5 papers
RAGognizer: Hallucination-Aware Fine-Tuning via Detection Head Integration
Fabian Ridder, Laurin Lessel, Malte Schilling
Retrieval-Augmented Generation (RAG) is widely used to augment the input to Large Language Models (LLMs) with external information, such as recent or domain-specific knowledge. Non…
Stochastic Parroting in Temporal Attention -- Regulating the Diagonal Sink
Victoria Hankemeier, Malte Schilling
Spatio-temporal models analyze spatial structures and temporal dynamics, which makes them prone to information degeneration among space and time. Prior literature has demonstrated…
Classifying German Language Proficiency Levels Using Large Language Models
Elias-Leander Ahlers, Witold Brunsmann, Malte Schilling
Assessing language proficiency is essential for education, as it enables instruction tailored to learners needs. This paper investigates the use of Large Language Models (LLMs) for…
Tailored Architectures for Time Series Forecasting: Evaluating Deep Learning Models on Gaussian Process-Generated Data
Victoria Hankemeier, Malte Schilling
Developments in Deep Learning have significantly improved time series forecasting by enabling more accurate modeling of complex temporal dependencies inherent in sequential data. T…
The HalluRAG Dataset: Detecting Closed-Domain Hallucinations in RAG Applications Using an LLM's Internal States
Fabian Ridder, Malte Schilling
Detecting hallucinations in large language models (LLMs) is critical for enhancing their reliability and trustworthiness. Most research focuses on hallucinations as deviations from…