6 papers
Target-Side Paraphrase Augmentation for Sign Language Translation with Large Language Models
Pedro Dal Bianco, Jean Paul Nunes Reinhold, Oscar Stanchi +3
Sign language translation (SLT) remains constrained by the limited availability of paired sign-video/text corpora and by the heavy-tailed vocabularies typical of real-world dataset…
Mind the Performance Gap: Capability-Behavior Trade-offs in Feature Steering
Eitan Sprejer, Oscar AgustÃn Stanchi, MarÃa Victoria Carro +2
Feature steering has emerged as a promising approach for controlling LLM behavior through direct manipulation of internal representations, offering advantages over prompt engineeri…
AI Debaters are More Persuasive when Arguing in Alignment with Their Own Beliefs
MarÃa Victoria Carro, Denise Alejandra Mester, Facundo Nieto +9
The core premise of AI debate as a scalable oversight technique is that it is harder to lie convincingly than to refute a lie, enabling the judge to identify the correct position.…
HandCraft: Dynamic Sign Generation for Synthetic Data Augmentation
Gaston Gustavo Rios, Pedro Dal Bianco, Franco Ronchetti +4
Sign Language Recognition (SLR) models face significant performance limitations due to insufficient training data availability. In this article, we address the challenge of limited…
Bringing Balance to Hand Shape Classification: Mitigating Data Imbalance Through Generative Models
Gaston Gustavo Rios, Pedro Dal Bianco, Franco Ronchetti +4
Most sign language handshape datasets are severely limited and unbalanced, posing significant challenges to effective model training. In this paper, we explore the effectiveness of…
SignAttention: On the Interpretability of Transformer Models for Sign Language Translation
Pedro Alejandro Dal Bianco, Oscar AgustÃn Stanchi, Facundo Manuel Quiroga +2
This paper presents the first comprehensive interpretability analysis of a Transformer-based Sign Language Translation (SLT) model, focusing on the translation from video-based Gre…