Fair Representation in Parliamentary Summaries: Measuring and Mitigating Inclusion Bias

ArXi:2507.14221v2 Announce Type: replace-cross The The use of Large language models (LLMs) to summarise parliamentary proceedings presents a promising means of increasing the accessibility of cratic 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