6 papers
Quantifying Retriever-Generator Alignment in RAG with Local Explanations
Korbinian Randl, Guido Rocchietti, Aron Henriksson +3
Retrieval-Augmented Generation (RAG) systems combine dense retrievers and language models to ground their outputs in external documents. However, the interaction between these comp…
Multimodal Machine Learning for Early Prediction of Metastasis in a Swedish Multi-Cancer Cohort
Franco Rugolon, Korbinian Randl, Braslav Jovanovic +2
Multimodal Machine Learning offers a holistic view of a patient's status, integrating structured and unstructured data from electronic health records (EHR). We propose a framework…
CHiL(L)Grader: Calibrated Human-in-the-Loop Short-Answer Grading
Pranav Raikote, Korbinian Randl, Ioanna Miliou +2
Scaling educational assessment with large language models requires not just accuracy, but the ability to recognize when predictions are trustworthy. Instruction-tuned models tend t…
Efficient Text Classification with Conformal In-Context Learning
Ippokratis Pantelidis, Korbinian Randl, Aron Henriksson
Large Language Models (LLMs) demonstrate strong in-context learning abilities, yet their effectiveness in text classification depends heavily on prompt design and incurs substantia…
SemEval-2025 Task 9: The Food Hazard Detection Challenge
Korbinian Randl, John Pavlopoulos, Aron Henriksson +2
In this challenge, we explored text-based food hazard prediction with long tail distributed classes. The task was divided into two subtasks: (1) predicting whether a web text impli…
Evaluating the Reliability of Self-Explanations in Large Language Models
Korbinian Randl, John Pavlopoulos, Aron Henriksson +1
This paper investigates the reliability of explanations generated by large language models (LLMs) when prompted to explain their previous output. We evaluate two kinds of such self…