Nouha Dziri

papers

4,602

total citations

papers (13)

Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties

AAAI 2024arXiv

citations

AI as Humanity’s Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text

ICLR 2025arXiv

citations

OMEGA: Can LLMs Reason Outside the Box in Math? Evaluating Exploratory, Compositional, and Transformative Generalization

NEURIPS 2025arXiv

citations

Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction

ICLR 2025arXiv

citations

CHAMPAGNE: Learning Real-world Conversation from Large-Scale Web Videos

ICCV 2023arXiv

citations

Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)

NEURIPS 2025arXiv

citations

SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior

ICML 2025arXiv

citations

Position: A Roadmap to Pluralistic Alignment

ICML 2024

citations

Nouha Dziri

papers (13)

Self-Refine: Iterative Refinement with Self-Feedback

Faith and Fate: Limits of Transformers on Compositionality

Tulu 3: Pushing Frontiers in Open Language Model Post-Training

Fine-Grained Human Feedback Gives Better Rewards for Language Model Training

WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild

Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties

AI as Humanity’s Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text

OMEGA: Can LLMs Reason Outside the Box in Math? Evaluating Exploratory, Compositional, and Transformative Generalization

Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction

CHAMPAGNE: Learning Real-world Conversation from Large-Scale Web Videos

Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)

SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior

Position: A Roadmap to Pluralistic Alignment

papers (13)

Self-Refine: Iterative Refinement with Self-Feedback

Faith and Fate: Limits of Transformers on Compositionality

Tulu 3: Pushing Frontiers in Open Language Model Post-Training

Fine-Grained Human Feedback Gives Better Rewards for Language Model Training

WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild

Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties

AI as Humanity’s Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text

OMEGA: Can LLMs Reason Outside the Box in Math? Evaluating Exploratory, Compositional, and Transformative Generalization

Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction

CHAMPAGNE: Learning Real-world Conversation from Large-Scale Web Videos

Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)

SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior

Position: A Roadmap to Pluralistic Alignment