Jessica Hoffmann
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jessica Hoffmann has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Ann Yuan
Google research
2 shared publications - Katrin Tomanek
Google research
2 shared publications - Lucas Dixon
Google research
2 shared publications - Maximilian Mozes
Google research
2 shared publications - Muhamed Kouate
Google research
2 shared publications - Nithum Thain
Harvard University MIT & NBER MIT
2 shared publications
Latest Publications
- Open Access
On Mitigating Affinity Bias through Bandits with Evolving Biased Feedback
Unconscious bias has been shown to influence how we assess our peers, with consequences for hiring, promotions and admissions. In this work, we focus on affinity bias, the component of unconscious bias which leads us to prefer people who are similar to us, despite no deliberate intention of favoritism. In a world where the people hired today become part of the hiring committee of tomorrow, we are particularly interested in understanding (and mitigating) how affinity bias affects this feedback loop. This problem has two distinctive features: 1) we only observe the biased value of a candidate, but we want to optimize with respect to their real value 2) the bias towards a candidate with a specific set of traits depends on the fraction of people in the hiring committee with the same set of traits. We introduce a new bandits variant that exhibits those two features, which we call affinity bandits. Unsurprisingly, classical algorithms such as UCB often fail to identify the best arm in this setting. We prove a new instance-dependent regret lower bound, which is larger than that in the standard bandit setting by a multiplicative function of $K$. Since we treat rewards that are time-varying and dependent on the policy's past actions, deriving this lower bound requires developing proof techniques beyond the standard bandit techniques. Finally, we design an elimination-style algorithm which nearly matches this regret, despite never observing the real rewards.Open AccessOn Mitigating Affinity Bias through Bandits with Evolving Biased Feedback
Unconscious bias has been shown to influence how we assess our peers, with consequences for hiring, promotions and admissions. In this work, we focus on affinity bias, the component of unconscious bias which leads us to prefer people who are similar to us, despite no deliberate intention of favoritism. In a world where the people hired today become part of the hiring committee of tomorrow, we are particularly interested in understanding (and mitigating) how affinity bias affects this feedback loop. This problem has two distinctive features: 1) we only observe the biased value of a candidate, but we want to optimize with respect to their real value 2) the bias towards a candidate with a specific set of traits depends on the fraction of people in the hiring committee with the same set of traits. We introduce a new bandits variant that exhibits those two features, which we call affinity bandits. Unsurprisingly, classical algorithms such as UCB often fail to identify the best arm in this setting. We prove a new instance-dependent regret lower bound, which is larger than that in the standard bandit setting by a multiplicative function of $K$. Since we treat rewards that are time-varying and dependent on the policy's past actions, deriving this lower bound requires developing proof techniques beyond the standard bandit techniques. Finally, we design an elimination-style algorithm which nearly matches this regret, despite never observing the real rewards. - Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 27426-27455
Improving Neutral Point-of-View Generation with Data- and Parameter-Efficient RL
Jessica Hoffmann, Christiane Ahlheim, Zac Yu, Aria Walfrand, Jarvis Jin, Marie Tano, Ahmad Beirami, Erin MacMurray van Liemt, Nithum Thain, Hakim Sidahmed, Lucas Dixon. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 27426-27455
Open AccessImproving Neutral Point-of-View Generation with Data- and Parameter-Efficient RL
Jessica Hoffmann, Christiane Ahlheim, Zac Yu, Aria Walfrand, Jarvis Jin, Marie Tano, Ahmad Beirami, Erin MacMurray van Liemt, Nithum Thain, Hakim Sidahmed, Lucas Dixon. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- Open Access
Towards Agile Text Classifiers for Everyone
Text-based safety classifiers are widely used for content moderation and increasingly to tune generative language model behavior - a topic of growing concern for the safety of digital assistants and chatbots. However, different policies require different classifiers, and safety policies themselves improve from iteration and adaptation. This paper introduces and evaluates methods for agile text classification, whereby classifiers are trained using small, targeted datasets that can be quickly developed for a particular policy. Experimenting with 7 datasets from three safety-related domains, comprising 15 annotation schemes, led to our key finding: prompt-tuning large language models, like PaLM 62B, with a labeled dataset of as few as 80 examples can achieve state-of-the-art performance. We argue that this enables a paradigm shift for text classification, especially for models supporting safer online discourse. Instead of collecting millions of examples to attempt to create universal safety classifiers over months or years, classifiers could be tuned using small datasets, created by individuals or small organizations, tailored for specific use cases, and iterated on and adapted in the time-span of a day.
Open AccessTowards Agile Text Classifiers for Everyone
Text-based safety classifiers are widely used for content moderation and increasingly to tune generative language model behavior - a topic of growing concern for the safety of digital assistants and chatbots. However, different policies require different classifiers, and safety policies themselves improve from iteration and adaptation. This paper introduces and evaluates methods for agile text classification, whereby classifiers are trained using small, targeted datasets that can be quickly developed for a particular policy. Experimenting with 7 datasets from three safety-related domains, comprising 15 annotation schemes, led to our key finding: prompt-tuning large language models, like PaLM 62B, with a labeled dataset of as few as 80 examples can achieve state-of-the-art performance. We argue that this enables a paradigm shift for text classification, especially for models supporting safer online discourse. Instead of collecting millions of examples to attempt to create universal safety classifiers over months or years, classifiers could be tuned using small datasets, created by individuals or small organizations, tailored for specific use cases, and iterated on and adapted in the time-span of a day.
- Open Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 400-414
Towards Agile Text Classifiers for Everyone
Maximilian Mozes, Jessica Hoffmann, Katrin Tomanek, Muhamed Kouate, Nithum Thain, Ann Yuan, Tolga Bolukbasi, Lucas Dixon. Findings of the Association for Computational Linguistics: EMNLP 2023. 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 400-414
Open AccessTowards Agile Text Classifiers for Everyone
Maximilian Mozes, Jessica Hoffmann, Katrin Tomanek, Muhamed Kouate, Nithum Thain, Ann Yuan, Tolga Bolukbasi, Lucas Dixon. Findings of the Association for Computational Linguistics: EMNLP 2023. 2023.