Hasil untuk "By religion"

J. Bezdek

Richard M. Ryan, E. Deci

Georges Bataille, R. Hurley

Martha Ene Utaji, Dominica Shanpepe Nyityo

The problem of environmental sustainability in Nigeria is exacerbated by the complex interplay of religious and political influences. Religious doctrines and political frameworks often clash or fail to adequately address environmental issues, leading to ineffective policies and practices. This paper therefore examined the impact of religion and politics on  environmental sustainabilty in Benue State, Nigeria. The study was guided by two research questions and hypotheses. The study employed a correctional survey research design. The study population comprise of 1,454,303 members of all registered religious bodies in Benue State out of which 400 respondents were randomly sampled for the study. The study employed structure questionnaire as instrument of data collection. Data collected was analysed using mean and standard deviation to answer research questions. Hypotheses were tested using chi-square statistical tool. The findings revealed that religion has positive impact on climate change. The study further revealed that religion also has impact on environmental sustainability in Benue State. Tapping into these motivations and combining them with religious teachings about climate change and environmental sustainability could provide a powerful story line to enable the desired change. It was therefore recommended, among other things, that the religious leaders should endeavour to adopt appropriate measures in motivating their members to change their behaviours towards enhance environmental sustainability in the state.

Anudeex Shetty, Amin Beheshti, Mark Dras et al.

Alignment techniques have become central to ensuring that Large Language Models (LLMs) generate outputs consistent with human values. However, existing alignment paradigms often model an averaged or monolithic preference, failing to account for the diversity of perspectives across cultures, demographics, and communities. This limitation is particularly critical in health-related scenarios, where plurality is essential due to the influence of culture, religion, personal values, and conflicting opinions. Despite progress in pluralistic alignment, no prior work has focused on health, likely due to the unavailability of publicly available datasets. To address this gap, we introduce VITAL, a new benchmark dataset comprising 13.1K value-laden situations and 5.4K multiple-choice questions focused on health, designed to assess and benchmark pluralistic alignment methodologies. Through extensive evaluation of eight LLMs of varying sizes, we demonstrate that existing pluralistic alignment techniques fall short in effectively accommodating diverse healthcare beliefs, underscoring the need for tailored AI alignment in specific domains. This work highlights the limitations of current approaches and lays the groundwork for developing health-specific alignment solutions.

Angelie Kraft, Judith Simon, Sonja Schimmler

Question-answering (QA) and reading comprehension (RC) benchmarks are commonly used for assessing the capabilities of large language models (LLMs) to retrieve and reproduce knowledge. However, we demonstrate that popular QA and RC benchmarks do not cover questions about different demographics or regions in a representative way. We perform a content analysis of 30 benchmark papers and a quantitative analysis of 20 respective benchmark datasets to learn (1) who is involved in the benchmark creation, (2) whether the benchmarks exhibit social bias, or whether this is addressed or prevented, and (3) whether the demographics of the creators and annotators correspond to particular biases in the content. Most benchmark papers analyzed provide insufficient information about those involved in benchmark creation, particularly the annotators. Notably, just one (WinoGrande) explicitly reports measures taken to address social representation issues. Moreover, the data analysis revealed gender, religion, and geographic biases across a wide range of encyclopedic, commonsense, and scholarly benchmarks. Our work adds to the mounting criticism of AI evaluation practices and shines a light on biased benchmarks being a potential source of LLM bias by incentivizing biased inference heuristics.

M. Ruel, S. Tambiah

Nur S. Kirabaev

The research examines the problem of different ways of perceiving the ancient philosophical tradition in classical Arab Muslim and medieval European philosophy. It is noted that the difference in the ways of perception is determined, in particular, by the peculiarities of the concept of “knowledge” in Islam and Christianity. In the interaction between Arab Muslim and Christian cultures, stereotypes emerge in mutual perceptions, surprisingly leading to paradoxes like the Christianization and Europeanization of Eastern Peripatetic teachings. Their works were translated into Latin, and their names were "Latinized". The most famous names of philosophers: Ibn Sina (980-1037) is better known in Europe as Avicenna and Ibn Rushd (1126-1198) as Averroes. These thinkers belonged to the school of Eastern Peripateticism. Eastern Peripateticism or Eastern Aristotelianism are terms that denote one of the directions of Arab-Muslim philosophy of the Middle Ages. As is known, it is the representatives of Eastern Peripateticism that are called falasifa (الفلاسفة), and their teachings falsafah (فلسفة). In medieval Arab-Muslim culture, the term "falsafa" referred to ancient philosophy and the teachings of thinkers like al-Farabi (870-950), Ibn Sina, and Ibn Rushd, who were influenced by ancient philosophical models. Unlike European medieval philosophy, a unique aspect of falsafa was that it was neither regarded as nor aspired to be a servant of religion. It is with the name of Ibn Rushd that one of the directions of development of medieval European philosophy is associated - “Latin Averroism”, which as a philosophical term is applied to the direction in scholasticism of the XIII-th century, based on Averroes’ interpretation of Aristotle and underlies the doctrine of “dual truth”, which considered the independence of truths of reason from truths of revelation, and, ultimately, philosophy from religion. The main representatives of this movement were Siger of Brabant (c. 1240-1284) and Boethius of Dacia (c. 1240-1284). The essence of the paradox is that medieval Europe knew the teachings of Averroes but did not know the teachings of Ibn Rushd or perceived them in its own way. At the same time, the Arab East, as the birthplace of Ibn Rushd’s teachings, was not familiar with either the so-called Averroism or the concept of “dual truth”. In this context, the paradox can be explained as a situation that exists in historical reality, but does not have a strictly logical explanation, that is, at first glance, the authorship of Averroes as the creator of the doctrine of “dual truth” seems true, but in fact is an unreliable statement. This is also due to the fact that the concepts and value attitudes of one culture, transferred to explain the phenomena of another culture, form a stereotypical perception of the phenomena of this other culture. At the same time, within the framework of the interaction of cultures, the spread of “Latin Averroism” is one of the examples of the integration of the Arab-Muslim philosophical tradition into medieval European culture.

Safdhinar Muhammad An Noor, Arisy Abror Dzukroni, Nasrullah Nasrullah et al.

This article contends that the principle of mu'âsyaroh bil ma'rûf has been inadequately interpreted, primarily due to its frequent application solely to men, resulting in the neglect and discrimination against women in conceptual formulation and validation. By positioning both men and women as equal participants in defining maqâshid al-syarî'ah, a fairer understanding of mu'asyaraoh bil ma'ruf can be achieved. This qualitative research seeks to redefine the interpretation of mu'âsyarah bil ma'rûf in the Qur'an through the Maqâshid Syarî'ah cum-Mubâdalah approach, integrating the critical concept of mashâlih al-'ibâd in kulliyât al-khams and the Mubâdalah perspective. The Maqâshid al-Syarî'ah cum-Mubâdalah methodology entails merging Maqâshid al-Syarî'ah theory with a perspective emphasizing mutual respect between genders. This study adopts a library research methodology. The findings reveal that, through the Maqâshid al-Syarî'ah cum-Mubâdalah approach, it can be inferred that: 1) mu'asyarah bil ma'ruf extends beyond marital relations to encompass interactions that uphold human values for all individuals; 2) apart from hifdz al-nafs (preservation of life), mu'asyarah bil ma'ruf also encompasses other elements including hifdz al-din (preservation of religion), hifdz al-mal (preservation of wealth), hifdz al-'aql (preservation of intellect), and hifdz al-nasl (preservation of lineage); 3) adherence to the five elements of maqashid sharia is obligatory for both parties engaging in interactions, rather than being imposed solely on one party.

Dawn Lu, Nina Rimsky

We address the challenge of societal bias in Large Language Models (LLMs), focusing on the Llama 2 7B Chat model. As LLMs are increasingly integrated into decision-making processes with substantial societal impact, it becomes imperative to ensure these models do not reinforce existing biases. Our approach employs activation steering to probe for and mitigate biases related to gender, race, and religion. This method manipulates model activations to direct responses towards or away from biased outputs, utilizing steering vectors derived from the StereoSet dataset and custom GPT4 generated gender bias prompts. Our findings reveal inherent gender bias in Llama 2 7B Chat, persisting even after Reinforcement Learning from Human Feedback (RLHF). We also observe a predictable negative correlation between bias and the model's tendency to refuse responses. Significantly, our study uncovers that RLHF tends to increase the similarity in the model's representation of different forms of societal biases, which raises questions about the model's nuanced understanding of different forms of bias. This work also provides valuable insights into effective red-teaming strategies for LLMs using activation steering, particularly emphasizing the importance of integrating a refusal vector.

Rocktim Jyoti Das, Simeon Emilov Hristov, Haonan Li et al.

We introduce EXAMS-V, a new challenging multi-discipline multimodal multilingual exam benchmark for evaluating vision language models. It consists of 20,932 multiple-choice questions across 20 school disciplines covering natural science, social science, and other miscellaneous studies, e.g., religion, fine arts, business, etc. EXAMS-V includes a variety of multimodal features such as text, images, tables, figures, diagrams, maps, scientific symbols, and equations. The questions come in 11 languages from 7 language families. Unlike existing benchmarks, EXAMS-V is uniquely curated by gathering school exam questions from various countries, with a variety of education systems. This distinctive approach calls for intricate reasoning across diverse languages and relies on region-specific knowledge. Solving the problems in the dataset requires advanced perception and joint reasoning over the text and the visual content of the image. Our evaluation results demonstrate that this is a challenging dataset, which is difficult even for advanced vision-text models such as GPT-4V and Gemini; this underscores the inherent complexity of the dataset and its significance as a future benchmark.

Rameez Qureshi, Naïm Es-Sebbani, Luis Galárraga et al.

With the introduction of (large) language models, there has been significant concern about the unintended bias such models may inherit from their training data. A number of studies have shown that such models propagate gender stereotypes, as well as geographical and racial bias, among other biases. While existing works tackle this issue by preprocessing data and debiasing embeddings, the proposed methods require a lot of computational resources and annotation effort while being limited to certain types of biases. To address these issues, we introduce REFINE-LM, a debiasing method that uses reinforcement learning to handle different types of biases without any fine-tuning. By training a simple model on top of the word probability distribution of a LM, our bias agnostic reinforcement learning method enables model debiasing without human annotations or significant computational resources. Experiments conducted on a wide range of models, including several LMs, show that our method (i) significantly reduces stereotypical biases while preserving LMs performance; (ii) is applicable to different types of biases, generalizing across contexts such as gender, ethnicity, religion, and nationality-based biases; and (iii) it is not expensive to train.

Mahek Vora, Tom Blau, Vansh Kachhwal et al.

The revolution of natural language processing via large language models has motivated its use in multidisciplinary areas that include social sciences and humanities and more specifically, comparative religion. Sentiment analysis provides a mechanism to study the emotions expressed in text. Recently, sentiment analysis has been used to study and compare translations of the Bhagavad Gita, which is a fundamental and sacred Hindu text. In this study, we use sentiment analysis for studying selected chapters of the Bible. These chapters are known as the Sermon on the Mount. We utilize a pre-trained language model for sentiment analysis by reviewing five translations of the Sermon on the Mount, which include the King James version, the New International Version, the New Revised Standard Version, the Lamsa Version, and the Basic English Version. We provide a chapter-by-chapter and verse-by-verse comparison using sentiment and semantic analysis and review the major sentiments expressed. Our results highlight the varying sentiments across the chapters and verses. We found that the vocabulary of the respective translations is significantly different. We detected different levels of humour, optimism, and empathy in the respective chapters that were used by Jesus to deliver his message.

Takeshi Kato, Yosuke Tanabe, Mohammad Rezoanul Hoque

Reducing wealth inequality and increasing utility are critical issues. This study reveals the effects of redistribution and consumption morals on wealth inequality and utility. To this end, we present a novel approach that couples the dynamic model of capital, consumption, and utility in macroeconomics with the interaction model of joint business and redistribution in econophysics. With this approach, we calculate the capital (wealth), the utility based on consumption, and the Gini index of these inequality using redistribution and consumption thresholds as moral parameters. The results show that: under-redistribution and waste exacerbate inequality; conversely, over-redistribution and stinginess reduce utility; and a balanced moderate moral leads to achieve both reduced inequality and increased utility. These findings provide renewed economic and numerical support for the moral importance known from philosophy, anthropology, and religion. The revival of redistribution and consumption morals should promote the transformation to a human mutual-aid economy, as indicated by philosopher and anthropologist, instead of the capitalist economy that has produced the current inequality. The practical challenge is to implement bottom-up social business, on a foothold of worker coops and platform cooperatives as a community against the state and the market, with moral consensus and its operation.

M. Donahue, P. Benson

Vaibhav Garg, Ganning Xu, Munindar P. Singh

In India, people identify with a particular group based on certain attributes such as religion. The same religious groups are often provoked against each other. Previous studies show the role of provocation in increasing tensions between India's two prominent religious groups: Hindus and Muslims. With the advent of the Internet, such provocation also surfaced on social media platforms such as WhatsApp. By leveraging an existing dataset of Indian WhatsApp posts, we identified three categories of provoking sentences against Indian Muslims. Further, we labeled 7,000 sentences for three provocation categories and called this dataset PACO. We leveraged PACO to train a model that can identify provoking sentences from a WhatsApp post. Our best model is fine-tuned RoBERTa and achieved a 0.851 average AUC score over five-fold cross-validation. Automatically identifying provoking sentences could stop provoking text from reaching out to the masses, and can prevent possible discrimination or violence against the target religious group. Further, we studied the provocative speech through a pragmatic lens, by identifying the dialog acts and impoliteness super-strategies used against the religious group.

Wu Zekun, Sahan Bulathwela, Adriano Soares Koshiyama

Large Language Models (LLM) have made significant advances in the recent past becoming more mainstream in Artificial Intelligence (AI) enabled human-facing applications. However, LLMs often generate stereotypical output inherited from historical data, amplifying societal biases and raising ethical concerns. This work introduces i) the Multi-Grain Stereotype Dataset, which includes 52,751 instances of gender, race, profession and religion stereotypic text and ii) a novel stereotype classifier for English text. We design several experiments to rigorously test the proposed model trained on the novel dataset. Our experiments show that training the model in a multi-class setting can outperform the one-vs-all binary counterpart. Consistent feature importance signals from different eXplainable AI tools demonstrate that the new model exploits relevant text features. We utilise the newly created model to assess the stereotypic behaviour of the popular GPT family of models and observe the reduction of bias over time. In summary, our work establishes a robust and practical framework for auditing and evaluating the stereotypic bias in LLM.

Queenie Luo, Yung-Sung Chuang

Scholars in the humanities rely heavily on ancient manuscripts to study history, religion, and socio-political structures in the past. Many efforts have been devoted to digitizing these precious manuscripts using OCR technology, but most manuscripts were blemished over the centuries so that an Optical Character Recognition (OCR) program cannot be expected to capture faded graphs and stains on pages. This work presents a neural spelling correction model built on Google OCR-ed Tibetan Manuscripts to auto-correct OCR-ed noisy output. This paper is divided into four sections: dataset, model architecture, training and analysis. First, we feature-engineered our raw Tibetan etext corpus into two sets of structured data frames -- a set of paired toy data and a set of paired real data. Then, we implemented a Confidence Score mechanism into the Transformer architecture to perform spelling correction tasks. According to the Loss and Character Error Rate, our Transformer + Confidence score mechanism architecture proves to be superior to Transformer, LSTM-2-LSTM and GRU-2-GRU architectures. Finally, to examine the robustness of our model, we analyzed erroneous tokens, visualized Attention and Self-Attention heatmaps in our model.

D. Wulff

A. Stepan