14 accepted papers
The standard way to evaluate language models on subjective tasks is through pairwise comparisons: an annotator chooses the "better" of two model responses for a given prompt. These comparisons are then aggregated into a single ranking via the Bradley–Terry (BT) framework, forcing heterogeneous prefe…
A *citizens' assembly* is a group of people who are randomly selected to represent a larger population in a deliberation. While this approach has successfully strengthened democracy, it has certain limitations that suggest the need for assemblies to form and associate more organically. In response,…
Current alignment pipelines presume a single, universal notion of desirable behavior. However, human preferences often diverge across users, contexts, and cultures. As a result, disagreement collapses into the majority signal and minority perspectives are discounted. To address this, we propose r…
The proportional veto principle, which captures the idea that a candidate vetoed by a large group of voters should not be chosen, has been studied for ranked ballots in single-winner voting. We introduce a version of this principle for approval ballots, which we call flexible-voter representation (F
In the context of reinforcement learning from human feedback (RLHF), the reward function is generally derived from maximum likelihood estimation of a random utility model based on pairwise comparisons made by humans. The problem of learning a reward function is one of preference aggregation that, we…
In many social choice applications, information about individuals' preferences can only be elicited using a limited number of pairwise comparisons. In these cases, the task is twofold: we must first choose the queries, and then second, we must aggregate the responses to choose an outcome. We study t…
Platforms for online civic participation rely heavily on methods for condensing thousands of comments into a relevant handful, based on whether participants agree or disagree with them. These methods should guarantee fair representation of the participants, as their outcomes may affect the health of…
In voting theory, when voters have ranked preferences over candidates, the celebrated Gibbard-Satterthwaite Theorem essentially rules out the existence of reasonable strategyproof methods for picking a winner. What if we weaken strategyproofness to only hold for Bayesian voters with beliefs over oth…
We study market interactions in which buyers are allowed to credibly reveal partial information about their types to the seller. Previous recent work has studied the special case of one buyer and one good, showing that such communication can simultaneously improve social welfare and ex ante buyer ut…
A fundamental question in social choice and multi-agent systems is aggregating ordinal preferences expressed by agents into a measurably prudent collective choice. A promising line of recent work views ordinal preferences as a proxy for underlying cardinal preferences. It aims to optimize distortion…
We consider the fundamental problem of fairly and efficiently allocating $T$ indivisible items among $n$ agents with additive preferences. The items become available over a sequence of rounds, and every item must be allocated immediately and irrevocably before the next one arrives. Previous work sho…
Aggregating opinions of a collection of agents is a question of interest to a broad array of researchers, ranging from ensemble-learning theorists to political scientists designing democratic institutions. This work investigates the optimal number of agents needed to decide on a binary issue under m…
We revisit the fundamental problem of predicting a binary ground truth based on independent binary judgments provided by experts. When the accuracy levels of the experts are known, the problem can be solved easily through maximum likelihood estimation. We consider, however, a setting in which we are…
We study the fundamental problem of allocating indivisible goods to agents with additive preferences. We consider eliciting from each agent only a ranking of her k most preferred goods instead of her full cardinal valuations. We characterize the amount of preference information that must be elicited…