Related papers: Fairness Auditing with Multi-Agent Collaboration

With the recent development of natural language generation models - termed as large language models (LLMs) - a potential use case has opened up to improve the way that humans interact with robot assistants. These LLMs should be able to…

Multi-agent LLM workflows route inference through specialized roles to lift end-task accuracy, but jointly training those roles with reinforcement learning is unstable in ways that are poorly understood. We study when end-to-end RL training…

Much of the success of multi-agent debates depends on carefully choosing the right parameters. The decision-making protocol stands out as it can highly impact final model answers, depending on how decisions are reached. Systematic…

LLMs generate buggy code: 29.6% of SWE-bench solved patches fail, 62% of BaxBench solutions have vulnerabilities, and existing tools only catch 65% of bugs with 35% false positives. We built CodeX-Verify, a multi-agent system that uses four…

Alignment research focuses on making individual AI systems reliable. Human institutions achieve reliable collective behaviour differently: they mitigate the risk posed by misaligned individuals through organisational structure. Multi-agent…

Advances in inference methods have enabled language models to improve their predictions without additional training. These methods often prioritize raw performance over cost-effective compute usage. However, computational efficiency is key…

In this work, we introduce a novel metric for auditing group fairness in ranked lists. Our approach offers two benefits compared to the state of the art. First, we offer a blueprint for modeling of user attention. Rather than assuming a…

LLM-based agents increasingly coordinate decisions in multi-agent systems, often attaching natural-language reasoning to actions. However, reasoning is neither free nor automatically reliable: it incurs computational cost and, without…

We consider a novel setting where a set of items are matched to the same set of agents repeatedly over multiple rounds. Each agent gets exactly one item per round, which brings interesting challenges to finding efficient and/or fair {\em…

With growing applications of Machine Learning (ML) techniques in the real world, it is highly important to ensure that these models work in an equitable manner. One main step in ensuring fairness is to effectively measure fairness, and to…

Systems integration is a difficult matter particularly when its components are varied. The problem becomes even more difficult when such components are heterogeneous such as humans, robots and software systems. Currently, the humans are…

We study a multiagent learning problem where agents can either learn via repeated interactions, or can follow the advice of a mediator who suggests possible actions to take. We present an algorithmthat each agent can use so that, with high…

In sensitive contexts, providers of machine learning algorithms are increasingly required to give explanations for their algorithms' decisions. However, explanation receivers might not trust the provider, who potentially could output…

We propose the use of Agent Based Models (ABMs) inside a reinforcement learning framework in order to better understand the relationship between automated decision making tools, fairness-inspired statistical constraints, and the social…

Social computation, whether in the form of searches performed by swarms of agents or collective predictions of markets, often supplies remarkably good solutions to complex problems. In many examples, individuals trying to solve a problem…

The justice system has increasingly employed AI techniques to enhance efficiency, yet limitations remain in improving the quality of decision-making, particularly regarding transparency and explainability needed to uphold public trust in…

We propose a fairness measure relaxing the equality conditions in the popular equal odds fairness regime for classification. We design an iterative, model-agnostic, grid-based heuristic that calibrates the outcomes per sensitive attribute…

Machine learning models are increasingly being used in important decision-making software such as approving bank loans, recommending criminal sentencing, hiring employees, and so on. It is important to ensure the fairness of these models so…

Distributed aggregative optimization methods are gaining increased traction due to their ability to address cooperative control and optimization problems, where the objective function of each agent depends not only on its own decision…

Large Language Model (LLM)-based multi-agent systems are increasingly used to simulate human interactions and solve collaborative tasks. A common practice is to assign agents with personas to encourage behavioral diversity. However, this…