paper-with-me

Papers

What Changed? Investigating Debiasing Methods using Causal Mediation Analysis

2022-06-01 · NAACL (GeBNLP) 2022 7 · Sullam Jeoung, Jana Diesner

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.

📄 PDF Abstract BibTeX arXiv:2206.00701

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

DINER: Debiasing Aspect-based Sentiment Analysis with Multi-variable Causal Inference

2024-03-02 · Jialong Wu, Linhai Zhang, Deyu Zhou, Guoqiang Xu

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+2

Causal Walk: Debiasing Multi-Hop Fact Verification with Front-Door Adjustment

2024-03-05 · Congzhi Zhang, Linhai Zhang, Deyu Zhou

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+2

On the Opportunity of Causal Learning in Recommendation Systems: Foundation, Estimation, Prediction and Challenges

2022-01-18 · Peng Wu, Haoxuan Li, yuhao deng, Wenjie Hu 외

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 Systems

Information Gain-Guided Causal Intervention for Autonomous Debiasing Large Language Models

2025-04-17 · Zhouhao Sun, Xiao Ding, Li Du, Yunpeng Xu 외

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 Learning

Causal Network Learning from Multiple Interventions of Unknown Manipulated Targets

2016-10-27 · Yango He, Zhi Geng

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…