Author name cluster

Manon Revel

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

ICML Conference 2025 Conference Paper

Representative Ranking for Deliberation in the Public Sphere

Manon Revel
Smitha Milli
Tyler Lu
Jamelle Watson-Daniels
Maximilian Nickel

Online comment sections, such as those on news sites or social media, have the potential to foster informal public deliberation, However, this potential is often undermined by the frequency of toxic or low-quality exchanges that occur in these settings. To combat this, platforms increasingly leverage algorithmic ranking to facilitate higher-quality discussions, e. g. , by using civility classifiers or forms of prosocial ranking. Yet, these interventions may also inadvertently reduce the visibility of legitimate viewpoints, undermining another key aspect of deliberation: representation of diverse views. We seek to remedy this problem by introducing guarantees of representation into these methods. In particular, we adopt the notion of justified representation (JR) from the social choice literature and incorporate a JR constraint into the comment ranking setting. We find that enforcing JR leads to greater inclusion of diverse viewpoints while still being compatible with optimizing for user engagement or other measures of conversational quality.

Details

AAAI Conference 2025 Conference Paper

SEAL: Systematic Error Analysis for Value ALignment

Manon Revel
Matteo Cargnelutti
Tyna Eloundou
Greg Leppert

Reinforcement Learning from Human Feedback (RLHF) aligns language models (LMs) with human values by training reward models (RMs) on binary preferences and using these RMs to fine-tune the base models. Despite its importance, the internal mechanisms of RLHF remain poorly understood. This paper introduces new metrics to evaluate RM effectiveness, focusing on feature imprint, feature resistance, and feature robustness. We categorize alignment datasets into target features (desired values) and spoiler features (undesired concepts). By regressing RM scores against these features, we quantify the extent to which RMs reward them -- feature imprint. We define alignment resistance as the proportion of the preference dataset where RMs fail to match human preferences, and we assess alignment robustness by analyzing RM responses to slightly perturbed texts. Our experiments, utilizing open-source components like the Anthropic/hh-rlhf preference dataset and OpenAssistant RMs, reveal significant imprints of target features and a notable sensitivity to spoiler features. We observed a 26% resistance incidence in portions of the dataset where LM labelers disagreed with human preferences. We also find that misalignment stems from confusing entries in the alignment dataset. These findings underscore the importance of scrutinizing both RMs and alignment datasets for a deeper understanding of value alignment.

PDF Details DOI

AAMAS Conference 2024 Conference Paper

Selecting Representative Bodies: An Axiomatic View

Manon Revel
Niclas Boehmer
Rachael Colley
Markus Brill
Piotr Faliszewski
Edith Elkind

As the world’s democratic institutions are challenged by dissatisfied citizens, political scientists and computer scientists have proposed and analyzed various (innovative) methods to select representative bodies, a crucial task in every democracy. However, a unified framework to analyze and compare different selection mechanisms is largely missing. To address this gap, we advocate employing concepts and tools from computational social choice to devise a model in which different selection mechanisms can be formalized. Such a model would allow for conceptualizing and evaluating desirable representation axioms. We make the first step in this direction by proposing a unifying mathematical formulation of different selection mechanisms as well as various social-choice-inspired axioms such as proportionality and monotonicity.

PDF

AAAI Conference 2022 Conference Paper

How Many Representatives Do We Need? The Optimal Size of a Congress Voting on Binary Issues

Manon Revel
Tao Lin
Daniel Halpern

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 majority rule. We take an epistemic view where the issue at hand has a ground truth “correct” outcome and each one of n voters votes correctly with a fixed probability, known as their competence level or competence. These competencies come from a fixed distribution D. Observing the competencies, we must choose a specific group that will represent the population. Finally, voters sample a decision (either correct or not), and the group is correct as long as more than half the chosen representatives voted correctly. Assuming that we can identify the best experts, i. e. , those with the highest competence, to form an epistemic congress we find that the optimal congress size should be linear in the population size. This result is striking because it holds even when allowing the top representatives to become arbitrarily accurate, choosing the correct outcome with probabilities approaching 1. We then analyze real-world data, observing that the actual sizes of representative bodies are much smaller than the optimal ones our theoretical results suggest. We conclude by examining under what conditions congresses of sub-optimal sizes would still outperform direct democracy, in which all voters vote. We find that a small congress would beat direct democracy if the rate at which the societal bias towards the ground truth decreases with the population size fast enough, and we quantify the speed needed for constant and polynomial congress sizes.

PDF Details