[2507.14221] Fair Representation in Parliamentary Summaries: Measuring and Mitigating Inclusion Bias

Computer Science > Computers and Society arXiv:2507.14221 (cs) [Submitted on 16 Jul 2025 (v1), last revised 2 Apr 2026 (this version, v2)] Title:Fair Representation in Parliamentary Summaries: Measuring and Mitigating Inclusion Bias Authors:Eoghan Cunningham, James Cross, Derek Greene View a PDF of the paper titled Fair Representation in Parliamentary Summaries: Measuring and Mitigating Inclusion Bias, by Eoghan Cunningham and 2 other authors View PDF HTML (experimental) Abstract:The The use of Large language models (LLMs) to summarise parliamentary proceedings presents a promising means of increasing the accessibility of democratic participation. However, as these systems increasingly mediate access to political information -- filtering and framing content before it reaches users -- there are important fairness considerations to address. In this work, we evaluate 5 LLMs (both proprietary and open-weight) in the summarisation of plenary debates from the European Parliament to investigate the representational biases that emerge in this context. We develop an attribution-aware evaluation framework to measure speaker-level inclusion and mis-representation in debate summaries. Across all models and experiments, we find that speakers are less accurately represented in the final summary on the basis of (i) their speaking-order (speeches in the middle of the debate were systematically excluded), (ii) language spoken (non-English speakers were less faithfully represented), and (ii...