EMEmilio Monti

Emilio Monti

*This is an algorithmically generated author record based on publicly available information.

Emilio Monti has a total of 7 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Enhancing Contextual Understanding in Large Language Models through Contrastive Decoding

    by Zheng Zhao, Emilio Monti, Jens Lehmann, Haytham Assem

    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 knowledge sources: 1) prior (parametric) knowledge from pretraining, and 2) contextual (non-parametric) knowledge from input prompts. The study addresses the open question of how LLMs effectively balance these knowledge sources during the generation process, specifically in the context of open-domain question answering. To address this issue, we introduce a novel approach integrating contrastive decoding with adversarial irrelevant passages as negative samples to enhance robust context grounding during generation. Notably, our method operates at inference time without requiring further training. We conduct comprehensive experiments to demonstrate its applicability and effectiveness, providing empirical evidence showcasing its superiority over existing methodologies. Our code is publicly available at: https://github.com/amazon-science/ContextualUnderstanding-ContrastiveDecoding.

  • Open Access

    Enhancing Contextual Understanding in Large Language Models through Contrastive Decoding

    by Zheng Zhao, Emilio Monti, Jens Lehmann, Haytham Assem

    Zheng Zhao, Emilio Monti, Jens Lehmann, Haytham Assem. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.


  • Open Access

    Handling Ontology Gaps in Semantic Parsing

    by Andrea Bacciu, Marco Damonte, Marco Basaldella, Emilio Monti

    Andrea Bacciu, Marco Damonte, Marco Basaldella, Emilio Monti. Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024). 2024.


  • Open Access

    Multilingual Neural Semantic Parsing for Low-Resourced Languages

    by Menglin Xia, Emilio Monti

    Multilingual semantic parsing is a cost-effective method that allows a single model to understand different languages. However, researchers face a great imbalance of availability of training data, with English being resource rich, and other languages having much less data. To tackle the data limitation problem, we propose using machine translation to bootstrap multilingual training data from the more abundant English data. To compensate for the data quality of machine translated training data, we utilize transfer learning from pretrained multilingual encoders to further improve the model. To evaluate our multilingual models on human-written sentences as opposed to machine translated ones, we introduce a new multilingual semantic parsing dataset in English, Italian and Japanese based on the Facebook Task Oriented Parsing (TOP) dataset. We show that joint multilingual training with pretrained encoders substantially outperforms our baselines on the TOP dataset and outperforms the state-of-the-art model on the public NLMaps dataset. We also establish a new baseline for zero-shot learning on the TOP dataset. We find that a semantic parser trained only on English data achieves a zero-shot performance of 44.9% exact-match accuracy on Italian sentences.