A Novel Interpretability Metric for Explaining Bias in Language Models: Applications on Multilingual Models from Southeast Asia
Work on bias in pretrained language models (PLMs) focuses on bias evaluation and mitigation and fails to tackle the question of bias attribution and explainability. We propose a novel metric, the $\textit{bias attribution score}$, which draws from information theory to measure token-level contributions to biased behavior in PLMs. We then demonstrate the utility of this metric by applying it on multilingual PLMs, including models from Southeast Asia which have not yet been thoroughly examined in bias evaluation literature. Our results confirm the presence of sexist and homophobic bias in Southeast Asian PLMs. Interpretability and semantic analyses also reveal that PLM bias is strongly induced by words relating to crime, intimate relationships, and helping among other discursive categories, suggesting that these are topics where PLMs strongly reproduce bias from pretraining data and where PLMs should be used with more caution.
Code (1)
Similar Papers 제목 키워드 기반
Explaining Multi-modal Large Language Models by Analyzing their Vision Perception
Multi-modal Large Language Models (MLLMs) have demonstrated remarkable capabilities in understanding and generating content across various modalities, such as images and text. However, their interpretability remains a ch…
Object LocalizationWasserstein-based fairness interpretability framework for machine learning models
The objective of this article is to introduce a fairness interpretability framework for measuring and explaining the bias in classification and regression models at the level of a distribution. In our work, we measure th…
BIG-bench Machine LearningFairnessregressionInterpretable Text Embeddings and Text Similarity Explanation: A Primer
Text embeddings and text embedding models are a backbone of many AI and NLP systems, particularly those involving search. However, interpretability challenges persist, especially in explaining obtained similarity scores,…
Similarity Explanationtext similarityExplaining Dialogue Evaluation Metrics using Adversarial Behavioral Analysis
There is an increasing trend in using neural methods for dialogue model evaluation. Lack of a framework to investigate these metrics can cause dialogue models to reflect their biases and cause unforeseen problems during …
Dialogue EvaluationAttributions All the Way Down? The Metagame of Interpretability
We introduce the metagame, a conceptual framework for quantifying second-order interaction effects of model explanations. For any first-order attribution $φ(f)$ explaining a model $f$, we measure the directional influenc…