Výsledky vyhledávání - "Semmann, Martin"

Report

Wiping out the limitations of Large Language Models -- A Taxonomy for Retrieval Augmented Generation

Autor: Li, Mahei Manhai, Nikishina, Irina, Sevgili, Özge, Semmann, Martin

Current research on RAGs is distributed across various disciplines, and since the technology is evolving very quickly, its unit of analysis is mostly on technological innovations, rather than applications in business contexts. Thus, in this research,

Externí odkaz: http://arxiv.org/abs/2408.02854

Zobrazit plný text záznamu

Report

Demarked: A Strategy for Enhanced Abusive Speech Moderation through Counterspeech, Detoxification, and Message Management

Autor: Yimam, Seid Muhie, Dementieva, Daryna, Fischer, Tim, Moskovskiy, Daniil, Rizwan, Naquee, Saha, Punyajoy, Roy, Sarthak, Semmann, Martin, Panchenko, Alexander, Biemann, Chris, Mukherjee, Animesh

Despite regulations imposed by nations and social media platforms, such as recent EU regulations targeting digital violence, abusive content persists as a significant challenge. Existing approaches primarily rely on binary solutions, such as outright

Externí odkaz: http://arxiv.org/abs/2406.19543

Zobrazit plný text záznamu

Report

New Kids on the Block: On the impact of information retrieval on contextual resource integration patterns

Autor: Semmann, Martin, Li, Mahei Manhei

The rise of new modes of interaction with AI skyrocketed the popularity, applicability, and amount of use cases. Despite this evolution, conceptual integration is falling behind. Studies suggest that there is hardly a systematization in using AI in o

Externí odkaz: http://arxiv.org/abs/2312.07878

Zobrazit plný text záznamu