NLPExplorer

Mor Geva

Number of Papers:- 36

Number of Citations:- 1

First ACL Paper:- 2017

Latest ACL Paper:- 2024

Venues:-

NAACL

COLING

EMNLP

TACL

ACL

KnowLLM

EACL

*SEMEVAL

Co-Authors:-

Similar Authors:-

Evaluating the Ripple Effects of Knowledge Editing in Language Models TACL

Proceedings of the 1st Workshop on Towards Knowledgeable Language Models (KnowLLM 2024) KnowLLM WS

The Hidden Space of Transformer Language Adapters ACL

Do Large Language Models Latently Perform Multi-Hop Reasoning? ACL

Narrowing the Knowledge Evaluation Gap: Open-Domain Question Answering with Multi-Granularity Answers ACL

Gal Yona | Roee Aharoni | Mor Geva |

RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations ACL

A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains ACL

Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words? EMNLP

Gal Yona | Roee Aharoni | Mor Geva |

Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop Queries EMNLP

Backward Lens: Projecting Language Model Gradients into the Vocabulary Space EMNLP

Shahar Katz | Yonatan Belinkov | Mor Geva | Lior Wolf |

From Insights to Actions: The Impact of Interpretability and Analysis Research on NLP EMNLP

Estimating Knowledge in Large Language Models Without Generating a Single Token EMNLP

Daniela Gottesman | Mor Geva |

Crawling The Internal Knowledge-Base of Language Models F i n d i n g s - E A C L

Roi Cohen | Mor Geva | Jonathan Berant | Amir Globerson |

Understanding Transformer Memorization Recall Through Idioms EACL

Don’t Blame the Annotator: Bias Already Starts in the Annotation Instructions EACL

Mihir Parmar | Swaroop Mishra | Mor Geva | Chitta Baral |

A Comprehensive Evaluation of Tool-Assisted Generation Strategies F i n d i n g s - E M N L P

Dissecting Recall of Factual Associations in Auto-Regressive Language Models EMNLP

Mor Geva | Jasmijn Bastings | Katja Filippova | Amir Globerson |

CRoW: Benchmarking Commonsense Reasoning in Real-World Tasks EMNLP

LM vs LM: Detecting Factual Errors via Cross Examination EMNLP

Roi Cohen | May Hamri | Mor Geva | Amir Globerson |

In-Context Learning Creates Task Vectors F i n d i n g s - E M N L P

Roee Hendel | Mor Geva | Amir Globerson |

Complex Reasoning in Natural Language ACL

Analyzing Transformers in Embedding Space ACL

Guy Dar | Mor Geva | Ankit Gupta | Jonathan Berant |

Break, Perturb, Build: Automatic Perturbation of Reasoning Paths Through Question Decomposition TACL

Mor Geva | Tomer Wolfson | Jonathan Berant |

Inferring Implicit Relations in Complex Questions with Language Models F i n d i n g s - E M N L P

Uri Katz | Mor Geva | Jonathan Berant |

SCROLLS: Standardized CompaRison Over Long Language Sequences EMNLP

Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space EMNLP

Mor Geva | Avi Caciularu | Kevin Wang | Yoav Goldberg |

LM-Debugger: An Interactive Tool for Inspection and Intervention in Transformer-Based Language Models EMNLP

Transformer Feed-Forward Layers Are Key-Value Memories EMNLP

Mor Geva | Roei Schuster | Jonathan Berant | Omer Levy |

What’s in Your Head? Emergent Behaviour in Multi-Task Transformer Models EMNLP

Mor Geva | Uri Katz | Aviv Ben-Arie | Jonathan Berant |

Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies TACL

Injecting Numerical Reasoning Skills into Language Models ACL

Mor Geva | Ankit Gupta | Jonathan Berant |

Break It Down: A Question Understanding Benchmark TACL

Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets EMNLP

Mor Geva | Yoav Goldberg | Jonathan Berant |

DiscoFuse: A Large-Scale Dataset for Discourse-Based Sentence Fusion NAACL

Mor Geva | Eric Malmi | Idan Szpektor | Jonathan Berant |

Learning to Search in Long Documents Using Document Structure COLING

Mor Geva | Jonathan Berant |

Evaluating Semantic Parsing against a Simple Web-based Question Answering Model *SEMEVAL

Alon Talmor | Mor Geva | Jonathan Berant |