Related papers: Question the Questions: Auditing Representation in…
LLMs are among the most advanced tools ever devised for understanding and generating natural language. Democratic deliberation and decision-making involve, at several distinct stages, the production and comprehension of language. So it is…
We seek to democratise public-opinion research by providing practitioners with a general methodology to make representative inference from cheap, high-frequency, highly unrepresentative samples. We focus specifically on samples which are…
Modern democracies face a critical issue of declining citizen participation in decision-making. Online discussion forums are an important avenue for enhancing citizen participation. This thesis proposal 1) identifies the challenges involved…
Multi-agent systems where Large Language Models (LLMs) deliberate to form consensus have gained significant attention, yet their practical value over simpler methods remains under-scrutinized. We introduce DELIBERATIONBENCH, a controlled…
We introduce Debate Speech Evaluation as a novel and challenging benchmark for assessing LLM judges. Evaluating debate speeches requires a deep understanding of the speech at multiple levels, including argument strength and relevance, the…
AI audits are an increasingly popular mechanism for algorithmic accountability; however, they remain poorly defined. Without a clear understanding of audit practices, let alone widely used standards or regulatory guidance, claims that an AI…
As the rapid proliferation of AI systems and harms spurs efforts in AI governance around the world, prioritizing among competing policy options has become increasingly challenging for policymakers and researchers. We introduce a methodology…
Elections are the central institution of democratic processes, and often the elected body -- in either public or private governance -- is a committee of individuals. To ensure the legitimacy of elected bodies, the electoral processes should…
Question answering (QA) systems are among the most important and rapidly developing research topics in natural language processing (NLP). A reason, therefore, is that a QA system allows humans to interact more naturally with a machine,…
A recent work by Hern\'andez et al. introduced a networked voting rule supported by a trust-based social network, where indications of possible representatives were based on individuals opinions. Individual contributions went beyond a…
Democratic processes increasingly aim to integrate large-scale voting with face-to-face deliberation, addressing the challenge of reconciling individual preferences with collective decision-making. This work introduces new methods that use…
The mathematical study of voting, social choice theory, has traditionally only been applicable to choices among a few predetermined alternatives, but not to open-ended decisions such as collectively selecting a textual statement. We…
Risk-limiting audits (RLAs) are techniques for verifying the outcomes of large elections. While they provide rigorous guarantees of correctness, widespread adoption has been impeded by both efficiency concerns and the fact they offer…
Deliberative democracy arguably leads to better collective decisions, but is fundamentally constrained by human attention and bandwidth. While recent AI-mediated deliberations scale participation by synthesizing inputs from many humans,…
Recent years have seen an increase in the use of online deliberation platforms (DPs). One of the main objectives of DPs is to enhance democratic participation, by allowing citizens to post, comment, and vote on policy proposals. But in what…
Justified representation (JR) is a standard notion of representation in multiwinner approval voting. Not only does a JR committee always exist, but previous work has also shown through experiments that the JR condition can typically be…
We present an online deliberation system using mutual evaluation in order to collaboratively develop solutions. Participants submit their proposals and evaluate each other's proposals; some of them may then be invited by the system to…
Large language models (LLMs) have demonstrated their remarkable performance across various language understanding tasks. While emerging benchmarks have been proposed to evaluate LLMs in various domains such as mathematics and computer…
Large language models (LLMs) have proven to be highly effective for solving complex reasoning tasks. Surprisingly, their capabilities can often be improved by iterating on previously generated solutions. In this context, a reasoning plan…
Large Language Models (LLMs) have in recent years demonstrated impressive prowess in natural language generation. A common practice to improve generation diversity is to sample multiple outputs from the model. However, there lacks a simple…