collaborators

6 papers

cs.LG2026

RREDCoT: Segment-Level Reward Redistribution for Reasoning Models

Mykyta Ielanskyi, Kajetan Schweighofer, Lukas Aichberger +1

Recent advancements in reasoning language models have been driven by Reinforcement Learning (RL) fine-tuning. Most often, these rely on the Group Relative Policy Optimization (GRPO…

cs.LG2026

MolecularIQ: Characterizing Chemical Reasoning Capabilities Through Symbolic Verification on Molecular Graphs

Christoph Bartmann, Johannes Schimunek, Mykyta Ielanskyi +3

A molecule's properties are fundamentally determined by its composition and structure encoded in its molecular graph. Thus, reasoning about molecular properties requires the abilit…

cs.LG2025

Improving Uncertainty Estimation through Semantically Diverse Language Generation

Lukas Aichberger, Kajetan Schweighofer, Mykyta Ielanskyi +1

Large language models (LLMs) can suffer from hallucinations when generating text. These hallucinations impede various applications in society and industry by making LLMs untrustwor…

cs.LG2025

Addressing Pitfalls in the Evaluation of Uncertainty Estimation Methods for Natural Language Generation

Mykyta Ielanskyi, Kajetan Schweighofer, Lukas Aichberger +1

Hallucinations are a common issue that undermine the reliability of large language models (LLMs). Recent studies have identified a specific subset of hallucinations, known as confa…

cs.LG2025

Uncertainty Quantification for Regression using Proper Scoring Rules

Alexander Fishkov, Kajetan Schweighofer, Mykyta Ielanskyi +3

Quantifying uncertainty of machine learning model predictions is essential for reliable decision-making, especially in safety-critical applications. Recently, uncertainty quantific…

cs.LG2025

On Information-Theoretic Measures of Predictive Uncertainty

Kajetan Schweighofer, Lukas Aichberger, Mykyta Ielanskyi +1

Reliable estimation of predictive uncertainty is crucial for machine learning applications, particularly in high-stakes scenarios where hedging against risks is essential. Despite…