcome. Through extensive experimentation on established benchmarks, we show that this novel masking paradigm outperforms existing explainability techniques in terms of fidelity to the model's true causal reasoning and provides more actionable, human-interpretable explanations. The proposed framework represents a significant step towards developing truly explainable and robust AI systems, fostering greater transparency and accountability in the deployment of advanced language models.
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_17815654
institution Zenodo
language
publishDate 2025
publisher Zenodo
record_format zenodo
spellingShingle Unmasking Causal Representations: A Novel Masking Paradigm for Explainable Language Models
Revista, Zen
IA, 10
The opaque nature of large language models (LLMs) presents a significant challenge to their widespread adoption in critical applications. While traditional interpretability methods offer insights into model behavior, they often fall short in identifying the underlying causal mechanisms driving predictions, instead focusing on correlations or feature importance. This paper introduces a novel masking paradigm designed to unmask and explicitly identify causal representations within pre-trained language models, thereby enhancing their explainability and trustworthiness. Our approach posits that by systematically intervening on and observing the resulting changes in model output, we can isolate textual segments or latent features that act as direct causal factors for a given prediction. This paradigm involves a sequence of structured masking operations coupled with counterfactual analysis, allowing for the distinction between merely correlated input features and truly causal ones. We demonstrate how this method can be applied to dissect model decisions across various natural language processing tasks, revealing not only which parts of the input are most influential but also how they causally contribute to the final outcome. Through extensive experimentation on established benchmarks, we show that this novel masking paradigm outperforms existing explainability techniques in terms of fidelity to the model's true causal reasoning and provides more actionable, human-interpretable explanations. The proposed framework represents a significant step towards developing truly explainable and robust AI systems, fostering greater transparency and accountability in the deployment of advanced language models.
title Unmasking Causal Representations: A Novel Masking Paradigm for Explainable Language Models
url https://doi.org/10.5281/zenodo.17815654