NLPExplorer

Edoardo Mosca

Number of Papers:- 8

Number of Citations:- 0

First ACL Paper:- 2021

Latest ACL Paper:- 2024

Venues:-

NAACL

LNLS

RepL4NLP

ACL

TrustNLP

WS

DeTermIt

SocialNLP

NLPMC

COLING

Co-Authors:-

Daniel Gallagher

Defne Demirturk

Fabio Raffagnato

Similar Authors:-

Simpler Becomes Harder: Do LLMs Exhibit a Coherent Behavior on Simplified Corpora? DeTermIt WS

Miriam Anschütz | Edoardo Mosca | Georg Groh |

“Dr LLM, what do I have?”: The Impact of User Beliefs and Prompt Formulation on Health Diagnoses NLPMC WS

Wojciech Kusa | Edoardo Mosca | Aldo Lipani |

GrammarSHAP: An Efficient Model-Agnostic and Structure-Aware NLP Explainer ACL LNLS

Edoardo Mosca | Defne Demirtürk | Luca Mülln | Fabio Raffagnato | Georg Groh |

Detecting Word-Level Adversarial Text Attacks via SHapley Additive exPlanations ACL RepL4NLP

Edoardo Mosca | Lukas Huber | Marc Alexander Kühn | Georg Groh |

“That Is a Suspicious Reaction!”: Interpreting Logits Variation to Detect NLP Adversarial Attacks ACL

Edoardo Mosca | Shreyash Agarwal | Javier Rando Ramírez | Georg Groh |

Explaining Neural NLP Models for the Joint Analysis of Open-and-Closed-Ended Survey Answers NAACL TrustNLP

Edoardo Mosca | Katharina Harmann | Tobias Eder | Georg Groh |

SHAP-Based Explanation Methods: A Review for NLP Interpretability COLING

Edoardo Mosca | Ferenc Szigeti | Stella Tragianni | Daniel Gallagher | Georg Groh |

Understanding and Interpreting the Impact of User Context in Hate Speech Detection NAACL SocialNLP

Edoardo Mosca | Maximilian Wich | Georg Groh |

.