25 citations · 50 across the 11 of their papers we have counts for
8 papers · 1 filter
Observable Patterns Are Not Explanations: A Causal-Geometric Analysis of Latent Reasoning Models
Darpan Aswal, Thomas Palmeira Ferraz, Yongxin Zhou +1
Latent reasoning models (LRMs) replace explicit chain-of-thought with continuous thoughts. Recent work treats observable latent-state patterns, such as BFS-like frontiers and decod…
Enriching GNNs with Text Contextual Representations for Detecting Disinformation Campaigns on Social Media
Bruno Croso Cunha da Silva, Thomas Palmeira Ferraz, Roseli De Deus Lopes
Disinformation on social media poses both societal and technical challenges, requiring robust detection systems. While previous studies have integrated textual information into pro…
No Argument Left Behind: Overlapping Chunks for Faster Processing of Arbitrarily Long Legal Texts
Israel Fama, Bárbara Bueno, Alexandre Alcoforado +3
In a context where the Brazilian judiciary system, the largest in the world, faces a crisis due to the slow processing of millions of cases, it becomes imperative to develop effici…
LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints
Thomas Palmeira Ferraz, Kartik Mehta, Yu-Hsiang Lin +7
Instruction following is a key capability for LLMs. However, recent studies have shown that LLMs often struggle with instructions containing multiple constraints (e.g. a request to…
Efficient Compression of Multitask Multilingual Speech Models
Thomas Palmeira Ferraz
Whisper is a multitask and multilingual speech model covering 99 languages. It yields commendable automatic speech recognition (ASR) results in a subset of its covered languages, b…
From Random to Informed Data Selection: A Diversity-Based Approach to Optimize Human Annotation and Few-Shot Learning
Alexandre Alcoforado, Thomas Palmeira Ferraz, Lucas Hideki Okamura +5
A major challenge in Natural Language Processing is obtaining annotated data for supervised learning. An option is the use of crowdsourcing platforms for data annotation. However,…
Multilingual DistilWhisper: Efficient Distillation of Multi-task Speech Models via Language-Specific Experts
Thomas Palmeira Ferraz, Marcely Zanon Boito, Caroline Brun +1
Whisper is a multitask and multilingual speech model covering 99 languages. It yields commendable automatic speech recognition (ASR) results in a subset of its covered languages, b…
ZeroBERTo: Leveraging Zero-Shot Text Classification by Topic Modeling
Alexandre Alcoforado, Thomas Palmeira Ferraz, Rodrigo Gerber +5
Traditional text classification approaches often require a good amount of labeled data, which is difficult to obtain, especially in restricted domains or less widespread languages.…