← Search

Katja Hose

2 accepted papers

2026

MultiHal: Multilingual Dataset for Knowledge-Graph Grounded Evaluation of LLM Hallucinations

ICML 2026poster

Large Language Models (LLMs) have inherent limitations of faithfulness and factuality, commonly referred to as hallucinations. Several benchmarks have been developed that provide a test bed for factuality evaluation within the context of English-centric datasets, while relying on supplementary infor…

Cited by 0SourcecodeScholar
2023

Metagenomic Binning using Connectivity-constrained Variational Autoencoders

ICML 2023poster

Current state-of-the-art techniques for metagenomic binning only utilize local features for the individual DNA sequences (contigs), neglecting additional information such as the assembly graph, in which the contigs are connected according to overlapping reads, and gene markers identified in the cont…

Cited by 10SourcePDFScholar