Yejin Choi
Stanford professor and AI2 senior director known for commonsense reasoning, social/cultural NLP, and the NLP datasets that have shaped LLM evaluation.
- Role
- professor
- Currently at
- Stanford University
- twitter.com/YejinChoinka
- Scholar
- scholar.google.com/citations
- Papers
- 119
Cite
Notes
Only stored in your browser.
Authored papers
119Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention
arXiv 2026
Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
arXiv 2026
Learning to Discover at Test Time
arXiv 2026
ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop
arXiv 2026
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
arXiv 2026
RAGEN-2: Reasoning Collapse in Agentic RL
arXiv 2026
EXAONE 4.5 Technical Report
arXiv 2026
K-EXAONE Technical Report
arXiv 2026
Towards Execution-Grounded Automated AI Research
arXiv 2026
Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?
arXiv 2026
Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs
arXiv 2026
Privasis: Synthesizing the Largest "Public" Private Dataset from Scratch
arXiv 2026
Latent Collaboration in Multi-Agent Systems
arXiv 2025
NitroGen: An Open Foundation Model for Generalist Gaming Agents
arXiv 2026
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
arXiv 2025
RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
arXiv 2025
Adaptation of Agentic AI
arXiv 2025
Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
arXiv 2025
OpenThoughts: Data Recipes for Reasoning Models
arXiv 2025
OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens
arXiv 2025
One-Minute Video Generation with Test-Time Training
CVPR 2025 1
PoseX: AI Defeats Physics Approaches on Protein-Ligand Cross Docking
arXiv 2025
Infini-gram mini: Exact n-gram Search at the Internet Scale with FM-Index
arXiv 2025
X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents
arXiv 2025
End-to-End Test-Time Training for Long Context
arXiv 2025
Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations
arXiv 2025
ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning
arXiv 2025
In-the-Flow Agentic System Optimization for Effective Planning and Tool Use
arXiv 2025
Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction
arXiv 2025
RLP: Reinforcement as a Pretraining Objective
arXiv 2025
MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes
arXiv 2025
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas
arXiv 2025
UQ: Assessing Language Models on Unsolved Questions
arXiv 2025
Multiplayer Nash Preference Optimization
arXiv 2025
Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers
arXiv 2025
When to Trust Context: Self-Reflective Debates for Context Reliability
arXiv 2025
The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage
arXiv 2025
ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration
arXiv 2025
G-FOCUS: Towards a Robust Method for Assessing UI Design Persuasiveness
arXiv 2025
Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
preprint
WildChat: 1M ChatGPT Interaction Logs in the Wild
ICLR
RewardBench: Evaluating Reward Models for Language Modeling
arXiv 2024
WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
arXiv 2024
Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokens
arXiv 2024
Do Membership Inference Attacks Work on Large Language Models?
arXiv 2024
WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
arXiv 2024
Tuning Language Models by Proxy
arXiv 2024
Negative Token Merging: Image-based Adversarial Feature Guidance
arXiv 2024
Agent AI: Surveying the Horizons of Multimodal Interaction
arXiv 2024
Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset
arXiv 2024
RESTOR: Knowledge Recovery through Machine Unlearning
arXiv 2024
StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements
arXiv 2024
MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens
arXiv 2024
WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild
arXiv 2024
From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
arXiv 2024
Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration
arXiv 2024
AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text
arXiv 2024
Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?
arXiv 2024
A Roadmap to Pluralistic Alignment
arXiv 2024
Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs
arXiv 2024
Perceptions to Beliefs: Exploring Precursory Inferences for Theory of Mind in Large Language Models
arXiv 2024
Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting
arXiv 2023
Faith and Fate: Limits of Transformers on Compositionality
faith-and-fate-limits-of-transformers-on
Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging
arXiv 2023
Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text
multimodal-c4-an-open-billion-scale-corpus-of
Agent Lumos: Unified and Modular Training for Open-Source Language Agents
arXiv 2023
We're Afraid Language Models Aren't Modeling Ambiguity
arXiv 2023
CHAMPAGNE: Learning Real-world Conversation from Large-Scale Web Videos
ICCV 2023 1
Structured Chemistry Reasoning with Large Language Models
arXiv 2023
Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
arXiv 2023
Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning
arXiv 2023
Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties
arXiv 2023
Crystal: Introspective Reasoners Reinforced with Self-Feedback
arXiv 2023
Tailoring Self-Rationalizers with Multi-Reward Distillation
arXiv 2023
Localized Symbolic Knowledge Distillation for Visual Commonsense Models
localized-symbolic-knowledge-distillation-for
Vera: A General-Purpose Plausibility Estimation Model for Commonsense Statements
arXiv 2023
PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planning
arXiv 2023
Symbolic Chain-of-Thought Distillation: Small Models Can Also "Think" Step-by-Step
arXiv 2023
FiLM: Fill-in Language Models for Any-Order Generation
arXiv 2023
Text as Images: Can Multimodal Large Language Models Follow Printed Instructions in Pixels?
arXiv 2023
STEER: Unified Style Transfer with Expert Reinforcement
arXiv 2023
In Search of the Long-Tail: Systematic Generation of Long-Tail Inferential Knowledge via Logical Rule Guided Search
arXiv 2023
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
TMLR
Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization
arXiv 2022
Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks
arXiv 2022
WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation
arXiv 2022
RealTime QA: What's the Answer Right Now?
realtime-qa-what-s-the-answer-right-now
Quark: Controllable Text Generation with Reinforced Unlearning
arXiv 2022
ProsocialDialog: A Prosocial Backbone for Conversational Agents
arXiv 2022
A Call for Clarity in Beam Search: How It Works and When It Stops
arXiv 2022
NaturalProver: Grounded Mathematical Proof Generation with Language Models
arXiv 2022
Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts
arXiv 2022
Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering
arXiv 2022
Multimodal Knowledge Alignment with Reinforcement Learning
arXiv 2022
SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization
arXiv 2022
COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics
arXiv 2022
ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situations
arXiv 2022
CLIPScore: A Reference-free Evaluation Metric for Image Captioning
EMNLP 2021 11
Understanding Dataset Difficulty with $\mathcal{V}$-Usable Information
arXiv 2021
Generated Knowledge Prompting for Commonsense Reasoning
ACL 2022 5
Reframing Human-AI Collaboration for Generating Free-Text Explanations
NAACL 2022 7
TIMEDIAL: Temporal Commonsense Reasoning in Dialog
ACL 2021 5
NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics
NAACL 2022 7
VinVL: Revisiting Visual Representations in Vision-Language Models
CVPR 2021 1
MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers
mauve-measuring-the-gap-between-neural-text
Symbolic Knowledge Distillation: from General Language Models to Commonsense Models
NAACL 2022 7
NaturalProofs: Mathematical Theorem Proving in Natural Language
arXiv 2021
DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts
ACL 2021 5
Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge Transfer
arXiv 2021
Challenges in Automated Debiasing for Toxic Language Detection
EACL 2021 2
It's not Rocket Science : Interpreting Figurative Language in Narratives
arXiv 2021
Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Prompts
NAACL 2022 7
Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics
EMNLP 2020 11
Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks
ECCV 2020 8
Scruples: A Corpus of Community Ethical Judgments on 32,000 Real-Life Anecdotes
arXiv 2020
The Curious Case of Neural Text Degeneration
ICLR 2020 1
Defending Against Neural Fake News
defending-against-neural-fake-news-1
Neural Motifs: Scene Graph Parsing with Global Context
neural-motifs-scene-graph-parsing-with-global-1
Dynamic Entity Representations in Neural Language Models
dynamic-entity-representations-in-neural-1
Tool contributions
1Affiliations
Frequent co-authors
10from 119 papers
Ximing Lu
Hannaneh Hajishirzi
professor
Noah A. Smith
Jack Hessel
researcher
Liwei Jiang
Sean Welleck
Ronan Le Bras
Nouha Dziri
researcher
Youngjae Yu
Jiacheng Liu