Related papers: MAP: Multi-Human-Value Alignment Palette
Generative foundation models are susceptible to implicit biases that can arise from extensive unsupervised training data. Such biases can produce suboptimal samples, skewed outcomes, and unfairness, with potentially serious consequences.…
Prevailing alignment methods target a fixed set of preferences and therefore risk forcing value lock-in as societal norms evolve over time. We introduce Adaptive Pluralistic Alignment (APA), a modular pipeline for updating pluralistically…
We propose a data-driven framework to enable the modeling and optimization of human-machine interaction processes, e.g., systems aimed at assisting humans in decision-making or learning, work-load allocation, and interactive advertising.…
The wide exploration of large language models (LLMs) raises the awareness of alignment between healthcare stakeholder preferences and model outputs. This alignment becomes a crucial foundation to empower the healthcare workflow effectively,…
Background: There is a growing awareness of the importance of human values (e.g., inclusiveness, privacy) in software systems. However, there are no practical tools to support the integration of human values during software development. We…
This paper introduces a novel visual mapping methodology for assessing strategic alignment in national artificial intelligence policies. The proliferation of AI strategies across countries has created an urgent need for analytical…
Large Language Models (LLMs) are typically aligned with human values using preference data or predefined principles such as helpfulness, honesty, and harmlessness. However, as AI systems progress toward Artificial General Intelligence (AGI)…
The holy grail of LLM personalization is a single LLM for each user, perfectly aligned with that user's preferences. However, maintaining a separate LLM per user is impractical due to constraints on compute, memory, and system complexity.…
Aligning AI systems with human values fundamentally relies on effective human feedback. While significant research has addressed training algorithms, the role of user interface is often overlooked and only treated as an implementation…
Recent advances in data-centric medical AI have produced highly accurate diagnostic systems, but the emphasis on data curation and performance metrics has not translated into widespread clinical adoption. We conjecture that this limited…
We propose incorporating human labelers in a model fine-tuning system that provides immediate user feedback. In our framework, human labelers can interactively query model predictions on unlabeled data, choose which data to label, and see…
Matching is a task at the heart of any data integration process, aimed at identifying correspondences among data elements. Matching problems were traditionally solved in a semi-automatic manner, with correspondences being generated by…
As we consider entrusting Large Language Models (LLMs) with key societal and decision-making roles, measuring their alignment with human cognition becomes critical. This requires methods that can assess how these systems represent…
Multi-Agent Path Finding (MAPF) is a fundamental coordination problem in large-scale robotic and cyber-physical systems, where multiple agents must compute conflict-free trajectories with limited computational and communication resources.…
A comparison between human and Generative AI decision-making attributes in complex health services is a knowledge gap in the literature, at present. Humans may possess unique attributes beneficial to decision-making in complex health…
Evolution has produced an astonishing diversity of species, each filling a different niche. Algorithms like MAP-Elites mimic this divergent evolutionary process to find a set of behaviorally diverse but high-performing solutions, called the…
As large language models (LLMs) become increasingly integrated into critical applications, aligning their behavior with human values presents significant challenges. Current methods, such as Reinforcement Learning from Human Feedback…
AI is becoming increasingly integrated into everyday life, both in professional work environments and in leisure and entertainment contexts. This integration requires AI to move beyond acting as an assistant for informational or…
While multiagent systems have shown promise for tackling complex tasks via specialization, finetuning multiple agents simultaneously faces two key challenges: (1) credit assignment across agents, and (2) sample efficiency of expensive…
As artificial intelligence (AI) increasingly becomes an integral part of our societal and individual activities, there is a growing imperative to develop responsible AI solutions. Despite a diverse assortment of machine learning fairness…