Step by Step to Fairness: Attributing Societal Bias in Task-oriented Dialogue Systems
Recent works have shown considerable improvements in task-oriented dialogue (TOD) systems by utilizing pretrained large language models (LLMs) in an end-to-end manner. However, the biased behavior of each component in a TOD system and the error propagation issue in the end-to-end framework can lead to seriously biased TOD responses. Existing works of fairness only focus on the total bias of a system. In this paper, we propose a diagnosis method to attribute bias to each component of a TOD system. With the proposed attribution method, we can gain a deeper understanding of the sources of bias. Additionally, researchers can mitigate biased model behavior at a more granular level. We conduct experiments to attribute the TOD system's bias toward three demographic axes: gender, age, and race. Experimental results show that the bias of a TOD system usually comes from the response generation model.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeFairnessResponse GenerationTask-Oriented Dialogue SystemsMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
FAE: A Fairness-Aware Ensemble Framework
Automated decision making based on big data and machine learning (ML) algorithms can result in discriminatory decisions against certain protected groups defined upon personal data like gender, race, sexual orientation et…
BIG-bench Machine LearningDecision MakingFairnessGroup Fairness in Bandit Arm Selection
We propose a novel formulation of group fairness with biased feedback in the contextual multi-armed bandit (CMAB) setting. In the CMAB setting, a sequential decision maker must, at each time step, choose an arm to pull f…
FairnessReinforcement Learning with Stepwise Fairness Constraints
AI methods are used in societally important settings, ranging from credit to employment to housing, and it is crucial to provide fairness in regard to algorithmic decision making. Moreover, many settings are dynamic, wit…
Decision MakingFairnessreinforcement-learningReinforcement Learning+1Fairness Research For Machine Learning Should Integrate Societal Considerations
Enhancing fairness in machine learning (ML) systems is increasingly important nowadays. While current research focuses on assistant tools for ML pipelines to promote fairness within them, we argue that: 1) The significan…
FairnessCausal Feature Selection for Algorithmic Fairness
The use of machine learning (ML) in high-stakes societal decisions has encouraged the consideration of fairness throughout the ML lifecycle. Although data integration is one of the primary steps to generate high quality …
Data IntegrationFairnessfeature selectionManagement