Zobrazeno 1 - 10
of 160 231
pro vyhledávání: '"Computer Science - Artificial Intelligence"'
Autor:
Miranda, Michele, Ruzzetti, Elena Sofia, Santilli, Andrea, Zanzotto, Fabio Massimo, Bratières, Sébastien, Rodolà, Emanuele
Large Language Models (LLMs) represent a significant advancement in artificial intelligence, finding applications across various domains. However, their reliance on massive internet-sourced datasets for training brings notable privacy issues, which a
Externí odkaz:
http://arxiv.org/abs/2408.05212
Unmanned aerial vehicles (UAVs) have revolutionized search and rescue (SAR) operations, but the lack of specialized human detection datasets for training machine learning models poses a significant challenge.To address this gap, this paper introduces
Externí odkaz:
http://arxiv.org/abs/2408.04922
Autor:
Heo, Jaehyuk, Kang, Pilsung
Active learning (AL) aims to enhance model performance by selectively collecting highly informative data, thereby minimizing annotation costs. However, in practical scenarios, unlabeled data may contain out-of-distribution (OOD) samples, leading to w
Externí odkaz:
http://arxiv.org/abs/2408.04917
Research on knowledge graph embeddings has recently evolved into knowledge base embeddings, where the goal is not only to map facts into vector spaces but also constrain the models so that they take into account the relevant conceptual knowledge avai
Externí odkaz:
http://arxiv.org/abs/2408.04913
In this study, we present an innovative fusion of language models and query analysis techniques to unlock cognition in artificial intelligence. Our system seamlessly integrates a Chess engine with a language model, enabling it to predict moves and pr
Externí odkaz:
http://arxiv.org/abs/2408.04910
Explaining decisions of black-box classifiers is both important and computationally challenging. In this paper, we scrutinize explainers that generate feature-based explanations from samples or datasets. We start by presenting a set of desirable prop
Externí odkaz:
http://arxiv.org/abs/2408.04903
Autor:
Bhaumik, Ankita, Strzalkowski, Tomek
Large language models (LLMs) have demonstrated impressive performance in mathematical and commonsense reasoning tasks using chain-of-thought (CoT) prompting techniques. But can they perform emotional reasoning by concatenating `Let's think step-by-st
Externí odkaz:
http://arxiv.org/abs/2408.04906
GlitchProber: Advancing Effective Detection and Mitigation of Glitch Tokens in Large Language Models
Autor:
Zhang, Zhibo, Bai, Wuxia, Li, Yuxi, Meng, Mark Huasong, Wang, Kailong, Shi, Ling, Li, Li, Wang, Jun, Wang, Haoyu
Large language models (LLMs) have achieved unprecedented success in the field of natural language processing. However, the black-box nature of their internal mechanisms has brought many concerns about their trustworthiness and interpretability. Recen
Externí odkaz:
http://arxiv.org/abs/2408.04905
Traditional Graph Neural Networks (GNNs) rely on network homophily, which can lead to performance degradation due to over-smoothing in many real-world heterophily scenarios. Recent studies analyze the smoothing effect (separability) after message-pas
Externí odkaz:
http://arxiv.org/abs/2408.04895
Retrieval augmented generation (RAG) is a process where a large language model (LLM) retrieves useful information from a database and then generates the responses. It is becoming popular in enterprise settings for daily business operations. For examp
Externí odkaz:
http://arxiv.org/abs/2408.04870