Papers
Topics
Authors
Recent
Search
2000 character limit reached

Measuring Political Bias in Large Language Models: What Is Said and How It Is Said

Published 27 Mar 2024 in cs.CL and cs.AI | (2403.18932v1)

Abstract: We propose to measure political bias in LLMs by analyzing both the content and style of their generated content regarding political issues. Existing benchmarks and measures focus on gender and racial biases. However, political bias exists in LLMs and can lead to polarization and other harms in downstream applications. In order to provide transparency to users, we advocate that there should be fine-grained and explainable measures of political biases generated by LLMs. Our proposed measure looks at different political issues such as reproductive rights and climate change, at both the content (the substance of the generation) and the style (the lexical polarity) of such bias. We measured the political bias in eleven open-sourced LLMs and showed that our proposed framework is easily scalable to other topics and is explainable.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (69)
  1. Mohammad Ali and Naeemul Hassan. 2022. A survey of computational framing analysis approaches. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 9335–9348, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
  2. Falcon-40B: an open large language model with state-of-the-art performance.
  3. Out of one, many: Using language models to simulate human samples. Political Analysis, 31(3):337–351.
  4. We can detect your bias: Predicting the political ideology of news articles. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4982–4991, Online. Association for Computational Linguistics.
  5. Mitigating framing bias with polarity minimization loss. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 11100–11110, Singapore. Association for Computational Linguistics.
  6. Assessing political prudence of open-domain chatbots. In Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 548–555, Singapore and Online. Association for Computational Linguistics.
  7. Framing and bias: a literature review of recent findings. Central European journal of management, 3(2).
  8. Language (technology) is power: A critical survey of “bias” in NLP. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5454–5476, Online. Association for Computational Linguistics.
  9. Tracking the development of media frames within and across policy issues.
  10. The media frames corpus: Annotations of frames across issues. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 438–444, Beijing, China. Association for Computational Linguistics.
  11. Beyond prompt brittleness: Evaluating the reliability and consistency of political worldviews in llms.
  12. Analyzing political bias and unfairness in news articles at different levels of granularity. In Proceedings of the Fourth Workshop on Natural Language Processing and Computational Social Science, pages 149–154, Online. Association for Computational Linguistics.
  13. Learning to flip the bias of news headlines. In Proceedings of the 11th International Conference on Natural Language Generation, pages 79–88, Tilburg University, The Netherlands. Association for Computational Linguistics.
  14. Dennis Chong and James N Druckman. 2007. Framing theory. Annu. Rev. Polit. Sci., 10:103–126.
  15. Stefano DellaVigna and Ethan Kaplan. 2007. The fox news effect: Media bias and voting. The Quarterly Journal of Economics, 122(3):1187–1234.
  16. Analyzing polarization in social media: Method and application to tweets on 21 mass shootings. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2970–3005, Minneapolis, Minnesota. Association for Computational Linguistics.
  17. BERT: pre-training of deep bidirectional transformers for language understanding. CoRR, abs/1810.04805.
  18. Bold: Dataset and metrics for measuring biases in open-ended language generation. In Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, FAccT ’21, page 862–872, New York, NY, USA. Association for Computing Machinery.
  19. Towards measuring the representation of subjective global opinions in language models. arXiv preprint arXiv:2306.16388.
  20. On the nature of real and perceived bias in the mainstream media. PloS one, 13(3):e0193765.
  21. Robert M Entman. 1993. Framing: Toward clarification of a fractured paradigm. Journal of communication, 43(4):51–58.
  22. Robert M Entman. 2007. Framing bias: Media in the distribution of power. Journal of communication, 57(1):163–173.
  23. In plain sight: Media bias through the lens of factual reporting. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 6343–6349, Hong Kong, China. Association for Computational Linguistics.
  24. From pretraining data to language models to downstream tasks: Tracking the trails of political biases leading to unfair NLP models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11737–11762, Toronto, Canada. Association for Computational Linguistics.
  25. Red teaming language models to reduce harms: Methods, scaling behaviors, and lessons learned. arXiv preprint arXiv:2209.07858.
  26. R Kelly Garrett. 2009. Politically motivated reinforcement seeking: Reframing the selective exposure debate. Journal of communication, 59(4):676–699.
  27. Matthew Gentzkow and Jesse M Shapiro. 2006. Media bias and reputation. Journal of political Economy, 114(2):280–316.
  28. David Giles and Rachel L Shaw. 2009. The psychology of news influence and the development of media framing analysis. Social and personality psychology compass, 3(4):375–393.
  29. Erving Goffman. 1974. Frame analysis: An essay on the organization of experience. Harvard University Press.
  30. Studying political bias via word embeddings. In Companion Proceedings of the Web Conference 2020, WWW ’20, page 760–764, New York, NY, USA. Association for Computing Machinery.
  31. Felix Hamborg. 2020. Media bias, the social sciences, and NLP: Automating frame analyses to identify bias by word choice and labeling. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pages 79–87, Online. Association for Computational Linguistics.
  32. Felix Hamborg and Karsten Donnay. 2021. NewsMTSC: A dataset for (multi-)target-dependent sentiment classification in political news articles. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1663–1675, Online. Association for Computational Linguistics.
  33. An empirical study of metrics to measure representational harms in pre-trained language models. In Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023), pages 121–134, Toronto, Canada. Association for Computational Linguistics.
  34. Survey of hallucination in natural language generation. ACM Computing Surveys, 55(12):1–38.
  35. CommunityLM: Probing partisan worldviews from language models. In Proceedings of the 29th International Conference on Computational Linguistics, pages 6818–6826, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
  36. Kristen Johnson and Dan Goldwasser. 2016. Identifying stance by analyzing political discourse on Twitter. In Proceedings of the First Workshop on NLP and Computational Social Science, pages 66–75, Austin, Texas. Association for Computational Linguistics.
  37. Lalitha Kameswari and Radhika Mamidi. 2021. Towards quantifying magnitude of political bias in news articles using a novel annotation schema. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 671–678, Held Online. INCOMA Ltd.
  38. Solar 10.7b: Scaling large language models with simple yet effective depth up-scaling.
  39. Language generation models can cause harm: So what can we do about it? an actionable survey. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 3299–3321, Dubrovnik, Croatia. Association for Computational Linguistics.
  40. NeuS: Neutral multi-news summarization for mitigating framing bias. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3131–3148, Seattle, United States. Association for Computational Linguistics.
  41. Quantifying and alleviating political bias in language models. Artificial Intelligence, 304:103654.
  42. Mitigating political bias in language models through reinforced calibration. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 14857–14866.
  43. Trustworthy llms: a survey and guideline for evaluating large language models’ alignment. arXiv preprint arXiv:2308.05374.
  44. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692.
  45. More human than human: Measuring chatgpt political bias. Public Choice, 198(1):3–23.
  46. StereoSet: Measuring stereotypical bias in pretrained language models. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 5356–5371, Online. Association for Computational Linguistics.
  47. Discovering language model behaviors with model-written evaluations. In Findings of the Association for Computational Linguistics: ACL 2023, pages 13387–13434, Toronto, Canada. Association for Computational Linguistics.
  48. Beyond binary labels: Political ideology prediction of Twitter users. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 729–740, Vancouver, Canada. Association for Computational Linguistics.
  49. Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence embeddings using Siamese BERT-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3982–3992, Hong Kong, China. Association for Computational Linguistics.
  50. Shamik Roy and Dan Goldwasser. 2020. Weakly supervised learning of nuanced frames for analyzing polarization in news media. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7698–7716, Online. Association for Computational Linguistics.
  51. David Rozado. 2023. The political biases of chatgpt. Social Sciences, 12(3):148.
  52. David Rozado. 2024. The political preferences of llms.
  53. Social media news communities: gatekeeping, coverage, and statement bias. In Proceedings of the 22nd ACM international conference on Information & Knowledge Management, pages 1679–1684.
  54. Dietram A Scheufele. 1999. Framing as a theory of media effects. Journal of communication, 49(1):103–122.
  55. Large pre-trained language models contain human-like biases of what is right and wrong to do. Nature Machine Intelligence, 4(3):258–268.
  56. Jais and jais-chat: Arabic-centric foundation and instruction-tuned open generative large language models. arXiv preprint arXiv:2308.16149.
  57. Societal biases in language generation: Progress and challenges. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 4275–4293, Online. Association for Computational Linguistics.
  58. “I’m sorry to hear that”: Finding new biases in language models with a holistic descriptor dataset. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 9180–9211, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
  59. Irene Solaiman and Christy Dennison. 2021. Process for adapting language models to society (palms) with values-targeted datasets. Advances in Neural Information Processing Systems, 34:5861–5873.
  60. Neural media bias detection using distant supervision with BABE - bias annotations by experts. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 1166–1177, Punta Cana, Dominican Republic. Association for Computational Linguistics.
  61. No word embedding model is perfect: Evaluating the representation accuracy for social bias in the media. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 2081–2093, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
  62. Natalie Jomini Stroud. 2010. Polarization and partisan selective exposure. Journal of communication, 60(3):556–576.
  63. BERTScore is unfair: On social bias in language model-based metrics for text generation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3726–3739, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
  64. Erik F. Tjong Kim Sang and Fien De Meulder. 2003. Introduction to the CoNLL-2003 shared task: Language-independent named entity recognition. In Proceedings of the Seventh Conference on Natural Language Learning at HLT-NAACL 2003, pages 142–147.
  65. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288.
  66. Dror Walter and Yotam Ophir. 2019. News frame analysis: An inductive mixed-method computational approach. Communication Methods and Measures, 13(4):248–266.
  67. Ethical and social risks of harm from language models. arXiv preprint arXiv:2112.04359.
  68. Judging LLM-as-a-judge with MT-bench and chatbot arena. In Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track.
  69. Caleb Ziems and Diyi Yang. 2021. To protect and to serve? analyzing entity-centric framing of police violence. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 957–976, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Citations (16)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up

Tweets

Sign up for free to view the 3 tweets with 7 likes about this paper.

Sign Up for Free