Ramona Comanescu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ramona Comanescu has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Abdullah Zaini
Verily, Cambridge, USA
1 shared publication Alexander S. Vezhnevets
Google DeepMind, Google UK Ltd
1 shared publication- Anushe Sheikh
AI71, Abu Dhabi, United Arab Emirates
1 shared publication - Ben Coppin
Google DeepMind, Google UK Ltd
1 shared publication - Cassandra Parent
Massachusetts Institute of Technology, Cambridge, USA
1 shared publication - David Yanni
Google, Cambridge, USA
1 shared publication
Latest Publications
- Open Access
- 25 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 2025-2054
Hedging and Non-Affirmation: Quantifying LLM Alignment on Questions of Human Rights
- 25 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 2025-2054
Open AccessHedging and Non-Affirmation: Quantifying LLM Alignment on Questions of Human Rights
- Open Access
- 16 June 2025
- Published by National Academy of Sciences in Proceedings of the National Academy of Sciences
- Vol. 122 (25)
Perceptual interventions ameliorate statistical discrimination in learning agents
Choosing social partners is a potentially demanding task which involves paying attention to the right information while disregarding salient but possibly irrelevant features. The resultant trade-off between cost of evaluation and quality of decisions can lead to undesired bias. Information-processing abilities mediate this trade-off, where individuals with higher ability choose better partners leading to higher performance. By altering the salience of features, technology can modulate the effect of information-processing limits, potentially increasing or decreasing undesired biases. Here, we use game theory and multiagent reinforcement learning to investigate how undesired biases emerge, and how a technological layer (in the form of a perceptual intervention) between individuals and their environment can ameliorate such biases. Our results show that a perceptual intervention designed to increase the salience of outcome-relevant features can reduce bias in agents making partner choice decisions. Individuals learning with a perceptual intervention showed less bias due to decreased reliance on features that only spuriously correlate with behavior. Mechanistically, the perceptual intervention effectively increased the information-processing abilities of the individuals. Our results highlight the benefit of using multiagent reinforcement learning to model theoretically grounded social behaviors, particularly when real-world complexity prohibits fully analytical approaches.
- 16 June 2025
- Published by National Academy of Sciences in Proceedings of the National Academy of Sciences
- Vol. 122 (25)
Open AccessPerceptual interventions ameliorate statistical discrimination in learning agents
Choosing social partners is a potentially demanding task which involves paying attention to the right information while disregarding salient but possibly irrelevant features. The resultant trade-off between cost of evaluation and quality of decisions can lead to undesired bias. Information-processing abilities mediate this trade-off, where individuals with higher ability choose better partners leading to higher performance. By altering the salience of features, technology can modulate the effect of information-processing limits, potentially increasing or decreasing undesired biases. Here, we use game theory and multiagent reinforcement learning to investigate how undesired biases emerge, and how a technological layer (in the form of a perceptual intervention) between individuals and their environment can ameliorate such biases. Our results show that a perceptual intervention designed to increase the salience of outcome-relevant features can reduce bias in agents making partner choice decisions. Individuals learning with a perceptual intervention showed less bias due to decreased reliance on features that only spuriously correlate with behavior. Mechanistically, the perceptual intervention effectively increased the information-processing abilities of the individuals. Our results highlight the benefit of using multiagent reinforcement learning to model theoretically grounded social behaviors, particularly when real-world complexity prohibits fully analytical approaches.