Value-alignment in normative multi-agent systems is used to promote a certain value and to ensure the consistent behaviour of agents in autonomous intelligent systems with human values. However, the current literature is limited to the incorporation of effective norms for single-value alignment with no consideration of agents' heterogeneity and the requirement of simultaneous promotion and alignment of multiple values. This research proposes a multi-value promotion model that uses multi-objective evolutionary algorithms and decentralised reasoning to produce the optimum parametric set of norms that is aligned with multiple simultaneous values of heterogeneous agents and the system. To understand various aspects of this complex problem, several evolutionary algorithms were used to find a set of optimised norm parameters considering two toy tax scenarios with two and five values are considered. The results are analysed from different perspectives to show the impact of a selected evolutionary algorithm on the solution, and the importance of understanding the relation between values when prioritising them.

AI-generated text has proliferated across various online platforms, offering both transformative prospects and posing significant risks related to misinformation and manipulation. It incorporates real AI-generate text from popular social media platforms like Zhihu and Quora. Unlike existing benchmarks, SAID deals with content that reflects the sophisticated strategies employed by real AI users on the Internet which may evade detection or gain visibility, providing a more realistic and challenging evaluation landscape. A notable finding of our study, based on the Zhihu dataset, reveals that annotators can distinguish between AI-generated and human-generated texts with an average accuracy rate of 96.5%. Furthermore, we present a new user-oriented AI-text detection challenge focusing on the practicality and effectiveness of identifying AI-generated text based on user information and multiple responses. The experimental results demonstrate that conducting detection tasks on actual social media platforms proves to be more challenging compared to traditional simulated AI-text detection, resulting in a decreased accuracy. On the other hand, user-oriented AI-generated text detection significantly improve the accuracy of detection. The advent of AI-generated text has had a profound impact on numerous sectors, including social media platforms. On one side, AI-generated responses enable automation, personalization, and scaling of content creation, thereby revolutionizing how information is disseminated and consumed. Addressing the abuse and malicious use of AI has led to significant research efforts in the field of AI-generated text detection. A range of approaches have been explored, including but not limited to machine learning algorithms Guo et al. (2023); Solaiman et al. (2019), text-based features analysis Mitchell et al. (2023); Tulchinskii et al. (2023); Mitchell et al. (2023), and positive unlabeled techniques Tian et al. (2023).

Clickbait spoiling aims to generate a short text to satisfy the curiosity induced by a clickbait post. As it is a newly introduced task, the dataset is only available in English so far. Our contributions include the construction of manually labeled clickbait spoiling corpus in Indonesian and an evaluation on using cross-lingual zero-shot question answering-based models to tackle clikcbait spoiling for low-resource language like Indonesian. We utilize selection of multilingual language models. The experimental results suggest that XLM-RoBERTa (large) model outperforms other models for phrase and passage spoilers, meanwhile, mDeBERTa (base) model outperforms other models for multipart spoilers.

Graph-structured data is ubiquitous in the world which models complex relationships between objects, enabling various Web applications. Daily influxes of unlabeled graph data on the Web offer immense potential for these applications. Graph self-supervised algorithms have achieved significant success in acquiring generic knowledge from abundant unlabeled graph data. These pre-trained models can be applied to various downstream Web applications, saving training time and improving downstream (target) performance. However, different graphs, even across seemingly similar domains, can differ significantly in terms of attribute semantics, posing difficulties, if not infeasibility, for transferring the pre-trained models to downstream tasks. Concretely speaking, for example, the additional task-specific node information in downstream tasks (specificity) is usually deliberately omitted so that the pre-trained representation (transferability) can be leveraged. The trade-off as such is termed as "transferability-specificity dilemma" in this work. To address this challenge, we introduce an innovative deployment module coined as GraphControl, motivated by ControlNet, to realize better graph domain transfer learning. Specifically, by leveraging universal structural pre-trained models and GraphControl, we align the input space across various graphs and incorporate unique characteristics of target data as conditional inputs. These conditions will be progressively integrated into the model during fine-tuning or prompt tuning through ControlNet, facilitating personalized deployment. Extensive experiments show that our method significantly enhances the adaptability of pre-trained models on target attributed datasets, achieving 1.4-3x performance gain. Furthermore, it outperforms training-from-scratch methods on target data with a comparable margin and exhibits faster convergence.

Large language models (LLMs) have demonstrated remarkable capabilities in natural language understanding across various domains, including healthcare and finance. For some tasks, LLMs achieve similar or better performance than trained human beings, therefore it is reasonable to employ human exams (e.g., certification tests) to assess the performance of LLMs. We present a comprehensive evaluation of popular LLMs, such as Llama 2 and GPT, on their ability to answer agriculture-related questions. In our evaluation, we also employ RAG (Retrieval-Augmented Generation) and ER (Ensemble Refinement) techniques, which combine information retrieval, generation capabilities, and prompting strategies to improve the LLMs' performance. To demonstrate the capabilities of LLMs, we selected agriculture exams and benchmark datasets from three of the largest agriculture producer countries: Brazil, India, and the USA. Our analysis highlights GPT-4's ability to achieve a passing score on exams to earn credits for renewing agronomist certifications, answering 93% of the questions correctly and outperforming earlier general-purpose models, which achieved 88% accuracy. On one of our experiments, GPT-4 obtained the highest performance when compared to human subjects. This performance suggests that GPT-4 could potentially pass on major graduate education admission tests or even earn credits for renewing agronomy certificates. We also explore the models' capacity to address general agriculture-related questions and generate crop management guidelines for Brazilian and Indian farmers, utilizing robust datasets from the Brazilian Agency of Agriculture (Embrapa) and graduate program exams from India. The results suggest that GPT-4, ER, and RAG can contribute meaningfully to agricultural education, assessment, and crop management practice, offering valuable insights to farmers and agricultural professionals.

Generating video stories from text prompts is a complex task. In addition to having high visual quality, videos need to realistically adhere to a sequence of text prompts whilst being consistent throughout the frames. Creating a benchmark for video generation requires data annotated over time, which contrasts with the single caption used often in video datasets. To fill this gap, we collect comprehensive human annotations on three existing datasets, and introduce StoryBench: a new, challenging multi-task benchmark to reliably evaluate forthcoming text-to-video models. Our benchmark includes three video generation tasks of increasing difficulty: action execution, where the next action must be generated starting from a conditioning video; story continuation, where a sequence of actions must be executed starting from a conditioning video; and story generation, where a video must be generated from only text prompts. We evaluate small yet strong text-to-video baselines, and show the benefits of training on story-like data algorithmically generated from existing video captions. Finally, we establish guidelines for human evaluation of video stories, and reaffirm the need of better automatic metrics for video generation. StoryBench aims at encouraging future research efforts in this exciting new area. Work completed during an internship at Google.

In this paper, we propose a fuzzy adaptive loss function for enhancing deep learning performance in classification tasks. Specifically, we redefine the cross-entropy loss to effectively address class-level noise conditions, including the challenging problem of class imbalance. Our approach introduces aggregation operators, leveraging the power of fuzzy logic to improve classification accuracy. The rationale behind our proposed method lies in the iterative up-weighting of class-level components within the loss function, focusing on those with larger errors. To achieve this, we employ the ordered weighted average (OWA) operator and combine it with an adaptive scheme for gradient-based learning. Through extensive experimentation, our method outperforms other commonly used loss functions, such as the standard cross-entropy or focal loss, across various binary and multiclass classification tasks. Furthermore, we explore the influence of hyperparameters associated with the OWA operators and present a default configuration that performs well across different experimental settings.

A primary criticism towards language models (LMs) is their inscrutability. This paper presents evidence that, despite their size and complexity, LMs sometimes exploit a simple computational mechanism to solve one-to-one relational tasks (e.g., capital_of(Poland)=Warsaw). We investigate a range of language model sizes (from 124M parameters to 176B parameters) in an in-context learning setting, and find that for a variety of tasks (involving capital cities, upper-casing, and past-tensing) a key part of the mechanism reduces to a simple linear update typically applied by the feedforward (FFN) networks. These updates also tend to promote the output of the relation in a content-independent way (e.g., encoding Poland:Warsaw::China:Beijing), revealing a predictable pattern that these models take in solving these tasks. We further show that this mechanism is specific to tasks that require retrieval from pretraining memory, rather than retrieval from local context. Our results contribute to a growing body of work on the mechanistic interpretability of LLMs, and offer reason to be optimistic that, despite the massive and non-linear nature of the models, the strategies they ultimately use to solve tasks can sometimes reduce to familiar and even intuitive algorithms.

Fine-tuning pre-trained language models has become the prevalent paradigm for building downstream NLP models. Oftentimes fine-tuned models are readily available but their training data is not, due to data privacy or intellectual property concerns. This creates a barrier to fusing knowledge across individual models to yield a better single model. In this paper, we study the problem of merging individual models built on different training data sets to obtain a single model that performs well both across all data set domains and can generalize on out-ofdomain data. We propose a dataless knowledge fusion method that merges models in their parameter space, guided by weights that minimize prediction differences between the merged model and the individual models. Over a battery of evaluation settings, we show that the proposed method significantly outperforms baselines such as Fisher-weighted averaging or model ensembling. Further, we find that our method is a promising alternative to multi-task learning that can preserve or sometimes improve over the individual models without access to the training data. Finally, model merging is more efficient than training a multi-task model, thus making it applicable to a wider set of scenarios. The dominant paradigm for solving NLP tasks ranging from classification to sequence tagging involves fine-tuning a pretrained language model (PLM) using task-specific labeled data (Devlin et al., 2019; He et al., 2021). This results in specialized models that are explicitly trained to run inference over a single domain and task.

Regression on manifolds, and, more broadly, statistics on manifolds, has garnered significant importance in recent years due to the vast number of applications for this type of data. Circular data is a classic example, but so is data in the space of covariance matrices, data on the Grassmannian manifold obtained as a result of principal component analysis, among many others. In this work we investigate prediction sets for regression scenarios when the response variable, denoted by $Y$, resides in a manifold, and the covariable, denoted by X, lies in Euclidean space. This extends the concepts delineated in [Lei and Wasserman, 2014] to this novel context. Aligning with traditional principles in conformal inference, these prediction sets are distribution-free, indicating that no specific assumptions are imposed on the joint distribution of $(X, Y)$, and they maintain a non-parametric character. We prove the asymptotic almost sure convergence of the empirical version of these regions on the manifold to their population counterparts. The efficiency of this method is shown through a comprehensive simulation study and an analysis involving real-world data.