Oskar Wysocki — accepted AI-conference papers

2025

SylloBio-NLI: Evaluating Large Language Models on Biomedical Syllogistic Reasoning

Magdalena Wysocka, Danilo Carvalho, Oskar Wysocki, Marco Valentino, Andre Freitas

NAACL 2025long

Syllogistic reasoning is crucial for Natural Language Inference (NLI). This capability is particularly significant in specialized domains such as biomedicine, where it can support automatic evidence interpretation and scientific discovery. This paper presents SylloBio-NLI, a novel framework that lev…

Cited by 2 Source ↗PDF ↗Scholar ↗

2024

An LLM-based Knowledge Synthesis and Scientific Reasoning Framework for Biomedical Discovery

Oskar Wysocki, Danilo Carvalho, Alex Bogatu, Andre Freitas

ACL 2024system demonstrations

We present BioLunar, developed using the Lunar framework, as a tool for supporting biological analyses, with a particular emphasis on molecular-level evidence enrichment for biomarker discovery in oncology. The platform integrates Large Language Models (LLMs) to facilitate complex scientific reasoni…

Cited by 24 Source ↗PDF ↗code ↗Scholar ↗