Social Alignment Reward
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Optimal Control Synthesis of Closed-Loop Recommendation Systems over Social Networks
arXiv:2603.10275v2 Announce Type: replace Abstract: This paper addresses the problem of designing recommendation systems for social networks and e-commerce platforms from a control-theoretic perspective. We treat the design of recommendation systems as a state-feedback infinite-horizon optimal control problem with a performance index that (i) rewards alignment and engagement, (ii) penalizes polarization and large deviations from an uncontrolled baseline, and (iii) regularizes exposure across...
Community-Aware Assessment of Social Textual Engagement and Resonance: A Human-Centric Perspective on User-Generated Content Evaluation
arXiv:2606.01897v3 Announce Type: replace Abstract: Traditional Video Quality Assessment (VQA) focuses narrowly on aesthetic fidelity, overlooking the complex social dynamics that define quality in User-Generated Content (UGC). In this work, we propose a paradigm shift from signal-centric metrics to human-centric resonance assessment. We introduce CASTER (Community-Aware Assessment of Social Textual Engagement and Resonance), a new task that evaluates whether a UGC item achieves positive...
Community-Aware Assessment of Social Textual Engagement and Resonance: A Human-Centric Perspective on User-Generated Content Evaluation
arXiv:2606.01897v1 Announce Type: new Abstract: Traditional Video Quality Assessment (VQA) focuses narrowly on aesthetic fidelity, overlooking the complex social dynamics that define quality in User-Generated Content (UGC). In this work, we propose a paradigm shift from signal-centric metrics to human-centric resonance assessment. We introduce CASTER (Community-Aware Assessment of Social Textual Engagement and Resonance), a new task that evaluates whether a UGC item achieves positive...
Community-Aware Assessment of Social Textual Engagement and Resonance: A Human-Centric Perspective on User-Generated Content Evaluation
arXiv:2606.01897v2 Announce Type: replace Abstract: Traditional Video Quality Assessment (VQA) focuses narrowly on aesthetic fidelity, overlooking the complex social dynamics that define quality in User-Generated Content (UGC). In this work, we propose a paradigm shift from signal-centric metrics to human-centric resonance assessment. We introduce CASTER (Community-Aware Assessment of Social Textual Engagement and Resonance), a new task that evaluates whether a UGC item achieves positive...
BiasGRPO: Stabilizing Bias Mitigation in High-Variance Reward Landscapes via Group-Relative Policy Optimization
arXiv:2606.04807v1 Announce Type: new Abstract: Mitigating social bias in Large Language Models (LLMs) presents a distinct alignment challenge: unlike verifiable tasks, bias lacks a single ground truth, creating a high-variance, subjective reward landscape. Previous preference-based fine-tuning methods have major trade-offs: Direct Preference Optimization (DPO) is limited by the lack of exploration inherent in offline training, while Proximal Policy Optimization (PPO) can lead to training...
TUX: Measuring Human--AI Tacit Understanding
Announce Type: new Abstract: As large language models (LLMs) increasingly act as collaborative partners, human--AI alignment is often evaluated through explicit task success, accuracy, or reward optimization. Yet many collaborative settings depend on tacit understanding: whether an agent can align with a human's evaluative stance or representational priors without clear objectives, communication, or feedback. To study this capacity, we develop a spectrum-placement task inspired by the social...
The push to standardize ESG scores could make corporate greenwashing easier, not harder
The push to standardize ESG scores could make corporate greenwashing easier, not harder Lisa Lock Scientific Editor Andrew Zinin Lead Editor Three-quarters of S&P 500 companies now tie a portion of their CEO's pay to environmental, social and governance (ESG) metrics. They typically include carbon emissions, workforce diversity and worker safety, among others. The justification is straightforward: if shareholders want corporations to take climate change and social responsibility seriously,...
Human-Like Neural Nets by Catapulting
Human-like Neural Nets by Catapulting Speculative proposal to create artificial neural nets with human-like performance by high-learning-rate/regularization training of overparameterized NNs to trigger catapulting/grokking. Over-parameterization as a route to true generalization would resolve many outstanding mysteries of artificial versus natural intelligence. There are many mysteries about deep learning and human intelligence, but we could describe the biggest anomaly this way: why are...
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...
Disney is poised to ramp its already booming advertising business. Rita Ferro is behind the push
As Rita Ferro, Disney president of global advertising, prepared to take the stage at the company's recent upfront presentation, she had actor Paul Anthony Kelly on her mind. Kelly recently portrayed John F. Kennedy Jr. in the limited FX TV series "Love Story," and met Ferro at an earlier event. After a fangirl moment that included an iPhone snapshot, Ferro requested that Kelly introduce her at the annual pitch to advertisers.