This study investigates the forecasting accuracy of human experts versus Large Language Models (LLMs) in the retail sector, particularly during standard and promotional sales periods. Utilizing a controlled experimental setup with 123 human forecasters and five LLMs, including ChatGPT4, ChatGPT3.5, Bard, Bing, and Llama2, we evaluated forecasting precision through Mean Absolute Percentage Error. Our analysis centered on the effect of the following factors on forecasters performance: the supporting statistical model (baseline and advanced), whether the product was on promotion, and the nature of external impact. The findings indicate that LLMs do not consistently outperform humans in forecasting accuracy and that advanced statistical forecasting models do not uniformly enhance the performance of either human forecasters or LLMs. Both human and LLM forecasters exhibited increased forecasting errors, particularly during promotional periods and under the influence of positive external impacts. Our findings call for careful consideration when integrating LLMs into practical forecasting processes.
相關內容
ACM/IEEE第23屆模型驅動工程語言和系統國際會議，是模型驅動軟件和系統工程的首要會議系列，由ACM-SIGSOFT和IEEE-TCSE支持組織。自1998年以來，模型涵蓋了建模的各個方面，從語言和方法到工具和應用程序。模特的參加者來自不同的背景，包括研究人員、學者、工程師和工業專業人士。MODELS 2019是一個論壇，參與者可以圍繞建模和模型驅動的軟件和系統交流前沿研究成果和創新實踐經驗。今年的版本將為建模社區提供進一步推進建模基礎的機會，并在網絡物理系統、嵌入式系統、社會技術系統、云計算、大數據、機器學習、安全、開源等新興領域提出建模的創新應用以及可持續性。
官網鏈接： ·
秩
·
MoDELS
·
語言模型化
·
大語言模型
·
The integration of Large Language Models (LLMs) in information retrieval has raised a critical reevaluation of fairness in the text-ranking models. LLMs, such as GPT models and Llama2, have shown effectiveness in natural language understanding tasks, and prior works (e.g., RankGPT) have also demonstrated that the LLMs exhibit better performance than the traditional ranking models in the ranking task. However, their fairness remains largely unexplored. This paper presents an empirical study evaluating these LLMs using the TREC Fair Ranking dataset, focusing on the representation of binary protected attributes such as gender and geographic location, which are historically underrepresented in search outcomes. Our analysis delves into how these LLMs handle queries and documents related to these attributes, aiming to uncover biases in their ranking algorithms. We assess fairness from both user and content perspectives, contributing an empirical benchmark for evaluating LLMs as the fair ranker.
Generative AI technologies promise to transform the product development lifecycle. This study evaluates the efficiency gains, areas for improvement, and emerging challenges of using GitHub Copilot, an AI-powered coding assistant. We identified 15 software development tasks and assessed Copilot's benefits through real-world projects on large proprietary code bases. Our findings indicate significant reductions in developer toil, with up to 50% time saved in code documentation and autocompletion, and 30-40% in repetitive coding tasks, unit test generation, debugging, and pair programming. However, Copilot struggles with complex tasks, large functions, multiple files, and proprietary contexts, particularly with C/C++ code. We project a 33-36% time reduction for coding-related tasks in a cloud-first software development lifecycle. This study aims to quantify productivity improvements, identify underperforming scenarios, examine practical benefits and challenges, investigate performance variations across programming languages, and discuss emerging issues related to code quality, security, and developer experience.
This paper explores the integration of human-like emotions and ethical considerations into Large Language Models (LLMs). We first model eight fundamental human emotions, presented as opposing pairs, and employ collaborative LLMs to reinterpret and express these emotions across a spectrum of intensity. Our focus extends to embedding a latent ethical dimension within LLMs, guided by a novel self-supervised learning algorithm with human feedback (SSHF). This approach enables LLMs to perform self-evaluations and adjustments concerning ethical guidelines, enhancing their capability to generate content that is not only emotionally resonant but also ethically aligned. The methodologies and case studies presented herein illustrate the potential of LLMs to transcend mere text and image generation, venturing into the realms of empathetic interaction and principled decision-making, thereby setting a new precedent in the development of emotionally aware and ethically conscious AI systems.
The study evaluates the efficacy of Conversational Artificial Intelligence (CAI) in rectifying cognitive biases and recognizing affect in human-AI interactions, which is crucial for digital mental health interventions. Cognitive biases (systematic deviations from normative thinking) affect mental health, intensifying conditions like depression and anxiety. Therapeutic chatbots can make cognitive-behavioral therapy (CBT) more accessible and affordable, offering scalable and immediate support. The research employs a structured methodology with clinical-based virtual case scenarios simulating typical user-bot interactions. Performance and affect recognition were assessed across two categories of cognitive biases: theory of mind biases (anthropomorphization of AI, overtrust in AI, attribution to AI) and autonomy biases (illusion of control, fundamental attribution error, just-world hypothesis). A qualitative feedback mechanism was used with an ordinal scale to quantify responses based on accuracy, therapeutic quality, and adherence to CBT principles. Therapeutic bots (Wysa, Youper) and general-use LLMs (GTP 3.5, GTP 4, Gemini Pro) were evaluated through scripted interactions, double-reviewed by cognitive scientists and a clinical psychologist. Statistical analysis showed therapeutic bots were consistently outperformed by non-therapeutic bots in bias rectification and in 4 out of 6 biases in affect recognition. The data suggests that non-therapeutic chatbots are more effective in addressing some cognitive biases.
The proliferation of Artificial Intelligence (AI) in workplaces stands to change the way humans work, with job satisfaction intrinsically linked to work life. Existing research on human-AI collaboration tends to prioritize performance over the experiential aspects of work. In contrast, this paper explores the impact of AI on job decency and meaningfulness in workplaces. Through interviews in the Information Technology (IT) domain, we not only examined the current work environment, but also explored the perceived evolution of the workplace ecosystem with the introduction of an AI. Findings from the preliminary exploratory study reveal that respondents tend to visualize a workplace where humans continue to play a dominant role, even with the introduction of advanced AIs. In this prospective scenario, AI is seen as serving as a complement rather than replacing the human workforce. Furthermore, respondents believe that the introduction of AI will maintain or potentially increase overall job satisfaction.
Histopathological analysis of Whole Slide Images (WSIs) has seen a surge in the utilization of deep learning methods, particularly Convolutional Neural Networks (CNNs). However, CNNs often fall short in capturing the intricate spatial dependencies inherent in WSIs. Graph Neural Networks (GNNs) present a promising alternative, adept at directly modeling pairwise interactions and effectively discerning the topological tissue and cellular structures within WSIs. Recognizing the pressing need for deep learning techniques that harness the topological structure of WSIs, the application of GNNs in histopathology has experienced rapid growth. In this comprehensive review, we survey GNNs in histopathology, discuss their applications, and explore emerging trends that pave the way for future advancements in the field. We begin by elucidating the fundamentals of GNNs and their potential applications in histopathology. Leveraging quantitative literature analysis, we identify four emerging trends: Hierarchical GNNs, Adaptive Graph Structure Learning, Multimodal GNNs, and Higher-order GNNs. Through an in-depth exploration of these trends, we offer insights into the evolving landscape of GNNs in histopathological analysis. Based on our findings, we propose future directions to propel the field forward. Our analysis serves to guide researchers and practitioners towards innovative approaches and methodologies, fostering advancements in histopathological analysis through the lens of graph neural networks.
We study graph clustering in the Stochastic Block Model (SBM) in the presence of both large clusters and small, unrecoverable clusters. Previous convex relaxation approaches achieving exact recovery do not allow any small clusters of size $o(\sqrt{n})$, or require a size gap between the smallest recovered cluster and the largest non-recovered cluster. We provide an algorithm based on semidefinite programming (SDP) which removes these requirements and provably recovers large clusters regardless of the remaining cluster sizes. Mid-sized clusters pose unique challenges to the analysis, since their proximity to the recovery threshold makes them highly sensitive to small noise perturbations and precludes a closed-form candidate solution. We develop novel techniques, including a leave-one-out-style argument which controls the correlation between SDP solutions and noise vectors even when the removal of one row of noise can drastically change the SDP solution. We also develop improved eigenvalue perturbation bounds of potential independent interest. Our results are robust to certain semirandom settings that are challenging for alternative algorithms. Using our gap-free clustering procedure, we obtain efficient algorithms for the problem of clustering with a faulty oracle with superior query complexities, notably achieving $o(n^2)$ sample complexity even in the presence of a large number of small clusters. Our gap-free clustering procedure also leads to improved algorithms for recursive clustering.
This work introduces EUvsDisinfo, a multilingual dataset of trustworthy and disinformation articles related to pro-Kremlin themes. It is sourced directly from the debunk articles written by experts leading the EUvsDisinfo project. Our dataset is the largest to-date resource in terms of the overall number of articles and distinct languages. It also provides the largest topical and temporal coverage. Using this dataset, we investigate the dissemination of pro-Kremlin disinformation across different languages, uncovering language-specific patterns targeting specific disinformation topics. We further analyse the evolution of topic distribution over an eight-year period, noting a significant surge in disinformation content before the full-scale invasion of Ukraine in 2022. Lastly, we demonstrate the dataset's applicability in training models to effectively distinguish between disinformation and trustworthy content in multilingual settings.
Due to the proliferation of Large Language Models research and the use of various Artificial Intelligence (AI) tools, the field of information systems (IS) and computer science (CS) has evolved. The use of tools such as ChatGPT to complete various student programming exercises (e.g., in Python) and assignments has gained prominence amongst various academic institutions. However, recent literature has suggested that the use of ChatGPT in academia is problematic and the impact on teaching and learning should be further scrutinized. More specifically, little is known about how ChatGPT can be practically used with code (programming) writing to complete programming exercises amongst IS and CS undergraduate university students. Furthermore, the paper provides insights for academics who teach programming to create more challenging exercises and how to engage responsibly in the use of ChatGPT to promote classroom integrity. In this paper, we used Complex Adaptive Systems (CAS) theory as a theoretical guide to understand the various dynamics through classroom code demonstrations. Using ChatGPT 3.5, we analyzed the various practical programming examples from past IS exercises and compared those with memos created by tutors and lecturers in a university setting. This paper highlights common ways of assessment, programming errors created by ChatGPT and the potential consideration for IS academics to ensure the development of critical programming skills among students.
The Resource Description Framework (RDF) is a fundamental technology in the Semantic Web, enabling the representation and interchange of structured data. However, RDF lacks the capability to express negated statements in a generic way. As a result, exchanging negative information on a Web scale is thus far restricted to specific cases and predefined statements. The ability to negate (virtually) any RDF statement allows for a comprehensive way to refute, deny or otherwise invalidate claims on a Web scale. Via an intermediate step of a diagrammatic approach to logical expressions called Peirce graphs, we introduce RDF Surfaces, an extension of RDF that incorporates the concept of classic negation, known from first-order logic. Overall, RDF Surfaces provides an abstract, visual approach to negation within the Semantic Web, offering a more general and widely applicable approach than previous attempts at incorporating negation. Aside from a (traditional) programmatic syntax, RDF Surfaces can also be represented visually by means of diagrams inspired by Peirce graphs. We demonstrate negation via RDF Surfaces and how to reason upon it in illustrative use cases drawn from the domains of academic publishing and eHealth. We hope this vision paper attracts new implementers and opens the discussion to its formal specification.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191