Apolinário Gustavo Dias

Knowing When Retrieval Has Failed: A Cheap, Unsupervised Signal That Generalizes Across Domains

Retrieval-augmented generation fails silently: when the retriever returns irrelevant passages, the language model answers anyway, and in high-stakes domains such as mental health question answering a fluent answer built on bad context can be harmful. For anyone running RAG who ne...

Order Inversions in Aggressive Low-Rank Compression: Activation Choice, Training Regime, and the Metric

Two decisions made before a network is compressed are usually treated as settled by uncompressed performance: which activation function to use, and whether to compress after training or to train under the rank constraint from the start. We show that both decisions reverse under a...

Order Inversions in Aggressive Low-Rank Compression: Activation Choice, Training Regime, and the Metric

Two decisions made before a network is compressed are usually treated as settled by uncompressed performance: which activation function to use, and whether to compress after training or to train under the rank constraint from the start. We show that both decisions reverse under a...