Share this page:

Societal Biases in Language Generation: Progress and Challenges

Emily Sheng, Kai-Wei Chang, Prem Natarajan, and Nanyun Peng, in ACL, 2021.

Download the full text

Abstract

Technology for language generation has advanced rapidly, spurred by advancements in pre-training large models on massive amounts of data and the need for intelligent agents to communicate in a natural manner. While techniques can effectively generate fluent text, they can also produce undesirable societal biases that can have a disproportionately negative impact on marginalized populations. Language generation presents unique challenges for biases in terms of direct user interaction and the structure of decoding techniques. To better understand these challenges, we present a survey on societal biases in language generation, focusing on how data and techniques contribute to biases and progress towards reducing biases. Motivated by a lack of studies on biases from decoding techniques, we also conduct experiments to quantify the effects of these techniques. By further discussing general trends and open challenges, we call to attention promising directions for research and the importance of fairness and inclusivity considerations for language generation applications.

Bib Entry

@inproceedings{sheng2021societal,
  title = {Societal Biases in Language Generation: Progress and Challenges},
  author = {Sheng, Emily and Chang, Kai-Wei and Natarajan, Prem and Peng, Nanyun},
  booktitle = {ACL},
  year = {2021}
}

Related Publications

  1. InsideOut: Measuring and Mitigating Insider-Outsider Bias in Interview Script Generation, ACL, 2026
  2. White Men Lead, Black Women Help? Benchmarking Language Agency Social Biases in LLMs, ACL, 2025
  3. A Meta-Evaluation of Measuring LLM Misgendering, COLM 2025, 2025
  4. Controllable Generation via Locally Constrained Resampling, ICLR, 2025
  5. On Localizing and Deleting Toxic Memories in Large Language Models, NAACL-Finding, 2025
  6. Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification, EMNLP-Finding, 2024
  7. Mitigating Bias for Question Answering Models by Tracking Bias Influence, NAACL, 2024
  8. Are you talking to ['xem'] or ['x', 'em']? On Tokenization and Addressing Misgendering in LLMs with Pronoun Tokenization Parity, NAACL-Findings, 2024
  9. The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarks, ACL (short), 2023
  10. Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems, EMNLP-Finding, 2023
  11. Kelly is a Warm Person, Joseph is a Role Model: Gender Biases in LLM-Generated Reference Letters, EMNLP-Findings, 2023
  12. Factoring the Matrix of Domination: A Critical Review and Reimagination of Intersectionality in AI Fairness, AIES, 2023
  13. How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions?, EMNLP (Short), 2022
  14. On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations, ACL (short), 2022
  15. "Nice Try, Kiddo": Investigating Ad Hominems in Dialogue Responses, NAACL, 2021
  16. BOLD: Dataset and metrics for measuring biases in open-ended language generation, FAccT, 2021
  17. Towards Controllable Biases in Language Generation, EMNLP-Finding, 2020
  18. The Woman Worked as a Babysitter: On Biases in Language Generation, EMNLP (short), 2019