← Search

Emilio Monti

2 accepted papers

2024

Enhancing Contextual Understanding in Large Language Models through Contrastive Decoding

NAACL 2024long

Large language models (LLMs) tend to inadequately integrate input context during text generation, relying excessively on encoded prior knowledge in model parameters, potentially resulting in generated text with factual inconsistencies or contextually unfaithful content. LLMs utilize two primary know…

2021

In Factuality: Efficient Integration of Relevant Facts for Visual Question Answering

ACL 2021short

Visual Question Answering (VQA) methods aim at leveraging visual input to answer questions that may require complex reasoning over entities. Current models are trained on labelled data that may be insufficient to learn complex knowledge representations. In this paper, we propose a new method to enha…