7 papers
Evaluating LLMs on Generating Age-Appropriate Child-Like Conversations
Syed Zohaib Hassan, PÃ¥l Halvorsen, Miriam S. Johnson +1
Large Language Models (LLMs), predominantly trained on adult conversational data, face significant challenges when generating authentic, child-like dialogue for specialized applica…
Enhancing Naturalness in LLM-Generated Utterances through Disfluency Insertion
Syed Zohaib Hassan, Pierre Lison, PÃ¥l Halvorsen
Disfluencies are a natural feature of spontaneous human speech but are typically absent from the outputs of Large Language Models (LLMs). This absence can diminish the perceived na…
A Systematic Approach to Predict the Impact of Cybersecurity Vulnerabilities Using LLMs
Anders Mølmen Høst, Pierre Lison, Leon Moonen
Vulnerability databases, such as the National Vulnerability Database (NVD), offer detailed descriptions of Common Vulnerabilities and Exposures (CVEs), but often lack information o…
Stronger Re-identification Attacks through Reasoning and Aggregation
Lucas Georges Gabriel Charpentier, Pierre Lison
Text de-identification techniques are often used to mask personally identifiable information (PII) from documents. Their ability to conceal the identity of the individuals mentione…
Following Route Instructions using Large Vision-Language Models: A Comparison between Low-level and Panoramic Action Spaces
Vebjørn Haug Kåsene, Pierre Lison
Vision-and-Language Navigation (VLN) refers to the task of enabling autonomous robots to navigate unfamiliar environments by following natural language instructions. While recent L…
Re-identification of De-identified Documents with Autoregressive Infilling
Lucas Georges Gabriel Charpentier, Pierre Lison
Documents revealing sensitive information about individuals must typically be de-identified. This de-identification is often done by masking all mentions of personally identifiable…