Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userMoral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences
القصص الأخلاقية: تقع التفكير في القواعد والمحتة والإجراءات وعواقبها
387
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في الإعدادات الاجتماعية، يخضع الكثير من السلوك البشري قواعد سلوك غير معلن في المعايير المجتمعية. بالنسبة للأنظمة الاصطناعية التي سيتم دمجها بالكامل في البيئات الاجتماعية، فإن الالتزام بهذه القواعد هو شرط أساسي. للتحقيق في ما إذا كانت نماذج توليد اللغة يمكن أن تكون بمثابة مشاكل سلوكية للأنظمة المنتشرة في الإعدادات الاجتماعية، فإننا نقيم قدرتها على توليد أوصاف عمل تحقق أهدافا محددة مسبقا في القيود المعيارية. علاوة على ذلك، نحن ندرس إذا كانت النماذج يمكن أن تتوقع عواقب من المحتمل إجراءات إما مراقبة أو تنتهك المعايير المعروفة، أو شرح سبب تفضيل بعض الإجراءات من خلال توليد فرضيات المعايير ذات الصلة. لهذا الغرض، نقدم قصصا أخلاقية، ومجموعة بيانات من جمهور الحشد من الروايات المنظمة، المتفرعة لدراسة المنطق الاجتماعي المحدد، الموجه نحو الأهداف. أخيرا، نقترح استراتيجيات فك التشفير التي تجمع بين نماذج خبراء متعددة لتحسين جودة الإجراءات الناتجة والآثار والمؤسسات القوية بشكل كبير.
In social settings, much of human behavior is governed by unspoken rules of conduct rooted in societal norms. For artificial systems to be fully integrated into social environments, adherence to such norms is a central prerequisite. To investigate whether language generation models can serve as behavioral priors for systems deployed in social settings, we evaluate their ability to generate action descriptions that achieve predefined goals under normative constraints. Moreover, we examine if models can anticipate likely consequences of actions that either observe or violate known norms, or explain why certain actions are preferable by generating relevant norm hypotheses. For this purpose, we introduce Moral Stories, a crowd-sourced dataset of structured, branching narratives for the study of grounded, goal-oriented social reasoning. Finally, we propose decoding strategies that combine multiple expert models to significantly improve the quality of generated actions, consequences, and norms compared to strong baselines.
References used
https://aclanthology.org/
rate research
Read More
Human-assisting systems such as dialogue systems must take thoughtful, appropriate actions not only for clear and unambiguous user requests, but also for ambiguous user requests, even if the users themselves are not aware of their potential requireme
nts. To construct such a dialogue agent, we collected a corpus and developed a model that classifies ambiguous user requests into corresponding system actions. In order to collect a high-quality corpus, we asked workers to input antecedent user requests whose pre-defined actions could be regarded as thoughtful. Although multiple actions could be identified as thoughtful for a single user request, annotating all combinations of user requests and system actions is impractical. For this reason, we fully annotated only the test data and left the annotation of the training data incomplete. In order to train the classification model on such training data, we applied the positive/unlabeled (PU) learning method, which assumes that only a part of the data is labeled with positive examples. The experimental results show that the PU learning method achieved better performance than the general positive/negative (PN) learning method to classify thoughtful actions given an ambiguous user request.
Using topic modeling and lexicon-based word similarity, we find that stories generated by GPT-3 exhibit many known gender stereotypes. Generated stories depict different topics and descriptions depending on GPT-3's perceived gender of the character i
n a prompt, with feminine characters more likely to be associated with family and appearance, and described as less powerful than masculine characters, even when associated with high power verbs in a prompt. Our study raises questions on how one can avoid unintended social biases when using large language models for storytelling.
This study deals with the role that the mother should play in raising her
children in a virtuous and benign education in order to provide them with the
necessary values that enable them to assume their future responsibilities at all
levels. The st
udy deals with many aspects, first: the nature of the role of the mother
in the upbringing of her children, second: the general rules used in raising children,
the moral needs of childhood, Sixth: Ethical values necessary for raising children
healthy education. In conclusion, several proposals were made to contribute to the
goal of the study to take advantage of the mother's creative abilities in raising
children and to prepare a healthy, moral and moral generation armed with good
morals as a way to make a successful future.
This study tries to show the importance of the story title and its
significance in children's stories. It displays the sense of the subject and
point to the resources of titles of the children's stories, through critical
studying of groups of children's stories in the Arab world.
Story visualization is an underexplored task that falls at the intersection of many important research directions in both computer vision and natural language processing. In this task, given a series of natural language captions which compose a story
, an agent must generate a sequence of images that correspond to the captions. Prior work has introduced recurrent generative models which outperform text-to-image synthesis models on this task. However, there is room for improvement of generated images in terms of visual quality, coherence and relevance. We present a number of improvements to prior modeling approaches, including (1) the addition of a dual learning framework that utilizes video captioning to reinforce the semantic alignment between the story and generated images, (2) a copy-transform mechanism for sequentially-consistent story visualization, and (3) MART-based transformers to model complex interactions between frames. We present ablation studies to demonstrate the effect of each of these techniques on the generative power of the model for both individual images as well as the entire narrative. Furthermore, due to the complexity and generative nature of the task, standard evaluation metrics do not accurately reflect performance. Therefore, we also provide an exploration of evaluation metrics for the model, focused on aspects of the generated frames such as the presence/quality of generated characters, the relevance to captions, and the diversity of the generated images. We also present correlation experiments of our proposed automated metrics with human evaluations.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
