What Changed? Investigating Debiasing Methods using Causal Mediation Analysis
Previous work has examined how debiasing language models affect downstream tasks, specifically, how debiasing techniques influence task performance and whether debiased models also make impartial predictions in downstream tasks or not. However, what we don't understand well yet is why debiasing methods have varying impacts on downstream tasks and how debiasing techniques affect internal components of language models, i.e., neurons, layers, and attentions. In this paper, we decompose the internal mechanisms of debiasing language models with respect to gender by applying causal mediation analysis to understand the influence of debiasing methods on toxicity detection as a downstream task. Our findings suggest a need to test the effectiveness of debiasing methods with different bias metrics, and to focus on changes in the behavior of certain components of the models, e.g.,first two layers of language models, and attention heads.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
DINER: Debiasing Aspect-based Sentiment Analysis with Multi-variable Causal Inference
Though notable progress has been made, neural-based aspect-based sentiment analysis (ABSA) models are prone to learn spurious correlations from annotation biases, resulting in poor robustness on adversarial data transfor…
Aspect-Based Sentiment AnalysisAspect-Based Sentiment Analysis (ABSA)Causal Inferencecounterfactual+2Causal Walk: Debiasing Multi-Hop Fact Verification with Front-Door Adjustment
Conventional multi-hop fact verification models are prone to rely on spurious correlations from the annotation artifacts, leading to an obvious performance decline on unbiased datasets. Among the various debiasing works,…
Causal InferencecounterfactualCounterfactual ReasoningFact Verification+2On the Opportunity of Causal Learning in Recommendation Systems: Foundation, Estimation, Prediction and Challenges
Recently, recommender system (RS) based on causal inference has gained much attention in the industrial community, as well as the states of the art performance in many prediction and debiasing tasks. Nevertheless, a unif…
Causal InferencePredictionRecommendation SystemsInformation Gain-Guided Causal Intervention for Autonomous Debiasing Large Language Models
Despite significant progress, recent studies indicate that current large language models (LLMs) may still capture dataset biases and utilize them during inference, leading to the poor generalizability of LLMs. However, d…
DiversityIn-Context LearningCausal Network Learning from Multiple Interventions of Unknown Manipulated Targets
In this paper, we discuss structure learning of causal networks from multiple data sets obtained by external intervention experiments where we do not know what variables are manipulated. For example, the conditions in th…