Papers by Marc Felix Brinner

2 papers
SemCSE: Semantic Contrastive Sentence Embeddings Using LLM-Generated Summaries For Scientific Abstracts (2025.emnlp-main)

Copied to clipboard

Challenge: SemCSE is an unsupervised method for learning semantic embeddings of scientific texts .
Approach: They propose an unsupervised method for learning semantic embeddings of scientific texts that leverages LLM-generated scientific summaries to train a model that positions semantically related summary closer together in the embeddable space.
Outcome: The proposed method achieves state-of-the-art performance on the SciRepEval benchmark for scientific text embeddings, highlighting the benefits of a semantically focused training approach.
Enhancing Domain-Specific Encoder Models with LLM-Generated Data: How to Leverage Ontologies, and How to Do Without Them (2025.findings-emnlp)

Copied to clipboard

Challenge: a new method for continual pretraining transformer encoder models is proposed for specialized domains with limited training data.
Approach: They propose to use LLM-generated data to enrich domain-specific ontologies and pretrain transformer encoder models as an ontology-informed embedding model for concept definitions.
Outcome: The proposed method improves on standard MLM pretraining on invasion biology domains.

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