Zobrazeno 1 - 10
of 2 693
pro vyhledávání: '"A, Suchánek"'
Autor:
Hamdani, Rajaa El, Bonald, Thomas, Malliaros, Fragkiskos, Holzenberger, Nils, Suchanek, Fabian
This paper investigates the factuality of large language models (LLMs) as knowledge bases in the legal domain, in a realistic usage scenario: we allow for acceptable variations in the answer, and let the model abstain from answering when uncertain. F
Externí odkaz:
http://arxiv.org/abs/2409.11798
Storytelling is an integral part of human experience and plays a crucial role in social interactions. Thus, Automatic Story Evaluation (ASE) and Generation (ASG) could benefit society in multiple ways, but they are challenging tasks which require hig
Externí odkaz:
http://arxiv.org/abs/2405.13769
Autor:
Wang, Hao, Qin, Jiayou, Chen, Xiwen, Bastola, Ashish, Suchanek, John, Gong, Zihao, Razi, Abolfazl
Assistive visual navigation systems for visually impaired individuals have become increasingly popular thanks to the rise of mobile computing. Most of these devices work by translating visual information into voice commands. In complex scenarios wher
Externí odkaz:
http://arxiv.org/abs/2404.17031
Autor:
Wang, Hao, Qin, Jiayou, Bastola, Ashish, Chen, Xiwen, Suchanek, John, Gong, Zihao, Razi, Abolfazl
This paper explores the potential of Large Language Models(LLMs) in zero-shot anomaly detection for safe visual navigation. With the assistance of the state-of-the-art real-time open-world object detection model Yolo-World and specialized prompts, th
Externí odkaz:
http://arxiv.org/abs/2403.12415
Large Language Models (LLMs), including ChatGPT and LLaMA, are susceptible to generating hallucinated answers in a confident tone. While efforts to elicit and calibrate confidence scores have proven useful, recent findings show that controlling uncer
Externí odkaz:
http://arxiv.org/abs/2402.04957
Phrase representations play an important role in data science and natural language processing, benefiting various tasks like Entity Alignment, Record Linkage, Fuzzy Joins, and Paraphrase Classification. The current state-of-the-art method involves fi
Externí odkaz:
http://arxiv.org/abs/2401.10407
We introduce MAFALDA, a benchmark for fallacy classification that merges and unites previous fallacy datasets. It comes with a taxonomy that aligns, refines, and unifies existing classifications of fallacies. We further provide a manual annotation of
Externí odkaz:
http://arxiv.org/abs/2311.09761
Positional Encodings (PEs) are used to inject word-order information into transformer-based language models. While they can significantly enhance the quality of sentence representations, their specific contribution to language models is not fully und
Externí odkaz:
http://arxiv.org/abs/2310.12864
Autor:
Suchanek, Fabian, Alam, Mehwish, Bonald, Thomas, Chen, Lihu, Paris, Pierre-Henri, Soria, Jules
Knowledge Bases (KBs) find applications in many knowledge-intensive tasks and, most notably, in information retrieval. Wikidata is one of the largest public general-purpose KBs. Yet, its collaborative nature has led to a convoluted schema and taxonom
Externí odkaz:
http://arxiv.org/abs/2308.11884
In recent years, understanding the decision-making process of black-box models has become not only a legal requirement but also an additional way to assess their performance. However, the state of the art post-hoc interpretation approaches rely on sy
Externí odkaz:
http://arxiv.org/abs/2305.11311