Hâfız-i Şirâzî’nin Gazellerinde Aşk Mefhumunun Değerlendirilmesi
Mukaddime, 2023 Aşk, muhabbetin en üst noktası ve mükemmelliğidir ve tüm büyüleyiciliği, tutkuları ve coşkusuyla, sevginin nihai ve doruk noktasıdır. Aşk, dizginsiz ve kontrol edilemez bazen, kaynayan ve isyankâr bazen de sel gibi ve ateş püskürtendir sevmek, ama yine
Mitat Çekici
doaj +2 more sources
Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback [PDF]
Conference on Empirical Methods in Natural Language Processing, 2023 A trustworthy real-world prediction system should produce well-calibrated confidence scores; that is, its confidence in an answer should be indicative of the likelihood that the answer is correct, enabling deferral to an expert in cases of low-confidence
Katherine Tian +7 more
semanticscholar +1 more source
Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners [PDF]
Conference on Robot Learning, 2023 Large language models (LLMs) exhibit a wide range of promising capabilities -- from step-by-step planning to commonsense reasoning -- that may provide utility for robots, but remain prone to confidently hallucinated predictions.
Allen Z. Ren +13 more
semanticscholar +1 more source
Ask Me Anything: A simple strategy for prompting language models [PDF]
International Conference on Learning Representations, 2022 Large language models (LLMs) transfer well to new tasks out-of-the-box simply given a natural language prompt that demonstrates how to perform the task and no additional training.
Simran Arora +8 more
semanticscholar +1 more source
Learning How to Ask: Querying LMs with Mixtures of Soft Prompts [PDF]
North American Chapter of the Association for Computational Linguistics, 2021 Natural-language prompts have recently been used to coax pretrained language models into performing other AI tasks, using a fill-in-the-blank paradigm (Petroni et al., 2019) or a few-shot extrapolation paradigm (Brown et al., 2020). For example, language
Guanghui Qin, J. Eisner
semanticscholar +1 more source
Fesad û Bêbext di Trajedîya Evînê da: Weku Nimûne Destanên Evîna Mêjûyî
Mukaddime, 2023 Destanên Evîna Mêjûyî cureyekî berbelav ê vegêrana gelêrî ya Kurdî ye. Evînên di van destanan da bi piranî trajîk in û evîndar nagihîjine hev û di dawîyê da dimirin.
Kenan Subaşı
doaj +1 more source
Learning to Execute Actions or Ask Clarification Questions [PDF]
NAACL-HLT, 2022 Collaborative tasks are ubiquitous activities where a form of communication is required in order to reach a joint goal. Collaborative building is one of such tasks.
Zhengxiang Shi, Yue Feng, Aldo Lipani
semanticscholar +1 more source
Klasik Arap Şiirinde Sevgiliye Duyulan Aşk ve Özlemin İfade Edilmesinde Kullanılan İmgeler
Mukaddime, 2023 Aşk teması, farklı ulus ve kültürlerin edebiyatında olduğu gibi Arap edebiyatında da şiirde en çok işlenen konulardan biri olmuştur. Hislerle duyumsanabilen ve deruni bir duygu olması hasebiyle insan hayatında manevi bir yolculuk veya süreç olarak ...
Ahmet Abdülhadioğlu
doaj +1 more source
Artificial intelligence in teaching and learning: what questions should we ask of ChatGPT?
Interactive Learning Environments, 2023 The recent release of ChatGPT, a fl exible and accessible form of arti fi cial intelligence, raises a multitude of questions for those of us interested in interactive learning environments.
Pericles 'Asher' Rospigliosi
semanticscholar +1 more source
Just Ask: Learning to Answer Questions from Millions of Narrated Videos [PDF]
IEEE International Conference on Computer Vision, 2020 Recent methods for visual question answering rely on large-scale annotated datasets. Manual annotation of questions and answers for videos, however, is tedious, expensive and prevents scalability.
Antoine Yang +4 more
semanticscholar +1 more source