8 citations · 16 across the 48 of their papers we have counts for
9 papers · 1 filter
Probing Context Localization of Polysemous Words in Pre-trained Language Model Sub-Layers
Soniya Vijayakumar, Josef van Genabith, Simon Ostermann
In the era of high performing Large Language Models, researchers have widely acknowledged that contextual word representations are one of the key drivers in achieving top performan…
GrEmLIn: A Repository of Green Baseline Embeddings for 87 Low-Resource Languages Injected with Multilingual Graph Knowledge
Daniil Gurgurov, Rishu Kumar, Simon Ostermann
Contextualized embeddings based on large language models (LLMs) are available for various languages, but their coverage is often limited for lower resourced languages. Using LLMs f…
Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem
Qianli Wang, Tatiana Anikina, Nils Feldhus +3
Natural language explanations (NLEs) are vital for elucidating the reasoning behind large language model (LLM) decisions. Many techniques have been developed to generate NLEs using…
Task Prompt Vectors: Effective Initialization through Multi-Task Soft-Prompt Transfer
Robert Belanec, Simon Ostermann, Ivan Srba +1
Prompt tuning is an efficient solution for training large language models (LLMs). However, current soft-prompt-based methods often sacrifice multi-task modularity, requiring the tr…
Soft Begging: Modular and Efficient Shielding of LLMs against Prompt Injection and Jailbreaking based on Prompt Tuning
Simon Ostermann, Kevin Baum, Christoph Endres +2
Prompt injection (both direct and indirect) and jailbreaking are now recognized as significant issues for large language models (LLMs), particularly due to their potential for harm…
Generative Large Language Models in Automated Fact-Checking: A Survey
Ivan Vykopal, Matúš Pikuliak, Simon Ostermann +1
The rapid spread of false and misleading information on online platforms poses a growing societal challenge, overwhelming the capacity of manual fact-checking and increasing the de…