no code implementations • EMNLP 2021 • Harsh Gupta, Luciano del Corro, Samuel Broscheit, Johannes Hoffart, Eliot Brenner
We investigate post-OCR correction in a setting where we have access to different OCR views of the same document.
no code implementations • 30 May 2025 • Juan Wisznia, Cecilia Bolaños, Juan Tollo, Giovanni Marraffini, Agustín Gianolini, Noe Hsueh, Luciano del Corro
We introduce a novel framework for analyzing sorting algorithms in pairwise ranking prompting (PRP), re-centering the cost model around LLM inferences rather than traditional pairwise comparisons.
no code implementations • 25 Mar 2025 • Giovanni Franco Gabriel Marraffini, Andrés Cotton, Noe Fabian Hsueh, Axel Fridman, Juan Wisznia, Luciano del Corro
The question of how to make decisions that maximise the well-being of all persons is very relevant to design language models that are beneficial to humanity and free from harm.
no code implementations • 13 Jul 2024 • Sanchit Ahuja, Kumar Tanmay, Hardik Hansrajbhai Chauhan, Barun Patra, Kriti Aggarwal, Luciano del Corro, Arindam Mitra, Tejas Indulal Dhamecha, Ahmed Awadallah, Monojit Choudhary, Vishrav Chaudhary, Sunayana Sitaram
In order to address this, we introduce a novel recipe for creating a multilingual synthetic instruction tuning dataset, sPhinX, which is created by selectively translating instruction response pairs from English into 50 languages.
no code implementations • 3 Jul 2024 • Arindam Mitra, Luciano del Corro, Guoqing Zheng, Shweti Mahajan, Dany Rouhana, Andres Codas, Yadong Lu, Wei-Ge Chen, Olga Vrousgos, Corby Rosset, Fillipe Silva, Hamed Khanpour, Yash Lara, Ahmed Awadallah
We focus on using synthetic data for post-training, specifically creating data by powerful models to teach a new skill or behavior to another model, we refer to this setting as Generative Teaching.
no code implementations • 18 Nov 2023 • Arindam Mitra, Luciano del Corro, Shweti Mahajan, Andres Codas, Clarisse Simoes, Sahaj Agarwal, Xuxi Chen, Anastasia Razdaibiedina, Erik Jones, Kriti Aggarwal, Hamid Palangi, Guoqing Zheng, Corby Rosset, Hamed Khanpour, Ahmed Awadallah
Research on training small LMs has often relied on imitation learning to replicate the output of more capable models.
Ranked #1 on
Crass AI
on BIG-bench
1 code implementation • 3 Oct 2023 • Canwen Xu, Corby Rosset, Ethan C. Chau, Luciano del Corro, Shweti Mahajan, Julian McAuley, Jennifer Neville, Ahmed Hassan Awadallah, Nikhil Rao
Remarkably, our automatic contrastive post-training further improves the performance of Orca, already a state-of-the-art instruction learning model tuned with GPT-4 outputs, to outperform ChatGPT.
no code implementations • 5 Jul 2023 • Luciano del Corro, Allie Del Giorno, Sahaj Agarwal, Bin Yu, Ahmed Awadallah, Subhabrata Mukherjee
While existing token-level early exit methods show promising results for online inference, they cannot be readily applied for batch inferencing and Key-Value caching.
no code implementations • EMNLP (ECONLP) 2021 • Luciano Del Corro, Johannes Hoffart
We present a method to automatically identify financially relevant news using stock price movements and news headlines as input.
1 code implementation • EMNLP 2018 • Marco Ponza, Luciano del Corro, Gerhard Weikum
This work introduces fact salience: The task of generating a machine-readable representation of the most prominent information in a text document as a set of facts.
no code implementations • ACL 2018 • Prabal Agarwal, Jannik Str{\"o}tgen, Luciano del Corro, Johannes Hoffart, Gerhard Weikum
Named Entity Disambiguation (NED) systems perform well on news articles and other texts covering a specific time interval.
no code implementations • ACL 2018 • Dominic Seyler, Tatiana Dembelova, Luciano del Corro, Johannes Hoffart, Gerhard Weikum
In this work, we discuss the importance of external knowledge for performing Named Entity Recognition (NER).
no code implementations • 11 Sep 2017 • Dominic Seyler, Tatiana Dembelova, Luciano del Corro, Johannes Hoffart, Gerhard Weikum
KnowNER is a multilingual Named Entity Recognition (NER) system that leverages different degrees of external knowledge.
Multilingual Named Entity Recognition
named-entity-recognition
+2
1 code implementation • EMNLP 2017 • Kiril Gashteovski, Rainer Gemulla, Luciano del Corro
The goal of Open Information Extraction (OIE) is to extract surface relations and their arguments from natural-language text in an unsupervised, domain-independent manner.