Alberto Lumbreras — accepted AI-conference papers

2025

SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generation

Song Duong, Florian Le Bronnec, Alexandre Allauzen, Vincent Guigue, Alberto Lumbreras, Laure Soulier +1

ICLR 2025poster

Large Language Models (LLMs), when used for conditional text generation, often produce hallucinations, i.e., information that is unfaithful or not grounded in the input context. This issue arises in typical conditional text generation tasks, such as text summarization and data-to-text generation, wh…

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

Learning from Multiple Sources for Data-to-Text and Text-to-Data

Song Duong, Alberto Lumbreras, Mike Gartrell, Patrick Gallinari

AISTATS 2023poster

Data-to-text (D2T) and text-to-data (T2D) are dual tasks that convert structured data, such as graphs or tables into fluent text, and vice versa. These tasks are usually handled separately and use corpora extracted from a single source. Current systems leverage pre-trained language models fine-tuned…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗

2018

Closed-form Marginal Likelihood in Gamma-Poisson Matrix Factorization

Louis Filstroff, Alberto Lumbreras, Cédric Févotte

ICML 2018oral

We present novel understandings of the Gamma-Poisson (GaP) model, a probabilistic matrix factorization model for count data. We show that GaP can be rewritten free of the score/activation matrix. This gives us new insights about the estimation of the topic/dictionary matrix by maximum marginal likel…

Cited by 6 Source ↗PDF ↗Scholar ↗