Papers by Alberto Purpura

5 papers
GRAID: Synthetic Data Generation with Geometric Constraints and Multi-Agentic Reflection for Harmful Content Detection (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) are expensive to run within a large-scale system and not ideal for low-latency use cases.
Approach: They propose a pipeline that leverages Large Language Models (LLMs) for dataset augmentation.
Outcome: The proposed pipeline improves the performance of a harmful text classification dataset using Large Language Models (LLMs).
Accelerating the Discovery of Semantic Associations from Medical Literature: Mining Relations Between Diseases and Symptoms (2022.emnlp-industry)

Copied to clipboard

Challenge: Existing methods to extract semantic associations from medical literature do not take into account the semantics of sentences from which entity co-occurrences are extracted.
Approach: They propose a system for the automatic discovery of semantic associations between different entities such as diseases and their symptoms using a semantic network and a binary relation classification model trained with distant supervision.
Outcome: The proposed system validates the extracted associations against a publicly available list of disease-symptom pairs against 14M PubMed abstracts.
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.
Deconstructing Instruction-Following: A New Benchmark for Granular Evaluation of Large Language Model Instruction Compliance Abilities (2026.eacl-long)

Copied to clipboard

Challenge: Existing benchmarks for ensuring Large Language Models (LLMs) follow complex instructions fail to reflect real-world use or isolate compliance from task success.
Approach: They propose a modular framework that uses a dynamically generated dataset with up to 20 application-oriented generation constraints to enable a granular and independent analysis of LLM instruction compliance.
Outcome: The proposed framework reveals that compliance is not a monolithic capability but varies significantly with constraint type, quantity, and position.
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.

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