Argumentative Debates for Transparent Bias Detection [Technical Report]
As the use of AI in society grows, addressing emerging biases is essential to prevent systematic discrimination. Several bias detection methods have been proposed, but, with few exceptions, these tend to ignore transparency. Instead, interpretability and explainability are core requirements for algorithmic fairness, even more so than for other algorithmic solutions, given the human-oriented nature of fairness. We present ABIDE (Argumentative BIas detection by DEbate), a novel framework that structures bias detection transparently as debate, guided by an underlying argument graph as understood in (formal and computational) argumentation. The arguments are about the success chances of groups in local neighbourhoods and the significance of these neighbourhoods. We evaluate ABIDE experimentally and demonstrate its strengths in performance against an argumentative baseline.
Code (0)
등록된 구현이 없습니다.
Tasks
Bias DetectionSimilar Papers 제목 키워드 기반
Who Argues What? Joint Argument-Entity Detection and Classification in Political Debates
Political debates are often analyzed through Argument Mining (AM) to investigate the key arguments that drive them. However, political arguments are rarely interpretable from argumentative spans alone, as claims and prem…
Argument MiningLLM-based Argument Mining meets Argumentation and Description Logics: a Unified Framework for Reasoning about Debates
Large Language Models (LLMs) achieve strong performance in analyzing and generating text, yet they struggle with explicit, transparent, and verifiable reasoning over complex texts such as those containing debates. In par…
Argument MiningUsing Complex Argumentative Interactions to Reconstruct the Argumentative Structure of Large-Scale Debates
In this paper we consider the insights that can be gained by considering large scale argument networks and the complex interactions between their constituent propositions. We investigate metrics for analysing properties …
Argument MiningDecision MakingAutomatic Paper Reviewing with Heterogeneous Graph Reasoning over LLM-Simulated Reviewer-Author Debates
Existing paper review methods often rely on superficial manuscript features or directly on large language models (LLMs), which are prone to hallucinations, biased scoring, and limited reasoning capabilities. Moreover, th…
RooseBERT: A New Deal For Political Language Modelling
The increasing amount of political debates and politics-related discussions calls for the definition of novel computational methods to automatically analyse such content with the final goal of lightening up political del…
Sentiment AnalysisLanguage ModellingStance Detection