Leonardo F. R. Ribeiro

Leonardo F. R. Ribeiro

I'm a Senior Applied Scientist on Amazon AGI, where I focus on building and refining Large Language and Multimodal Foundation Models. My work centers on large-scale training solutions to enhance reasoning capabilities, model performance, and user alignment across a wide range of tasks. My research interests lie in various areas of controllable text generation, summarization and knowledge-intensive NLP tasks such as (multi-modal) Retrieval Augmented Generation (RAG). I hold a PhD in Computer Science from the UKP Lab at the Technical University of Darmstadt, where I was advised by Iryna Gurevych.

My work has been published in top-tier AI conferences such as ACL, EMNLP, NAACL, and KDD. I actively contribute to the research community, serving as a Senior Area Chair for NAACL 2025, Tutorial Chair for ACL 2024, and Area Chair for EACL 2024, NAACL 2024, ACL 2024, EMNLP 2024, COLING 2022, and ARR.

leonardofribeiro@gmail.com | Resume | CV

Publications

GaRAGe
GaRAGe: A Benchmark with Grounding Annotations for RAG Evaluation
Ionut-Teodor Sorodoc, Leonardo F. R. Ribeiro, Rexhina Blloshmi, Christopher Davis, Adrià de Gispert
ACL 2025 (Findings)
PDF Code
XRAG
XRAG: Cross-lingual Retrieval-Augmented Generation
Wei Liu, Sony Trenous, Leonardo F. R. Ribeiro, Bill Byrne, Felix Hieber
pre-print
PDF
NeoQA
NeoQA: Evidence-based Question Answering with Generated News Events
Max Glockner, Xiang Jiang, Leonardo F. R. Ribeiro, Iryna Gurevych, Markus Dreyer
ACL 2025 (Findings)
PDF Code
Tuning-Free Personalized Alignment
Tuning-Free Personalized Alignment via Trial-Error-Explain In-Context Learning
Hyundong Cho, Karishma Sharma, Nicolaas Jedema, Leonardo F. R. Ribeiro, Alessandro Moschitti, Ravi Krishnan, Jonathan May
NAACL 2025 (Findings)
PDF
SpeechLLM
Speechworthy Instruction-tuned Language Models
Hyundong Cho, Nicolaas Jedema, Leonardo F. R. Ribeiro, Karishma Sharma, Pedro Szekely, Alessandro Moschitti, Ruben Janssen, and Jonathan May
EMNLP 2024
PDF
Conversational QA
Learning When to Retrieve, What to Rewrite, and How to Respond in Conversational QA
Nirmal Roy, Leonardo F. R. Ribeiro, Rexhina Blloshmi, Kevin Small
EMNLP 2024 (Findings)
PDF
FANTA
FANTAstic SEquences and Where to Find Them: Faithful and Efficient API Call Generation through State-tracked Constrained Decoding and Reranking
Zhuoer Wang, Leonardo F. R. Ribeiro, Alexandros Papangelis, Rohan Mukherjee, Tzu-Yen Wang, Xinyan Zhao, Arijit Biswas, James Caverlee, Angeliki Metallinou
EMNLP 2024 (Findings)
PDF
REFINESUMM
REFINESUMM: Self-Refining MLLM for Generating a Multimodal Summarization Dataset
Vaidehi Patil, Leonardo F. R. Ribeiro, Mengwen Liu, Mohit Bansal, Markus Dreyer
ACL 2024
PDF
Retrieval Complexity
Measuring Retrieval Complexity in Question Answering Systems
Matteo Gabburo, Nicolaas Paul Jedema, Siddhant Garg, Leonardo F. R. Ribeiro, Alessandro Moschitti
ACL 2024 (Findings)
PDF
SCU
On the Role of Summary Content Units in Text Summarization Evaluation
Marcel Nawrath, Agnieszka Wiktoria Nowak, Tristan Ratz, Danilo Constantin Walenta, Juri Opitz, Leonardo F. R. Ribeiro, Joao Sedoc, Daniel Deutsch, Simon Mille, Yixin Liu, Sebastian Gehrmann, Lining Zhang, Saad Mahamood, Miruna Clinciu, Khyathi Chandu, Yufang Hou
NAACL 2024
PDF Code
Controllable Readability
Generating Summaries with Controllable Readability Levels
Leonardo F. R. Ribeiro, Mohit Bansal, Markus Dreyer
EMNLP 2023
PDF Code
Robot Language Model
Learning to reason over scene graphs: a case study of finetuning GPT-2 into a robot language model for grounded task planning
Georgia Chalvatzaki, Ali Younes, Daljeet Nandha, An Thai Le, Leonardo F. R. Ribeiro, Iryna Gurevych
2023 Frontiers in Robotics and AI
PDF Data
FactGraph
FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations
Leonardo F. R. Ribeiro, Mengwen Liu, Iryna Gurevych, Markus Dreyer, Mohit Bansal
NAACL 2022
PDF Code
UKP-SQUARE
UKP-SQUARE: An Online Platform for Question Answering Research
Tim Baumgärtner, Kexin Wang, Rachneet Sachdeva, Max Eichler, Gregor Geigle, Clifton Poth, Hannah Sterz, Haritz Puerto, Leonardo FR Ribeiro, Jonas Pfeiffer, Nils Reimers, Gözde Gül Şahin, Iryna Gurevych
ACL 2022 (Demo)
PDF Code
Structural Adapters
Structural Adapters in Pretrained Language Models for AMR-to-Text Generation
Leonardo F. R. Ribeiro, Yue Zhang and Iryna Gurevych
EMNLP 2021
PDF Code Video
Multilingual AMR-to-Text
Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generation
Leonardo F. R. Ribeiro, Jonas Pfeiffer, Yue Zhang and Iryna Gurevych
EMNLP 2021
PDF Code
Graph-to-Text
Investigating Pretrained Language Models for Graph-to-Text Generation
Leonardo F. R. Ribeiro, Martin Schmitt, Hinrich Schütze and Iryna Gurevych
NLP for Conversational AI, EMNLP 2021
PDF Code Video
Graformer
Modeling Graph Structure via Relative Position for Text Generation from Knowledge Graphs
Martin Schmitt, Leonardo F. R. Ribeiro, Philipp Dufter, Iryna Gurevych, Hinrich Schütze
TextGraphs-15, NAACL 2021
PDF Code
Global and Local Node Contexts
Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs
Leonardo F. R. Ribeiro, Yue Zhang, Claire Gardent and Iryna Gurevych
TACL 2020
PDF Code Video
Dual Graph Representations
Enhancing AMR-to-Text Generation with Dual Graph Representations
Leonardo F. R. Ribeiro, Claire Gardent and Iryna Gurevych
EMNLP 2019
PDF Code
Ranking Generated Summaries
Ranking Generated Summaries by Correctness: An Interesting but Challenging Application for Natural Language Inference
Tobias Falke, Leonardo F. R. Ribeiro, Prasetya Ajie Utama, Ido Dagan and Iryna Gurevych
ACL 2019
PDF Data
MCTS Ataxx
Performance of Monte Carlo Tree Search Algorithms when Playing the Game Ataxx
Leonardo F. R. Ribeiro, Daniel R. Figueiredo
ENIAC 2018
PDF
struc2vec
struc2vec: Learning Node Representations from Structural Identity
Leonardo F. R. Ribeiro, Pedro H. P. Saverese, Daniel R. Figueiredo
KDD 2017
PDF Code
Ranking Lawyers
Ranking lawyers using a social network induced by legal cases
Leonardo F. R. Ribeiro, Daniel R. Figueiredo
JBCS 2017
PDF

Professional Service

Editorial & Chairing Roles
  • Senior Area Chair (Resources and Evaluation) - NAACL 2025
  • Tutorial Chair - The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024)
  • Area Chair (Summarization, Machine Learning for NLP [ARR Action Editor]) - The 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2024)
  • Area Chair (Summarization [ARR Action Editor]) - Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2024)
  • Area Chair (Natural Language Generation, Summarization and Simplification) - The 29th International Conference on Computational Linguistics (COLING 2022)
Reviewing & Program Committee

Served as Reviewer/Program Committee Member in the following events:

  • ACL Rolling Review (ARR)
  • Conference on Empirical Methods in Natural Language Processing (EMNLP): 2020, 2021, 2022, 2023
  • Annual Meeting of the Association for Computational Linguistics (ACL): 2021, 2023
  • Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): 2021
  • AAAI Conference on Artificial Intelligence (AAAI): 2021, 2022, 2023, 2024
  • LREC-COLING 2024 - The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation: 2024
  • Generation, Evaluation & Metrics (GEM) Workshop: 2022, 2023
  • Evaluation and Comparison of NLP Systems (Eval4NLP): 2020, 2021, 2022, 2023
  • Workshop on Graph-Based Natural Language Processing (TextGraphs): 2020, 2021, 2022
  • Workshop on Knowledge Extraction and Integration for Deep Learning Architectures (DeeLIO): 2022
  • Workshop on Graph Learning Benchmarks (GBL): 2022, 2023
  • Brazilian Conference on Intelligent Systems (BRACIS): 2020, 2021, 2022, 2023
  • Symposium on Knowledge Discovery, Mining and Learning (KDMiLe): 2023
  • Workshop on Multilingual Surface Realization: 2019, 2020
Journal Reviewing

Served as reviewer to the following journals:

  • Journal of Machine Learning Research (JMLR)
  • Language Resources and Evaluation (LREV)