Zobrazeno 1 - 10
of 40 469
pro vyhledávání: '"KHALIFA, A."'
This survey offers a comprehensive overview of Large Language Models (LLMs) designed for Arabic language and its dialects. It covers key architectures, including encoder-only, decoder-only, and encoder-decoder models, along with the datasets used for
Externí odkaz:
http://arxiv.org/abs/2410.20238
We present the design, development, and experimental validation of BlueME, a compact magnetoelectric (ME) antenna array system for underwater robot-to-robot communication. BlueME employs ME antennas operating at their natural mechanical resonance fre
Externí odkaz:
http://arxiv.org/abs/2411.09241
Language models (LMs) have demonstrated an improved capacity to handle long-context information, yet existing long-context benchmarks primarily measure LMs' retrieval abilities with extended inputs, e.g., pinpointing a short phrase from long-form tex
Externí odkaz:
http://arxiv.org/abs/2411.07130
Language models (LMs) hallucinate. We inquire: Can we detect and mitigate hallucinations before they happen? This work answers this research question in the positive, by showing that the internal representations of LMs provide rich signals that can b
Externí odkaz:
http://arxiv.org/abs/2410.02899
Autor:
Alami, Reda, Almansoori, Ali Khalifa, Alzubaidi, Ahmed, Seddik, Mohamed El Amine, Farooq, Mugariya, Hacid, Hakim
We demonstrate that preference optimization methods can effectively enhance LLM safety. Applying various alignment techniques to the Falcon 11B model using safety datasets, we achieve a significant boost in global safety score (from $57.64\%$ to $99.
Externí odkaz:
http://arxiv.org/abs/2409.07772
Autor:
Al-Khalifa, Shahad, Al-Khalifa, Hend
Despite the growing importance of Arabic as a global language, there is a notable lack of language models pre-trained exclusively on Arabic data. This shortage has led to limited benchmarks available for assessing language model performance in Arabic
Externí odkaz:
http://arxiv.org/abs/2407.00146
Publikováno v:
ELRA and ICCL 2024
Label errors are a common issue in machine learning datasets, particularly for tasks such as Named Entity Recognition. Such label errors might hurt model training, affect evaluation results, and lead to an inaccurate assessment of model performance.
Externí odkaz:
http://arxiv.org/abs/2408.12362
We investigate the spontaneous disintegration of magnons in two-dimensional ferromagnets and antiferromagnets dominated by long-range dipolar interactions. Analyzing kinematic constraints, we show that the unusual dispersion of dipolar ferromagnets i
Externí odkaz:
http://arxiv.org/abs/2407.19011
Autor:
Barthet, Matthew, Gallotta, Roberto, Khalifa, Ahmed, Liapis, Antonios, Yannakakis, Georgios N.
Game environments offer a unique opportunity for training virtual agents due to their interactive nature, which provides diverse play traces and affect labels. Despite their potential, no reinforcement learning framework incorporates human affect mod
Externí odkaz:
http://arxiv.org/abs/2407.18316
Autonomously tailoring content to a set of predetermined affective patterns has long been considered the holy grail of affect-aware human-computer interaction at large. The experience-driven procedural content generation framework realises this visio
Externí odkaz:
http://arxiv.org/abs/2408.06346