7 papers
An Isotropic Approach to Efficient Uncertainty Quantification with Gradient Norms
Nils Grünefeld, Jes Frellsen, Christian Hardmeier
Existing methods for quantifying predictive uncertainty in neural networks are either computationally intractable for large language models or require access to training data that…
Epistemic Injustice in Language Models: An Audit of Pretraining Filters and Guardrails
Marco Antonio Stranisci, A Pranav, Rossana Damiano +2
Modern language models rely on pretraining filters to remove undesirable content from training corpora and inference-time guardrails to suppress undesirable outputs during deployme…
Tracing Uncertainty in Language Model "Reasoning"
Nils Grünefeld, Bertram Højer, Philipp Mondorf +5
Language model (LM) "reasoning", commonly described as Chain-of-Thought or test-time scaling, often improves benchmark performance, but the dynamics underlying this process remain…
Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missing
Dennis Ulmer, Alexandra Lorson, Ivan Titov +1
Human users increasingly communicate with large language models (LLMs), but LLMs suffer from frequent overconfidence in their output, even when its accuracy is questionable, which…
What Are They Filtering Out? An Experimental Benchmark of Filtering Strategies for Harm Reduction in Pretraining Datasets
Marco Antonio Stranisci, Christian Hardmeier
Data filtering strategies are a crucial component to develop safe Large Language Models (LLM), since they support the removal of harmful contents from pretraining datasets. There i…
Code Like Humans: A Multi-Agent Solution for Medical Coding
Andreas Motzfeldt, Joakim Edin, Casper L. Christensen +3
In medical coding, experts map unstructured clinical notes to alphanumeric codes for diagnoses and procedures. We introduce Code Like Humans: a new agentic framework for medical co…