NLPExplorer

Jacob Andreas

Number of Papers:- 58

Number of Citations:- 156

First ACL Paper:- 2010

Latest ACL Paper:- 2024

Venues:-

NAACL

CoNLL

COLING

EMNLP

LREC

LNLS

TACL

ACL

WMT

RoboNLP

IJCNLP

Co-Authors:-

Similar Authors:-

Interpreting User Requests in the Context of Natural Language Standing Instructions F i n d i n g s - N A A C L

Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks NAACL

Visual Grounding Helps Learn Word Meanings in Low-Data Regimes NAACL

Chengxu Zhuang | Evelina Fedorenko | Jacob Andreas |

Toward In-Context Teaching: Adapting Examples to Students’ Misconceptions ACL

Alexis Ross | Jacob Andreas |

Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability F i n d i n g s - A C L

Lexicon-Level Contrastive Visual-Grounding Improves Language Modeling F i n d i n g s - A C L

Chengxu Zhuang | Evelina Fedorenko | Jacob Andreas |

Regularized Conventions: Equilibrium Computation as a Model of Pragmatic Reasoning NAACL

Athul Jacob | Gabriele Farina | Jacob Andreas |

MisinfoEval: Generative AI in the Era of “Alternative Facts” EMNLP

Language-to-Code Translation with a Single Labeled Example EMNLP

Decision-Oriented Dialogue for Human-AI Collaboration TACL

Jessy Lin | Nicholas Tomlin | Jacob Andreas | Jason Eisner |

LexSym: Compositionality as Lexical Symmetry ACL

Ekin Akyurek | Jacob Andreas |

Alignment via Mutual Information CoNLL

Language Modeling with Latent Situations F i n d i n g s - A C L

Belinda Z. Li | Maxwell Nye | Jacob Andreas |

Grokking of Hierarchical Structure in Vanilla Transformers ACL

Shikhar Murty | Pratyusha Sharma | Jacob Andreas | Christopher Manning |

Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness? EMNLP

Kevin Liu | Stephen Casper | Dylan Hadfield-Menell | Jacob Andreas |

The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding F i n d i n g s - A C L

Pushdown Layers: Encoding Recursive Structure in Transformer Language Models EMNLP

Shikhar Murty | Pratyusha Sharma | Jacob Andreas | Christopher Manning |

Guided K-best Selection for Semantic Parsing Annotation ACL

Skill Induction and Planning with Latent Language ACL

Pratyusha Sharma | Antonio Torralba | Jacob Andreas |

Proceedings of the First Workshop on Learning with Natural Language Supervision ACL LNLS

Jacob Andreas | Karthik Narasimhan | Aida Nematzadeh |

Quantifying Adaptability in Pre-trained Language Models with 500 Tasks NAACL

Hierarchical Phrase-Based Sequence-to-Sequence Learning EMNLP

Bailin Wang | Ivan Titov | Jacob Andreas | Yoon Kim |

Towards Tracing Knowledge in Language Models Back to the Training Data F i n d i n g s - E M N L P

Language Models as Agent Models F i n d i n g s - E M N L P

Jacob Andreas |

Compositional Generalization for Neural Semantic Parsing via Span-level Supervised Attention NAACL

Multitasking Inhibits Semantic Drift NAACL

Athul Paul Jacob | Mike Lewis | Jacob Andreas |

The Low-Dimensional Linear Geometry of Contextualized Word Representations CoNLL EMNLP

Evan Hernandez | Jacob Andreas |

Lexicon Learning for Few Shot Sequence Modeling ACL IJCNLP

Ekin Akyurek | Jacob Andreas |

How Do Neural Sequence Models Generalize? Local and Global Cues for Out-of-Distribution Prediction EMNLP

D. Anthony Bau | Jacob Andreas |

Value-Agnostic Conversational Semantic Parsing ACL IJCNLP

Implicit Representations of Meaning in Neural Language Models ACL IJCNLP

Belinda Z. Li | Maxwell Nye | Jacob Andreas |

What Context Features Can Transformer Language Models Use? ACL IJCNLP

Joe O’Connor | Jacob Andreas |

Good-Enough Compositional Data Augmentation ACL

Jacob Andreas |

Experience Grounds Language EMNLP

Task-Oriented Dialogue as Dataflow Synthesis TACL