112 citations · 146 across the 13 of their papers we have counts for
15 papers
Emergent Misaligned Communication in Long-Horizon Multi-Agent LLM Commerce
Zeyuan Li, Lukas Petersson, Alessandro Acquisti +1
Frontier LLM agents increasingly transact on behalf of separate principals, often using natural language rather than structured APIs. Much of the safety literature studies misalign…
Benchmarking Overton Pluralism in LLMs
Elinor Poole-Dayan, Jiayi Wu, Taylor Sorensen +2
We introduce OVERTONBENCH, a novel framework for measuring Overton pluralism in LLMs--the extent to which diverse viewpoints are represented in model outputs. We (i) formalize Over…
Can AI Truly Represent Your Voice in Deliberations? A Comprehensive Study of Large-Scale Opinion Aggregation with LLMs
Shenzhe Zhu, Shu Yang, Michiel A. Bakker +2
Large-scale public deliberations generate thousands of free-form contributions that must be synthesized into representative and neutral summaries for policy use. While LLMs have be…
RE-PO: Robust Enhanced Policy Optimization as a General Framework for LLM Alignment
Xiaoyang Cao, Zelai Xu, Mo Guang +4
Standard human preference-based alignment methods, such as Reinforcement Learning from Human Feedback (RLHF), are a cornerstone for aligning large language models (LLMs) with human…
Scaling Human Judgment in Community Notes with LLMs
Haiwen Li, Soham De, Manon Revel +6
This paper argues for a new paradigm for Community Notes in the LLM era: an open ecosystem where both humans and LLMs can write notes, and the decision of which notes are helpful e…
Supernotes: Driving Consensus in Crowd-Sourced Fact-Checking
Soham De, Michiel A. Bakker, Jay Baxter +1
X's Community Notes, a crowd-sourced fact-checking system, allows users to annotate potentially misleading posts. Notes rated as helpful by a diverse set of users are prominently d…
Democratic AI is Possible. The Democracy Levels Framework Shows How It Might Work
Aviv Ovadya, Kyle Redman, Luke Thorburn +11
This position paper argues that effectively "democratizing AI" requires democratic governance and alignment of AI, and that this is particularly valuable for decisions with systemi…
Fine-tuning language models to find agreement among humans with diverse preferences
Michiel A. Bakker, Martin J. Chadwick, Hannah R. Sheahan +8
Recent work in large language modeling (LLMs) has used fine-tuning to align outputs with the preferences of a prototypical user. This work assumes that human preferences are static…
Statistical discrimination in learning agents
Edgar A. Duéñez-Guzmán, Kevin R. McKee, Yiran Mao +9
Undesired bias afflicts both human and algorithmic decision making, and may be especially prevalent when information processing trade-offs incentivize the use of heuristics. One pr…
Modelling Cooperation in Network Games with Spatio-Temporal Complexity
Michiel A. Bakker, Richard Everett, Laura Weidinger +4
The real world is awash with multi-agent problems that require collective action by self-interested agents, from the routing of packets across a computer network to the management…
DADI: Dynamic Discovery of Fair Information with Adversarial Reinforcement Learning
Michiel A. Bakker, Duy Patrick Tu, Humberto Riverón Valdés +4
We introduce a framework for dynamic adversarial discovery of information (DADI), motivated by a scenario where information (a feature set) is used by third parties with unknown ob…
Sherlock: A Deep Learning Approach to Semantic Data Type Detection
Madelon Hulsebos, Kevin Hu, Michiel Bakker +5
Correctly detecting the semantic type of data columns is crucial for data science tasks such as automated data cleaning, schema matching, and data discovery. Existing data preparat…
VizNet: Towards A Large-Scale Visualization Learning and Benchmarking Repository
Kevin Hu, Neil Gaikwad, Michiel Bakker +7
Researchers currently rely on ad hoc datasets to train automated visualization tools and evaluate the effectiveness of visualization designs. These exemplars often lack the charact…
Active Fairness in Algorithmic Decision Making
Alejandro Noriega-Campero, Michiel A. Bakker, Bernardo Garcia-Bulle +1
Society increasingly relies on machine learning models for automated decision making. Yet, efficiency gains from automation have come paired with concern for algorithmic discrimina…
VizML: A Machine Learning Approach to Visualization Recommendation
Kevin Z. Hu, Michiel A. Bakker, Stephen Li +2
Data visualization should be accessible for all analysts with data, not just the few with technical expertise. Visualization recommender systems aim to lower the barrier to explori…