Home Knowledge Base Pluralistic

Pluralistic

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Adaptive Pluralistic Alignment: A pipeline for dynamic artificial democracy

Announce Type: replace Abstract: 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 aligned AI systems to track evolving values and avoid value lock-in without repeating costly pretraining or large-scale data collection. APA has three stages: (1) learning compact personalized reward models via low-rank...

arXiv CS 2d ago

Agent Economics: An Entropy-Controlled Pluralistic Alignment Framework for Preventing Artificial Hivemind in Autonomous Agents

arXiv:2606.09039v1 Announce Type: new Abstract: This study proposes the Behavioral Protocol Framework (BPF), an entropy-controlled pluralistic alignment framework designed to address two critical challenges in autonomous agent economies: the hivemind effect arising from excessive strategic convergence among agents and the lack of transparency in autonomous decision-making processes. The proposed BPF consists of three core modules: Mentalizing-based Social Intelligence (MbSI) grounded in...

arXiv CS 1d ago

Memetic Capture: A Pluralistic Policy Framework for Governing AI-Driven Cultural Disempowerment

Announce Type: new Abstract: Culture is the most insidious vector of gradual human disempowerment by AI: unlike economic or political displacement, cultural displacement attacks the very preferences and values through which humans recognise and resist disempowerment itself. We argue that existing AI governance frameworks suffer from a critical blind spot by treating cultural impact as secondary to economic and safety concerns. This paper develops \emph{memetic capture} as a unifying concept...

arXiv CS 1d ago

DiverAge: Reliable Pluralistic Face Aging with Cross-Age Identity Relation Guidance

arXiv:2606.04881v1 Announce Type: new Abstract: Face aging plays an important role in long-term biometric analysis, cross-age identity verification, and forensic identity analysis. Since the same subject may exhibit multiple plausible appearances at a target age due to genetic, environmental, and lifestyle factors, face aging is inherently a one-to-many generation problem.

arXiv CS 6d ago

A Persona-Based Evaluation Framework for Pluralistic Alignment in Generative AI

arXiv:2605.31021v1 Announce Type: new Abstract: Current alignment paradigms for generative artificial intelligence rely predominantly on monolithic benchmarking frameworks that reduce the plurality of human judgment to aggregated statistical baselines, thereby obscuring cultural, demographic, and contextual variability in evaluation. We introduce a state-space constrained emulation framework for AI evaluation that replaces singular assessment functions with a structured manifold of synthetic...

arXiv CS 9d ago

Pluralistic Leaderboards

arXiv:2606.02547v1 Announce Type: new Abstract: Recent leaderboard-based evaluations of large language models aggregate user feedback by fitting a Bradley--Terry model to pairwise comparisons, producing a single global ranking based on a latent quality score. While appealing for its simplicity, this approach is incompatible with heterogeneous preferences: when LLMs are used across diverse tasks and use cases, users who favor fundamentally different model behaviors can be systematically...

arXiv CS 8d ago

VALUEFLOW: Toward Pluralistic and Steerable Value-based Alignment in Large Language Models

Announce Type: replace Abstract: Aligning Large Language Models (LLMs) with the diverse spectrum of human values remains a central challenge: preference-based methods often fail to capture deeper motivational principles. Value-based approaches offer a more principled path, yet three gaps persist: extraction often ignores hierarchical structure, evaluation detects presence but not calibrated intensity, and the steerability of LLMs at controlled intensities remains insufficiently understood....

arXiv CS 2d ago

Coherence Maximization Improves Pluralistic Alignment

arXiv:2606.03110v1 Announce Type: new Abstract: Aligning AI systems with diverse human values requires value specifications grounded in concrete examples, but generating such examples without extensive human supervision remains an open challenge. We investigate what makes these examples effective, using Internal Coherence Maximization (ICM) -- which infers labels by maximizing their mutual predictability -- to generate persona-specific examples that steer a model toward a target group's...

arXiv CS 7d ago

Coherence Maximization Improves Pluralistic Alignment

arXiv:2606.03110v2 Announce Type: replace Abstract: Aligning AI systems with diverse human values requires value specifications grounded in concrete examples, but generating such examples without extensive human supervision remains an open challenge. We investigate what makes these examples effective, using Internal Coherence Maximization (ICM) -- which infers labels by maximizing their mutual predictability -- to generate persona-specific examples that steer a model toward a target group's...

arXiv CS 6d ago

Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences

arXiv:2605.07724v2 Announce Type: replace Abstract: Recursive retraining of generative models poses a critical representation challenge: when synthetic outputs are curated based on a fixed reward signal, the model tends to collapse onto a narrow set of outputs that over-optimize that objective. Prior work suggests that such collapse is unavoidable without adding real data into the mix. We revisit this conclusion from an alignment perspective and show that collapse can be mitigated through...

arXiv CS 6d ago