5 papers
Beyond pass@k: Redundancy-Aware RLVR for Multi-Sample Code Generation
Le Bronnec Florian, Alexandre Verine, Rio Yokota +1
LLMs for code generation are commonly evaluated in repeated-sampling settings using Pass@k, where multiple candidate programs are executed against unit tests under a finite samplin…
Equalized Generative Treatment: Matching f-divergences for Fairness in Generative Models
Alexandre Verine, Rafael Pinot, Florian Le Bronnec
Fairness is a crucial concern for generative models, which not only reflect but can also amplify societal and cultural biases. Existing fairness notions for generative models are l…
Improving Diversity in Language Models: When Temperature Fails, Change the Loss
Alexandre Verine, Florian Le Bronnec, Kunhao Zheng +3
Increasing diversity in language models is a challenging yet essential objective. A common approach is to raise the decoding temperature. In this work, we investigate this approach…
Improving Discriminator Guidance in Diffusion Models
Alexandre Verine, Ahmed Mehdi Inane, Florian Le Bronnec +2
Discriminator Guidance has become a popular method for efficiently refining pre-trained Score-Matching Diffusion models. However, in this paper, we demonstrate that the standard im…
SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generation
Song Duong, Florian Le Bronnec, Alexandre Allauzen +4
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. Th…