NLPExplorer

Yejin Choi

Number of Papers:- 170

Number of Citations:- 660

First ACL Paper:- 2005

Latest ACL Paper:- 2024

Venues:-

NAACL

CoNLL

COLING

INLG

EMNLP

Findings

HLT

RANLP

TACL

ACL

EACL

IJCNLP

LSDSem

Co-Authors:-

Aaron Chan

Abhilasha Ravichander

Aditya Gupta

Aida Amini

Ainur Yessenalina

Similar Authors:-

Jie Wang

Jingwen Wang

Malgorzata Budzikowska

Changbeom Lee

Cody Rioux

NeuroComparatives: Neuro-Symbolic Distillation of Comparative Knowledge F i n d i n g s - N A A C L

Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models EACL

JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models NAACL

Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs ACL

Siyuan Wang | Zhongyu Wei | Yejin Choi | Xiang Ren |

Agent Lumos: Unified and Modular Training for Open-Source Language Agents ACL

Selective “Selective Prediction”: Reducing Unnecessary Abstention in Vision-Language Reasoning F i n d i n g s - A C L

Impossible Distillation for Paraphrasing and Summarization: How to Make High-quality Lemonade out of Small, Low-quality Model NAACL

UNcommonsense Reasoning: Abductive Reasoning about Uncommon Situations NAACL

MacGyver: Are Large Language Models Creative Problem Solvers? NAACL

CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generation EMNLP

Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration EMNLP

StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements EMNLP

Perceptions to Beliefs: Exploring Precursory Inferences for Theory of Mind in Large Language Models EMNLP

How to Train Your Fact Verifier: Knowledge Transfer with Multimodal Open Models F i n d i n g s - E M N L P

Symbolic Working Memory Enhances Language Models for Complex Rule Application EMNLP

Siyuan Wang | Zhongyu Wei | Yejin Choi | Xiang Ren |

WildVis: Open Source Visualizer for Million-Scale Chat Logs in the Wild EMNLP

In Search of the Long-Tail: Systematic Generation of Long-Tail Inferential Knowledge via Logical Rule Guided Search EMNLP

Penguins Don’t Fly: Reasoning about Generics through Instantiations and Exceptions EACL

SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization EMNLP

Symbolic Chain-of-Thought Distillation: Small Models Can Also “Think” Step-by-Step ACL

Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-text Rationales ACL

Vera: A General-Purpose Plausibility Estimation Model for Commonsense Statements EMNLP

Crystal: Introspective Reasoners Reinforced with Self-Feedback EMNLP

Reading Books is Great, But Not if You Are Driving! Visually Grounded Reasoning about Defeasible Commonsense Norms EMNLP

What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations F i n d i n g s - E M N L P

“You Are An Expert Linguistic Annotator”: Limits of LLMs as Analyzers of Abstract Meaning Representation F i n d i n g s - E M N L P

FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions EMNLP

Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts ACL

Skyler Hallinan | Alisa Liu | Yejin Choi | Maarten Sap |

NovaCOMET: Open Commonsense Foundation Models with Symbolic Knowledge Distillation F i n d i n g s - E M N L P

STEER: Unified Style Transfer with Expert Reinforcement F i n d i n g s - E M N L P

Commonsense Knowledge Transfer for Pre-trained Language Models F i n d i n g s - A C L

Wangchunshu Zhou | Ronan Le Bras | Yejin Choi |

We’re Afraid Language Models Aren’t Modeling Ambiguity EMNLP

Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference F i n d i n g s - A C L

Wangchunshu Zhou | Ronan Le Bras | Yejin Choi |

Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning EMNLP

SQuARe: A Large-Scale Dataset of Sensitive Questions and Acceptable Responses Created through Human-Machine Collaboration ACL

BotPercent: Estimating Bot Populations in Twitter Communities F i n d i n g s - E M N L P

Do Androids Laugh at Electric Sheep? Humor “Understanding” Benchmarks from The New Yorker Caption Contest ACL

REV: Information-Theoretic Evaluation of Free-Text Rationales ACL

ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situations ACL

Faking Fake News for Real Fake News Detection: Propaganda-Loaded Training Data Generation ACL

I Cast Detect Thoughts: Learning to Converse and Guide with Intents and Theory-of-Mind in Dungeons and Dragons ACL

Minding Language Models’ (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief Tracker ACL

From Dogwhistles to Bullhorns: Unveiling Coded Rhetoric with Language Models ACL

Julia Mendelsohn | Ronan Le Bras | Yejin Choi | Maarten Sap |

I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation ACL

Generated Knowledge Prompting for Commonsense Reasoning ACL

Misinfo Reaction Frames: Reasoning about Readers’ Reactions to News Headlines ACL

Is GPT-3 Text Indistinguishable from Human Text? Scarecrow: A Framework for Scrutinizing Machine Text ACL

Reframing Instructional Prompts to GPTk’s Language ACL Findings

Probing Factually Grounded Content Transfer with Factual Ablation ACL Findings

Peter West | Chris Quirk | Michel Galley | Yejin Choi |

It’s not Rocket Science: Interpreting Figurative Language in Narratives TACL

Tuhin Chakrabarty | Yejin Choi | Vered Shwartz |

Symbolic Knowledge Distillation: from General Language Models to Commonsense Models NAACL

Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection NAACL

Aligning to Social Norms and Values in Interactive Narratives NAACL

Bidimensional Leaderboards: Generate and Evaluate Language Hand in Hand NAACL

Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Prompts NAACL

Transparent Human Evaluation for Image Captioning NAACL

Exposing the Limits of Video-Text Models through Contrast Sets NAACL

Reframing Human-AI Collaboration for Generating Free-Text Explanations NAACL

NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics NAACL

Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge Transfer NAACL

NeuroCounterfactuals: Beyond Minimal-Edit Counterfactuals for Richer Data Augmentation F i n d i n g s - E M N L P

Referee: Reference-Free Sentence Summarization with Sharper Controllability through Symbolic Knowledge Distillation EMNLP

WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation F i n d i n g s - E M N L P

Alisa Liu | Swabha Swayamdipta | Noah A. Smith | Yejin Choi |

GENIE: Toward Reproducible and Standardized Human Evaluation for Text Generation EMNLP

Twist Decoding: Diverse Generators Guide Each Other EMNLP

Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs EMNLP

Maarten Sap | Ronan Le Bras | Daniel Fried | Yejin Choi |

NaturalAdversaries: Can Naturalistic Adversaries Be as Effective as Artificial Adversaries? F i n d i n g s - E M N L P

Saadia Gabriel | Hamid Palangi | Yejin Choi |

Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations EMNLP

Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering EMNLP

ProsocialDialog: A Prosocial Backbone for Conversational Agents EMNLP

Discourse Understanding and Factual Consistency in Abstractive Summarization EACL

Challenges in Automated Debiasing for Toxic Language Detection EACL

NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints NAACL

TuringAdvice: A Generative and Dynamic Evaluation of Language Use NAACL

“I’m Not Mad”: Commonsense Implications of Negation and Contradiction NAACL

Liwei Jiang | Antoine Bosselut | Chandra Bhagavatula | Yejin Choi |

GO FIGURE: A Meta Evaluation of Factuality in Summarization Findings

DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts ACL IJCNLP

Reflective Decoding: Beyond Unidirectional Generation with Off-the-Shelf Language Models ACL IJCNLP

proScript: Partially Ordered Scripts Generation EMNLP Findings

On-the-Fly Attention Modulation for Neural Generation Findings

PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World ACL IJCNLP

Contrastive Explanations for Model Interpretability EMNLP

Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences EMNLP

Edited Media Understanding Frames: Reasoning About the Intent and Implications of Visual Misinformation ACL IJCNLP

Surface Form Competition: Why the Highest Probability Answer Isn’t Always Right EMNLP

TIMEDIAL: Temporal Commonsense Reasoning in Dialog ACL IJCNLP

Conversational Multi-Hop Reasoning with Neural Commonsense Knowledge and Symbolic Logic Rules EMNLP

CLIPScore: A Reference-free Evaluation Metric for Image Captioning EMNLP

Commonsense Reasoning for Natural Language Processing ACL

Recollection versus Imagination: Exploring Human Memory and Cognition via Neural Language Models ACL

Social Bias Frames: Reasoning about Social and Power Implications of Language ACL

Do Neural Language Models Overcome Reporting Bias? COLING

Vered Shwartz | Yejin Choi |

Unsupervised Commonsense Question Answering with Self-Talk EMNLP

Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics EMNLP

PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking EMNLP

Hannah Rashkin | Asli Celikyilmaz | Yejin Choi | Jianfeng Gao |

PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction EMNLP

Xinyao Ma | Maarten Sap | Hannah Rashkin | Yejin Choi |

Thinking Like a Skeptic: Defeasible Inference in Natural Language EMNLP Findings

Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning EMNLP

RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models EMNLP Findings

Generative Data Augmentation for Commonsense Reasoning EMNLP Findings

Social Chemistry 101: Learning to Reason about Social and Moral Norms EMNLP

CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning EMNLP Findings

Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs EMNLP Findings

Structured Local Training and Biased Potential Functions for Conditional Random Fields with Application to Coreference Resolution NAACL

Yejin Choi | Claire Cardie |