Papers by Gabriele Picco

5 papers
Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language Models (2023.acl-long)

Copied to clipboard

Challenge: generative large language models (LLMs) are widely used but fine-tuned to improve performance on downstream applications leads to violations of model licenses, model theft, and copyright infringement.
Approach: They propose to trace back the origin of a model trained to its pre-trained base model . they use different knowledge levels and attribution strategies to find out how the model was trained .
Outcome: The proposed method can trace back 8 out of 10 fine tuned models with different knowledge levels and attribution strategies.
Neural Unification for Logic Reasoning over Natural Language (2021.findings-emnlp)

Copied to clipboard

Challenge: Automated Theorem Proving (ATP) is a computer program that can show that conjectures are logical consequences of a set of axioms.
Approach: They propose a transformer-based architecture for deriving conjectures given axioms . they propose 'neural unifier' and relative training procedure to train the model .
Outcome: The proposed architectures are able to answer queries with deep queries with a relatively low training time.
Zshot: An Open-source Framework for Zero-Shot Named Entity Recognition and Relation Extraction (2023.acl-demo)

Copied to clipboard

Challenge: ZSL is a machine learning field that uses textual descriptions of entities or relations to perform tasks that are not seen during training.
Approach: They propose a framework that allows researchers to compare state-of-the-art ZSL methods with standard benchmark datasets.
Outcome: The proposed framework compares state-of-the-art methods with benchmark datasets and provides APIs for production under the standard SpaCy NLP pipeline.
Description Boosting for Zero-Shot Entity and Relation Classification (2024.findings-acl)

Copied to clipboard

Challenge: Named Entity Recognition and Relation Extraction (RE) methods are expensive and require domain experts for data acquisition and labeling.
Approach: They propose a strategy for generating variations of an initial description, a heuristic for ranking them and an ensemble method capable of boosting the predictions of zero-shot models.
Outcome: The proposed method outperforms existing approaches and achieves new SOTA results on four different entity and relation classification datasets.
Towards Protecting Vital Healthcare Programs by Extracting Actionable Knowledge from Policy (2021.findings-acl)

Copied to clipboard

Challenge: In the U.S., an estimated annual amount of USD$20-30B is lost to Fraud, Waste and abuse (FWA)
Approach: They propose a method for automatically extracting knowledge from healthcare policy documents into a semantically-meaningful knowledge graph of rules.
Outcome: The proposed method fuses advances in dependency parsing with a policy ontology to transform the content of regulatory healthcare policy into human-friendly policy rules with human oversight.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations