# Bias in Opinion Summarisation from Pre-training to Adaptation: A Case Study in Political Bias

arXiv: https://arxiv.org/abs/2402.00322 · HTML: https://mlsanity.com/paper/2402.00322/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 61 references that are in the map.
- First posted on arXiv 1 Feb 2024.

## Builds on (most cited first, 30 of 36)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [AdapterHub: A Framework for Adapting Transformers](https://mlsanity.com/paper/2007.07779/) (2020)
- [TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification](https://mlsanity.com/paper/2010.12421/) (2020)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [Towards Understanding and Mitigating Social Biases in Language Models](https://mlsanity.com/paper/2106.13219/) (2021)
- [From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models](https://mlsanity.com/paper/2305.08283/) (2023)
- [Demographic Dialectal Variation in Social Media: A Case Study of African-American English](https://mlsanity.com/paper/1608.08868/) (2016)
- [Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias](https://mlsanity.com/paper/2004.12265/) (2020)
- [Co-Writing with Opinionated Language Models Affects Users' Views](https://mlsanity.com/paper/2302.00560/) (2023)
- [Yara Parser: A Fast and Accurate Dependency Parser](https://mlsanity.com/paper/1503.06733/) (2015)
- [Stance Detection with Bidirectional Conditional Encoding](https://mlsanity.com/paper/1606.05464/) (2016)
- [Multi-View Sequence-to-Sequence Models with Conversational Structure for Abstractive Dialogue Summarization](https://mlsanity.com/paper/2010.01672/) (2020)
- [Unsupervised Opinion Summarization as Copycat-Review Generation](https://mlsanity.com/paper/1911.02247/) (2019)
- [From Arguments to Key Points: Towards Automatic Argument Summarization](https://mlsanity.com/paper/2005.01619/) (2020)
- [Bidirectional Language Models Are Also Few-shot Learners](https://mlsanity.com/paper/2209.14500/) (2022)
- [Aspect-Controllable Opinion Summarization](https://mlsanity.com/paper/2109.03171/) (2021)
- [ConvoSumm: Conversation Summarization Benchmark and Improved Abstractive Summarization with Argument Mining](https://mlsanity.com/paper/2106.00829/) (2021)
- [Unsupervised Opinion Summarization with Noising and Denoising](https://mlsanity.com/paper/2004.10150/) (2020)
- [Robust Transfer Learning with Pretrained Language Models through Adapters](https://mlsanity.com/paper/2108.02340/) (2021)
- [Quantitative Argument Summarization and Beyond: Cross-Domain Key Point Analysis](https://mlsanity.com/paper/2010.05369/) (2020)
- [Learning Opinion Summarizers by Selecting Informative Reviews](https://mlsanity.com/paper/2109.04325/) (2021)
- [Hierarchical Sketch Induction for Paraphrase Generation](https://mlsanity.com/paper/2203.03463/) (2022)

## Built on by (most cited first, 12 of 12)

- [Uncovering Political Bias in Large Language Models using Parliamentary Voting Records](https://mlsanity.com/paper/2601.08785/) (2026)
- [LLMs Do Not See Age: Assessing Demographic Bias in Automated Systematic Review Synthesis](https://mlsanity.com/paper/2511.06000/) (2025)
- [Less Is More? Examining Fairness in Pruned Large Language Models for Summarising Opinions](https://mlsanity.com/paper/2508.17610/) (2025)
- [REFER: Mitigating Bias in Opinion Summarisation via Frequency Framed Prompting](https://mlsanity.com/paper/2509.15723/) (2025)
- [When Bigger Isn't Better: A Comprehensive Fairness Evaluation of Political Bias in Multi-News Summarisation](https://mlsanity.com/paper/2604.21309/) (2026)
- [Coverage-based Fairness in Multi-document Summarization](https://mlsanity.com/paper/2412.08795/) (2024)
- [Faithful Summarisation under Disagreement via Belief-Level Aggregation](https://mlsanity.com/paper/2601.04889/) (2026)
- [AI-Mediated Communication Can Steer Collective Opinion](https://mlsanity.com/paper/2605.16245/) (2026)
- [Improving Fairness of Large Language Models in Multi-document Summarization](https://mlsanity.com/paper/2506.07479/) (2025)
- [Fair Representation in Parliamentary Summaries: Measuring and Mitigating Inclusion Bias](https://mlsanity.com/paper/2507.14221/) (2025)
- [Discrimination by LLMs: Cross-lingual Bias Assessment and Mitigation in Decision-Making and Summarisation](https://mlsanity.com/paper/2509.09735/) (2025)
- [Responsible AI for General-Purpose Systems: Overview, Challenges, and A Path Forward](https://mlsanity.com/paper/2601.13122/) (2026)

## Abstract (arXiv)

Opinion summarisation aims to summarise the salient information and opinions presented in documents such as product reviews, discussion forums, and social media texts into short summaries that enable users to effectively understand the opinions therein. Generating biased summaries has the risk of potentially swaying public opinion. Previous studies focused on studying bias in opinion summarisation using extractive models, but limited research has paid attention to abstractive summarisation models. In this study, using political bias as a case study, we first establish a methodology to quantify bias in abstractive models, then trace it from the pre-trained models to the task of summarising social media opinions using different models and adaptation methods. We find that most models exhibit intrinsic bias. Using a social media text summarisation dataset and contrasting various adaptation methods, we find that tuning a smaller number of parameters is less biased compared to standard fine-tuning; however, the diversity of topics in training data used for fine-tuning is critical.