2018 · Language models
ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning
ATOMIC organizes everyday commonsense knowledge as typed relationships between events, intentions, reactions, and consequences.
Paper & contextYejin Choi
Studying commonsense knowledge and model behavior.
Choi studies commonsense reasoning, language-model behavior, and the limits of what models learn. This selection connects resources for social and everyday reasoning with newer approaches to training, evaluating, and improving language-model capabilities.
Selected work
10 papers
2019 · Language models
SocialIQA: Commonsense Reasoning about Social Interactions
SocialIQA tests commonsense reasoning about everyday social situations using multiple-choice questions.
Paper & context2025 · Machine learning
UQ: Assessing Language Models on Unsolved Questions
Selected research in machine learning, ai evaluation. Read the full paper, including the methods, experiments, and reported results.
Paper & context2022 · Benchmarks
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench collects a broad set of language-model evaluation tasks to study capabilities and limitations beyond a single benchmark.
Paper & context2026 · Machine learning
Prefix Sliding for efficient test-time scaling
Selected research in machine learning, ai evaluation. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Language models
SPADE: Self-Play in Adaptive Synthetic Executable Environments
Selected research in language models. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Language models
Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients
Selected research in language models. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Language models
ProCUA-SFT Technical Report
Selected research in language models. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Language models
Spokes: Optimizing for Diverse Pretraining Data Selection
Selected research in language models. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Language models
Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
Selected research in language models. Read the full paper, including the methods, experiments, and reported results.
Paper & contextAn independent editorial profile. Inclusion does not imply Council membership or endorsement. Research is collaborative; coauthorship does not imply sole credit.
Selection & sources