# Fair Representation in Parliamentary Summaries: Measuring and Mitigating Inclusion Bias

arXiv: https://arxiv.org/abs/2507.14221 · HTML: https://mlsanity.com/paper/2507.14221/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 50 references that are in the map.
- First posted on arXiv 16 Jul 2025.

## Builds on (most cited first, 25 of 25)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [SummEval: Re-evaluating Summarization Evaluation](https://mlsanity.com/paper/2007.12626/) (2020)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Asking and Answering Questions to Evaluate the Factual Consistency of Summaries](https://mlsanity.com/paper/2004.04228/) (2020)
- [QuestEval: Summarization Asks for Fact-based Evaluation](https://mlsanity.com/paper/2103.12693/) (2021)
- [BooookScore: A systematic exploration of book-length summarization in the era of LLMs](https://mlsanity.com/paper/2310.00785/) (2023)
- [Hierarchical Transformers for Multi-Document Summarization](https://mlsanity.com/paper/1905.13164/) (2019)
- [HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization](https://mlsanity.com/paper/1905.06566/) (2019)
- [The Political Preferences of LLMs](https://mlsanity.com/paper/2402.01789/) (2024)
- [A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models](https://mlsanity.com/paper/2406.11289/) (2024)
- [Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Tasks](https://mlsanity.com/paper/2306.05550/) (2023)
- [Harnessing Large Language Models for Text-Rich Sequential Recommendation](https://mlsanity.com/paper/2403.13325/) (2024)
- [Anchoring Bias in Large Language Models: An Experimental Study](https://mlsanity.com/paper/2412.06593/) (2024)
- [Assessing Political Bias in Large Language Models](https://mlsanity.com/paper/2405.13041/) (2024)
- [On Context Utilization in Summarization with Large Language Models](https://mlsanity.com/paper/2310.10570/) (2023)
- [Generalization Bias in Large Language Model Summarization of Scientific Research](https://mlsanity.com/paper/2504.00025/) (2025)
- [Bias in News Summarization: Measures, Pitfalls and Corpora](https://mlsanity.com/paper/2309.08047/) (2023)
- [From 'Showgirls' to 'Performers': Fine-tuning with Gender-inclusive Language for Bias Reduction in LLMs](https://mlsanity.com/paper/2407.04434/) (2024)
- [Bias in Opinion Summarisation from Pre-training to Adaptation: A Case Study in Political Bias](https://mlsanity.com/paper/2402.00322/) (2024)
- [What Large Language Models Do Not Talk About: An Empirical Study of Moderation and Censorship Practices](https://mlsanity.com/paper/2504.03803/) (2025)
- [SummAct: Uncovering User Intentions Through Interactive Behaviour Summarisation](https://mlsanity.com/paper/2410.08356/) (2024)
- [Low-Resource Cross-Lingual Summarization through Few-Shot Learning with Large Language Models](https://mlsanity.com/paper/2406.04630/) (2024)

## Abstract (arXiv)

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 (iii) political affiliations (better outcomes for left-of-centre parties). We further show how biases in these contexts can be decomposed to distinguish inclusion bias (systematic omission) from hallucination bias (systematic misrepresentation), and explore the effect of different mitigation strategies. Prompting strategies do not affect these biases. Instead, we propose a hierarchical summarisation method that decomposes the task into simpler extraction and aggregation steps, which we show significantly improves the positional/speaking-order bias across all models. These findings underscore the need for domain-sensitive evaluation metrics and ethical oversight in the deployment of LLMs for multilingual democratic applications.