-
Belief Change based on Knowledge Measures arXiv.cs.AI Pub Date : 2024-03-15 Umberto Straccia, Giovanni Casini
Knowledge Measures (KMs) aim at quantifying the amount of knowledge/information that a knowledge base carries. On the other hand, Belief Change (BC) is the process of changing beliefs (in our case, in terms of contraction, expansion and revision) taking into account a new piece of knowledge, which possibly may be in contradiction with the current belief. We propose a new quantitative BC framework that
-
Gradient based Feature Attribution in Explainable AI: A Technical Review arXiv.cs.AI Pub Date : 2024-03-15 Yongjie Wang, Tong Zhang, Xu Guo, Zhiqi Shen
The surge in black-box AI models has prompted the need to explain the internal mechanism and justify their reliability, especially in high-stakes applications, such as healthcare and autonomous driving. Due to the lack of a rigorous definition of explainable AI (XAI), a plethora of research related to explainability, interpretability, and transparency has been developed to explain and analyze the model
-
A Multi-constraint and Multi-objective Allocation Model for Emergency Rescue in IoT Environment arXiv.cs.AI Pub Date : 2024-03-15 Xinrun Xu, Zhanbiao Lian, Yurong Wu, Manying Lv, Zhiming Ding, Jian Yan, Shang Jiang
Emergency relief operations are essential in disaster aftermaths, necessitating effective resource allocation to minimize negative impacts and maximize benefits. In prolonged crises or extensive disasters, a systematic, multi-cycle approach is key for timely and informed decision-making. Leveraging advancements in IoT and spatio-temporal data analytics, we've developed the Multi-Objective Shuffled
-
A Survey on Game Playing Agents and Large Models: Methods, Applications, and Challenges arXiv.cs.AI Pub Date : 2024-03-15 Xinrun Xu, Yuxin Wang, Chaoyi Xu, Ziluo Ding, Jiechuan Jiang, Zhiming Ding, Börje F. Karlsson
The swift evolution of Large-scale Models (LMs), either language-focused or multi-modal, has garnered extensive attention in both academy and industry. But despite the surge in interest in this rapidly evolving area, there are scarce systematic reviews on their capabilities and potential in distinct impactful scenarios. This paper endeavours to help bridge this gap, offering a thorough examination
-
Surrogate Assisted Monte Carlo Tree Search in Combinatorial Optimization arXiv.cs.AI Pub Date : 2024-03-14 Saeid Amiri, Parisa Zehtabi, Danial Dervovic, Michael Cashmore
Industries frequently adjust their facilities network by opening new branches in promising areas and closing branches in areas where they expect low profits. In this paper, we examine a particular class of facility location problems. Our objective is to minimize the loss of sales resulting from the removal of several retail stores. However, estimating sales accurately is expensive and time-consuming
-
xLP: Explainable Link Prediction for Master Data Management arXiv.cs.AI Pub Date : 2024-03-14 Balaji Ganesan, Matheen Ahmed Pasha, Srinivasa Parkala, Neeraj R Singh, Gayatri Mishra, Sumit Bhatia, Hima Patel, Somashekar Naganna, Sameep Mehta
Explaining neural model predictions to users requires creativity. Especially in enterprise applications, where there are costs associated with users' time, and their trust in the model predictions is critical for adoption. For link prediction in master data management, we have built a number of explainability solutions drawing from research in interpretability, fact verification, path ranking, neuro-symbolic
-
GPT, Ontology, and CAABAC: A Tripartite Personalized Access Control Model Anchored by Compliance, Context and Attribute arXiv.cs.AI Pub Date : 2024-03-13 Raza Nowrozy, Khandakar Ahmed, Hua Wang
As digital healthcare evolves, the security of electronic health records (EHR) becomes increasingly crucial. This study presents the GPT-Onto-CAABAC framework, integrating Generative Pretrained Transformer (GPT), medical-legal ontologies and Context-Aware Attribute-Based Access Control (CAABAC) to enhance EHR access security. Unlike traditional models, GPT-Onto-CAABAC dynamically interprets policies
-
Clinical Reasoning over Tabular Data and Text with Bayesian Networks arXiv.cs.AI Pub Date : 2024-03-14 Paloma Rabaey, Johannes Deleu, Stefan Heytens, Thomas Demeester
Bayesian networks are well-suited for clinical reasoning on tabular data, but are less compatible with natural language data, for which neural networks provide a successful framework. This paper compares and discusses strategies to augment Bayesian networks with neural text representations, both in a generative and discriminative manner. This is illustrated with simulation results for a primary care
-
Heuristic Reasoning in AI: Instrumental Use and Mimetic Absorption arXiv.cs.AI Pub Date : 2024-03-14 Anirban Mukherjee, Hannah Hanwen Chang
We propose a novel program of heuristic reasoning within artificial intelligence (AI) systems. Through a series of innovative experiments, including variations of the classic Linda problem and a novel application of the Beauty Contest game, we uncover trade-offs between accuracy maximization and effort reduction that shape the conditions under which AIs transition between exhaustive logical processing
-
A Multi-population Integrated Approach for Capacitated Location Routing arXiv.cs.AI Pub Date : 2024-03-14 Pengfei He, Jin-Kao Hao, Qinghua Wu
The capacitated location-routing problem involves determining the depots from a set of candidate capacitated depot locations and finding the required routes from the selected depots to serve a set of customers whereas minimizing a cost function that includes the cost of opening the chosen depots, the fixed utilization cost per vehicle used, and the total cost (distance) of the routes. This paper presents
-
Silico-centric Theory of Mind arXiv.cs.AI Pub Date : 2024-03-14 Anirban Mukherjee, Hannah Hanwen Chang
Theory of Mind (ToM) refers to the ability to attribute mental states, such as beliefs, desires, intentions, and knowledge, to oneself and others, and to understand that these mental states can differ from one's own and from reality. We investigate ToM in environments with multiple, distinct, independent AI agents, each possessing unique internal states, information, and objectives. Inspired by human
-
Leveraging Constraint Programming in a Deep Learning Approach for Dynamically Solving the Flexible Job-Shop Scheduling Problem arXiv.cs.AI Pub Date : 2024-03-14 Imanol Echeverria, Maialen Murua, Roberto Santana
Recent advancements in the flexible job-shop scheduling problem (FJSSP) are primarily based on deep reinforcement learning (DRL) due to its ability to generate high-quality, real-time solutions. However, DRL approaches often fail to fully harness the strengths of existing techniques such as exact methods or constraint programming (CP), which can excel at finding optimal or near-optimal solutions for
-
Generating Feasible and Plausible Counterfactual Explanations for Outcome Prediction of Business Processes arXiv.cs.AI Pub Date : 2024-03-14 Alexander Stevens, Chun Ouyang, Johannes De Smedt, Catarina Moreira
In recent years, various machine and deep learning architectures have been successfully introduced to the field of predictive process analytics. Nevertheless, the inherent opacity of these algorithms poses a significant challenge for human decision-makers, hindering their ability to understand the reasoning behind the predictions. This growing concern has sparked the introduction of counterfactual
-
Meta-operators for Enabling Parallel Planning Using Deep Reinforcement Learning arXiv.cs.AI Pub Date : 2024-03-13 Ángel Aso-Mollar, Eva Onaindia
There is a growing interest in the application of Reinforcement Learning (RL) techniques to AI planning with the aim to come up with general policies. Typically, the mapping of the transition model of AI planning to the state transition system of a Markov Decision Process is established by assuming a one-to-one correspondence of the respective action spaces. In this paper, we introduce the concept
-
Fuzzy Fault Trees Formalized arXiv.cs.AI Pub Date : 2024-03-13 Thi Kim Nhung Dang, Milan Lopuhaä-Zwakenberg, Mariëlle Stoelinga
Fault tree analysis is a vital method of assessing safety risks. It helps to identify potential causes of accidents, assess their likelihood and severity, and suggest preventive measures. Quantitative analysis of fault trees is often done via the dependability metrics that compute the system's failure behaviour over time. However, the lack of precise data is a major obstacle to quantitative analysis
-
Random Search as a Baseline for Sparse Neural Network Architecture Search arXiv.cs.AI Pub Date : 2024-03-13 Rezsa Farahani
Sparse neural networks have shown similar or better generalization performance than their dense counterparts while having higher parameter efficiency. This has motivated a number of works to learn or search for high performing sparse networks. While reports of task performance or efficiency gains are impressive, standard baselines are lacking leading to poor comparability and unreliable reproducibility
-
Emergence of Social Norms in Large Language Model-based Agent Societies arXiv.cs.AI Pub Date : 2024-03-13 Siyue Ren, Zhiyao Cui, Ruiqi Song, Zhen Wang, Shuyue Hu
The emergence of social norms has attracted much interest in a wide array of disciplines, ranging from social science and cognitive science to artificial intelligence. In this paper, we propose the first generative agent architecture that empowers the emergence of social norms within a population of large language model-based agents. Our architecture, named CRSEC, consists of four modules: Creation
-
A Novel Feature Learning-based Bio-inspired Neural Network for Real-time Collision-free Rescue of Multi-Robot Systems arXiv.cs.AI Pub Date : 2024-03-13 Junfei Li, Simon X. Yang
Natural disasters and urban accidents drive the demand for rescue robots to provide safer, faster, and more efficient rescue trajectories. In this paper, a feature learning-based bio-inspired neural network (FLBBINN) is proposed to quickly generate a heuristic rescue path in complex and dynamic environments, as traditional approaches usually cannot provide a satisfactory solution to real-time responses
-
Robust Decision Aggregation with Adversarial Experts arXiv.cs.AI Pub Date : 2024-03-13 Yongkang Guo, Yuqing Kong
We consider a binary decision aggregation problem in the presence of both truthful and adversarial experts. The truthful experts will report their private signals truthfully with proper incentive, while the adversarial experts can report arbitrarily. The decision maker needs to design a robust aggregator to forecast the true state of the world based on the reports of experts. The decision maker does
-
Large Language Models are Contrastive Reasoners arXiv.cs.AI Pub Date : 2024-03-13 Liang Yao
Prompting methods play a crucial role in enhancing the capabilities of pre-trained large language models (LLMs). We explore how contrastive prompting (CP) significantly improves the ability of large language models to perform complex reasoning. We demonstrate that LLMs are decent contrastive reasoners by simply adding "Let's give a correct and a wrong answer." before LLMs provide answers. Experiments
-
Deep Submodular Peripteral Network arXiv.cs.AI Pub Date : 2024-03-13 Gantavya Bhatt, Arnav Das, Jeff Bilmes
Submodular functions, crucial for various applications, often lack practical learning methods for their acquisition. Seemingly unrelated, learning a scaling from oracles offering graded pairwise preferences (GPC) is underexplored, despite a rich history in psychometrics. In this paper, we introduce deep submodular peripteral networks (DSPNs), a novel parametric family of submodular functions, and methods
-
PAGE: Domain-Incremental Adaptation with Past-Agnostic Generative Replay for Smart Healthcare arXiv.cs.AI Pub Date : 2024-03-13 Chia-Hao Li, Niraj K. Jha
We propose PAGE, a domain-incremental adaptation strategy with past-agnostic generative replay for smart healthcare. PAGE enables generative replay without the aid of any preserved data or information from prior domains. When adapting to a new domain, it exploits real data from the new distribution and the current model to generate synthetic data that retain the learned knowledge of previous domains
-
Rethinking Loss Functions for Fact Verification arXiv.cs.AI Pub Date : 2024-03-13 Yuta Mukobara, Yutaro Shigeto, Masashi Shimbo
We explore loss functions for fact verification in the FEVER shared task. While the cross-entropy loss is a standard objective for training verdict predictors, it fails to capture the heterogeneity among the FEVER verdict classes. In this paper, we develop two task-specific objectives tailored to FEVER. Experimental results confirm that the proposed objective functions outperform the standard cross-entropy
-
Measuring the Energy Consumption and Efficiency of Deep Neural Networks: An Empirical Analysis and Design Recommendations arXiv.cs.AI Pub Date : 2024-03-13 Charles Edison Tripp, Jordan Perr-Sauer, Jamil Gafur, Amabarish Nag, Avi Purkayastha, Sagi Zisman, Erik A. Bensen
Addressing the so-called ``Red-AI'' trend of rising energy consumption by large-scale neural networks, this study investigates the actual energy consumption, as measured by node-level watt-meters, of training various fully connected neural network architectures. We introduce the BUTTER-E dataset, an augmentation to the BUTTER Empirical Deep Learning dataset, containing energy consumption and performance
-
From Paper to Card: Transforming Design Implications with Generative AI arXiv.cs.AI Pub Date : 2024-03-12 Donghoon Shin, Lucy Lu Wang, Gary Hsieh
Communicating design implications is common within the HCI community when publishing academic papers, yet these papers are rarely read and used by designers. One solution is to use design cards as a form of translational resource that communicates valuable insights from papers in a more digestible and accessible format to assist in design processes. However, creating design cards can be time-consuming
-
RoboCertProb: Property Specification for Probabilistic RoboChart Models arXiv.cs.AI Pub Date : 2024-03-12 Kangfeng Ye, Jim Woodcock
RoboChart is a core notation in the RoboStar framework which brings modern modelling and formal verification technologies into software engineering for robotics. It is a timed and probabilistic domain-specific language for robotics and provides a UML-like architectural and state machine modelling. This work presents RoboCertProb for specifying quantitative properties of probabilistic robotic systems
-
Physics-Inspired Deep Learning Anti-Aliasing Framework in Efficient Channel State Feedback arXiv.cs.AI Pub Date : 2024-03-12 Yu-Chien LinJianzhong, Yan XinJianzhong, Ta-Sung LeeJianzhong, CharlieJianzhong, Zhang, Zhi Ding
Acquiring downlink channel state information (CSI) at the base station is vital for optimizing performance in massive Multiple input multiple output (MIMO) Frequency-Division Duplexing (FDD) systems. While deep learning architectures have been successful in facilitating UE-side CSI feedback and gNB-side recovery, the undersampling issue prior to CSI feedback is often overlooked. This issue, which arises
-
Towards Independence Criterion in Machine Unlearning of Features and Labels arXiv.cs.AI Pub Date : 2024-03-12 Ling Han, Nanqing Luo, Hao Huang, Jing Chen, Mary-Anne Hartley
This work delves into the complexities of machine unlearning in the face of distributional shifts, particularly focusing on the challenges posed by non-uniform feature and label removal. With the advent of regulations like the GDPR emphasizing data privacy and the right to be forgotten, machine learning models face the daunting task of unlearning sensitive information without compromising their integrity
-
Legally Binding but Unfair? Towards Assessing Fairness of Privacy Policies arXiv.cs.AI Pub Date : 2024-03-12 Vincent Freiberger, Erik Buchmann
Privacy policies are expected to inform data subjects about their data protection rights. They should explain the data controller's data management practices, and make facts such as retention periods or data transfers to third parties transparent. Privacy policies only fulfill their purpose, if they are correctly perceived, interpreted, understood, and trusted by the data subject. Amongst others, this
-
AI-Assisted Causal Pathway Diagram for Human-Centered Design arXiv.cs.AI Pub Date : 2024-03-12 Ruican Zhong, Donghoon Shin, Rosemary Meza, Predrag Klasnja, Lucas Colusso, Gary Hsieh
This paper explores the integration of causal pathway diagrams (CPD) into human-centered design (HCD), investigating how these diagrams can enhance the early stages of the design process. A dedicated CPD plugin for the online collaborative whiteboard platform Miro was developed to streamline diagram creation and offer real-time AI-driven guidance. Through a user study with designers (N=20), we found
-
Contextual Clarity: Generating Sentences with Transformer Models using Context-Reverso Data arXiv.cs.AI Pub Date : 2024-03-12 Ruslan Musaev
In the age of information abundance, the ability to provide users with contextually relevant and concise information is crucial. Keyword in Context (KIC) generation is a task that plays a vital role in and generation applications, such as search engines, personal assistants, and content summarization. In this paper, we present a novel approach to generating unambiguous and brief sentence-contexts for
-
A Review of Cybersecurity Incidents in the Food and Agriculture Sector arXiv.cs.AI Pub Date : 2024-03-12 Ajay Kulkarni, Yingjie Wang, Munisamy Gopinath, Dan Sobien, Abdul Rahman, Feras A. Batarseh
The increasing utilization of emerging technologies in the Food & Agriculture (FA) sector has heightened the need for security to minimize cyber risks. Considering this aspect, this manuscript reviews disclosed and documented cybersecurity incidents in the FA sector. For this purpose, thirty cybersecurity incidents were identified, which took place between July 2011 and April 2023. The details of these
-
Harnessing Artificial Intelligence to Combat Online Hate: Exploring the Challenges and Opportunities of Large Language Models in Hate Speech Detection arXiv.cs.AI Pub Date : 2024-03-12 Tharindu Kumarage, Amrita Bhattacharjee, Joshua Garland
Large language models (LLMs) excel in many diverse applications beyond language generation, e.g., translation, summarization, and sentiment analysis. One intriguing application is in text classification. This becomes pertinent in the realm of identifying hateful or toxic speech -- a domain fraught with challenges and ethical dilemmas. In our study, we have two objectives: firstly, to offer a literature
-
An Interpretable Generalization Mechanism for Accurately Detecting Anomaly and Identifying Networking Intrusion Techniques arXiv.cs.AI Pub Date : 2024-03-12 Hao-Ting Pai, Yu-Hsuan Kang, Wen-Cheng Chung
Recent advancements in Intrusion Detection Systems (IDS), integrating Explainable AI (XAI) methodologies, have led to notable improvements in system performance via precise feature selection. However, a thorough understanding of cyber-attacks requires inherently explainable decision-making processes within IDS. In this paper, we present the Interpretable Generalization Mechanism (IG), poised to revolutionize
-
Algorithmic Bayesian Epistemology arXiv.cs.AI Pub Date : 2024-03-11 Eric Neyman
One aspect of the algorithmic lens in theoretical computer science is a view on other scientific disciplines that focuses on satisfactory solutions that adhere to real-world constraints, as opposed to solutions that would be optimal ignoring such constraints. The algorithmic lens has provided a unique and important perspective on many academic fields, including molecular biology, ecology, neuroscience
-
Improving Reinforcement Learning from Human Feedback Using Contrastive Rewards arXiv.cs.AI Pub Date : 2024-03-12 Wei Shen, Xiaoying Zhang, Yuanshun Yao, Rui Zheng, Hongyi Guo, Yang Liu
Reinforcement learning from human feedback (RLHF) is the mainstream paradigm used to align large language models (LLMs) with human preferences. Yet existing RLHF heavily relies on accurate and informative reward models, which are vulnerable and sensitive to noise from various sources, e.g. human labeling errors, making the pipeline fragile. In this work, we improve the effectiveness of the reward model
-
Verification-Aided Learning of Neural Network Barrier Functions with Termination Guarantees arXiv.cs.AI Pub Date : 2024-03-12 Shaoru Chen, Lekan Molu, Mahyar Fazlyab
Barrier functions are a general framework for establishing a safety guarantee for a system. However, there is no general method for finding these functions. To address this shortcoming, recent approaches use self-supervised learning techniques to learn these functions using training data that are periodically generated by a verification procedure, leading to a verification-aided learning framework
-
Specification Overfitting in Artificial Intelligence arXiv.cs.AI Pub Date : 2024-03-13 Benjamin Roth, Pedro Henrique Luz de Araujo, Yuxi Xia, Saskia Kaltenbrunner, Christoph Korab
Machine learning (ML) and artificial intelligence (AI) approaches are often criticized for their inherent bias and for their lack of control, accountability, and transparency. Consequently, regulatory bodies struggle with containing this technology's potential negative side effects. High-level requirements such as fairness and robustness need to be formalized into concrete specification metrics, imperfect
-
Optimal Design and Implementation of an Open-source Emulation Platform for User-Centric Shared E-mobility Services arXiv.cs.AI Pub Date : 2024-03-12 Maqsood Hussain Shah, Yue Ding, Shaoshu Zhu, Yingqi Gu, Mingming Liu
In response to the escalating global challenge of increasing emissions and pollution in transportation, shared electric mobility services, encompassing e-cars, e-bikes, and e-scooters, have emerged as a popular strategy. However, existingshared electric mobility services exhibit critical design deficiencies, including insufficient service integration, imprecise energy consumption forecasting, limited
-
An Improved Strategy for Blood Glucose Control Using Multi-Step Deep Reinforcement Learning arXiv.cs.AI Pub Date : 2024-03-12 Weiwei Gu, Senquan Wang
Blood Glucose (BG) control involves keeping an individual's BG within a healthy range through extracorporeal insulin injections is an important task for people with type 1 diabetes. However,traditional patient self-management is cumbersome and risky. Recent research has been devoted to exploring individualized and automated BG control approaches, among which Deep Reinforcement Learning (DRL) shows
-
Relevance Score: A Landmark-Like Heuristic for Planning arXiv.cs.AI Pub Date : 2024-03-12 Oliver Kim, Mohan Sridharan
Landmarks are facts or actions that appear in all valid solutions of a planning problem. They have been used successfully to calculate heuristics that guide the search for a plan. We investigate an extension to this concept by defining a novel "relevance score" that helps identify facts or actions that appear in most but not all plans to achieve any given goal. We describe an approach to compute this
-
A New Random Forest Ensemble of Intuitionistic Fuzzy Decision Trees arXiv.cs.AI Pub Date : 2024-03-12 Yingtao Ren, Xiaomin Zhu, Kaiyuan Bai, Runtong Zhang
Classification is essential to the applications in the field of data mining, artificial intelligence, and fault detection. There exists a strong need in developing accurate, suitable, and efficient classification methods and algorithms with broad applicability. Random forest is a general algorithm that is often used for classification under complex conditions. Although it has been widely adopted, its
-
On Globular T-Spherical Fuzzy (G-TSF) Sets with Application to G-TSF Multi-Criteria Group Decision-Making arXiv.cs.AI Pub Date : 2024-03-09 Miin-Shen Yang, Yasir Akhtar, Mehboob Ali
In this paper, we give the concept of Globular T-Spherical Fuzzy (G-TSF) Sets (G-TSFSs) as an innovative extension of T-Spherical Fuzzy Sets (TSFSs) and Circular Spherical Fuzzy Sets (C-SFSs). G-TSFSs represent membership, indeterminacy, and non-membership degrees using a globular/sphere bound that can offer a more accurate portrayal of vague, ambiguous, and imprecise information. By employing a structured
-
Better Understandings and Configurations in MaxSAT Local Search Solvers via Anytime Performance Analysis arXiv.cs.AI Pub Date : 2024-03-11 Furong Ye, Chuan Luo, Shaowei Cai
Though numerous solvers have been proposed for the MaxSAT problem, and the benchmark environment such as MaxSAT Evaluations provides a platform for the comparison of the state-of-the-art solvers, existing assessments were usually evaluated based on the quality, e.g., fitness, of the best-found solutions obtained within a given running time budget. However, concerning solely the final obtained solutions
-
OntoChat: a Framework for Conversational Ontology Engineering using Language Models arXiv.cs.AI Pub Date : 2024-03-09 Bohui Zhang, Valentina Anita Carriero, Katrin Schreiberhuber, Stefani Tsaneva, Lucía Sánchez González, Jongmo Kim, Jacopo de Berardinis
Ontology engineering (OE) in large projects poses a number of challenges arising from the heterogeneous backgrounds of the various stakeholders, domain experts, and their complex interactions with ontology designers. This multi-party interaction often creates systematic ambiguities and biases from the elicitation of ontology requirements, which directly affect the design, evaluation and may jeopardise
-
Enhancing Multi-Hop Knowledge Graph Reasoning through Reward Shaping Techniques arXiv.cs.AI Pub Date : 2024-03-09 Chen Li, Haotian Zheng, Yiping Sun, Cangqing Wang, Liqiang Yu, Che Chang, Xinyu Tian, Bo Liu
In the realm of computational knowledge representation, Knowledge Graph Reasoning (KG-R) stands at the forefront of facilitating sophisticated inferential capabilities across multifarious domains. The quintessence of this research elucidates the employment of reinforcement learning (RL) strategies, notably the REINFORCE algorithm, to navigate the intricacies inherent in multi-hop KG-R. This investigation
-
Can Large Language Models Play Games? A Case Study of A Self-Play Approach arXiv.cs.AI Pub Date : 2024-03-08 Hongyi Guo, Zhihan Liu, Yufeng Zhang, Zhaoran Wang
Large Language Models (LLMs) harness extensive data from the Internet, storing a broad spectrum of prior knowledge. While LLMs have proven beneficial as decision-making aids, their reliability is hampered by limitations in reasoning, hallucination phenomenon, and so on. On the other hand, Monte-Carlo Tree Search (MCTS) is a heuristic search algorithm that provides reliable decision-making solutions
-
DeepSeek-VL: Towards Real-World Vision-Language Understanding arXiv.cs.AI Pub Date : 2024-03-08 Haoyu Lu, Wen Liu, Bo Zhang, Bingxuan Wang, Kai Dong, Bo Liu, Jingxiang Sun, Tongzheng Ren, Zhuoshu Li, Yaofeng Sun, Chengqi Deng, Hanwei Xu, Zhenda Xie, Chong Ruan
We present DeepSeek-VL, an open-source Vision-Language (VL) Model designed for real-world vision and language understanding applications. Our approach is structured around three key dimensions: We strive to ensure our data is diverse, scalable, and extensively covers real-world scenarios including web screenshots, PDFs, OCR, charts, and knowledge-based content, aiming for a comprehensive representation
-
Algorithmic Identification of Essential Exogenous Nodes for Causal Sufficiency in Brain Networks arXiv.cs.AI Pub Date : 2024-03-08 Abdolmahdi Bagheri, Mahdi Dehshiri, Babak Nadjar Araabi, Alireza Akhondi Asl
In the investigation of any causal mechanisms, such as the brain's causal networks, the assumption of causal sufficiency plays a critical role. Notably, neglecting this assumption can result in significant errors, a fact that is often disregarded in the causal analysis of brain networks. In this study, we propose an algorithmic identification approach for determining essential exogenous nodes that
-
Tapilot-Crossing: Benchmarking and Evolving LLMs Towards Interactive Data Analysis Agents arXiv.cs.AI Pub Date : 2024-03-08 Jinyang Li, Nan Huo, Yan Gao, Jiayi Shi, Yingxiu Zhao, Ge Qu, Yurong Wu, Chenhao Ma, Jian-Guang Lou, Reynold Cheng
Interactive Data Analysis, the collaboration between humans and LLM agents, enables real-time data exploration for informed decision-making. The challenges and costs of collecting realistic interactive logs for data analysis hinder the quantitative evaluation of Large Language Model (LLM) agents in this task. To mitigate this issue, we introduce Tapilot-Crossing, a new benchmark to evaluate LLM agents
-
MMoE: Robust Spoiler Detection with Multi-modal Information and Domain-aware Mixture-of-Experts arXiv.cs.AI Pub Date : 2024-03-08 Zinan Zeng, Sen Ye, Zijian Cai, Heng Wang, Yuhan Liu, Qinghua Zheng, Minnan Luo
Online movie review websites are valuable for information and discussion about movies. However, the massive spoiler reviews detract from the movie-watching experience, making spoiler detection an important task. Previous methods simply focus on reviews' text content, ignoring the heterogeneity of information in the platform. For instance, the metadata and the corresponding user's information of a review
-
Predicting Single-cell Drug Sensitivity by Adaptive Weighted Feature for Adversarial Multi-source Domain Adaptation arXiv.cs.AI Pub Date : 2024-03-08 Wei Duan, Hui Liu
The development of single-cell sequencing technology had promoted the generation of a large amount of single-cell transcriptional profiles, providing valuable opportunities to explore drug-resistant cell subpopulations in a tumor. However, the drug sensitivity data in single-cell level is still scarce to date, pressing an urgent and highly challenging task for computational prediction of the drug sensitivity
-
Developing Federated Time-to-Event Scores Using Heterogeneous Real-World Survival Data arXiv.cs.AI Pub Date : 2024-03-08 Siqi Li, Yuqing Shang, Ziwen Wang, Qiming Wu, Chuan Hong, Yilin Ning, Di Miao, Marcus Eng Hock Ong, Bibhas Chakraborty, Nan Liu
Survival analysis serves as a fundamental component in numerous healthcare applications, where the determination of the time to specific events (such as the onset of a certain disease or death) for patients is crucial for clinical decision-making. Scoring systems are widely used for swift and efficient risk prediction. However, existing methods for constructing survival scores presume that data originates
-
From Chain to Tree: Refining Chain-like Rules into Tree-like Rules on Knowledge Graphs arXiv.cs.AI Pub Date : 2024-03-08 Wangtao Sun, Shizhu He, Jun Zhao, Kang Liu
With good explanatory power and controllability, rule-based methods play an important role in many tasks such as knowledge reasoning and decision support. However, existing studies primarily focused on learning chain-like rules, which limit their semantic expressions and accurate prediction abilities. As a result, chain-like rules usually fire on the incorrect grounding values, producing inaccurate
-
RLPeri: Accelerating Visual Perimetry Test with Reinforcement Learning and Convolutional Feature Extraction arXiv.cs.AI Pub Date : 2024-03-08 Tanvi Verma, Linh Le Dinh, Nicholas Tan, Xinxing Xu, Chingyu Cheng, Yong Liu
Visual perimetry is an important eye examination that helps detect vision problems caused by ocular or neurological conditions. During the test, a patient's gaze is fixed at a specific location while light stimuli of varying intensities are presented in central and peripheral vision. Based on the patient's responses to the stimuli, the visual field mapping and sensitivity are determined. However, maintaining
-
BjTT: A Large-scale Multimodal Dataset for Traffic Prediction arXiv.cs.AI Pub Date : 2024-03-08 Chengyang Zhang, Yong Zhang, Qitan Shao, Bo Li, Yisheng Lv, Xinglin Piao, Baocai Yin
Traffic prediction is one of the most significant foundations in Intelligent Transportation Systems (ITS). Traditional traffic prediction methods rely only on historical traffic data to predict traffic trends and face two main challenges. 1) insensitivity to unusual events. 2) limited performance in long-term prediction. In this work, we explore how generative models combined with text describing the
-
Towards Multimodal Human Intention Understanding Debiasing via Subject-Deconfounding arXiv.cs.AI Pub Date : 2024-03-08 Dingkang Yang, Dongling Xiao, Ke Li, Yuzheng Wang, Zhaoyu Chen, Jinjie Wei, Lihua Zhang
Multimodal intention understanding (MIU) is an indispensable component of human expression analysis (e.g., sentiment or humor) from heterogeneous modalities, including visual postures, linguistic contents, and acoustic behaviors. Existing works invariably focus on designing sophisticated structures or fusion strategies to achieve impressive improvements. Unfortunately, they all suffer from the subject
-
Medical Speech Symptoms Classification via Disentangled Representation arXiv.cs.AI Pub Date : 2024-03-08 Jianzong Wang, Pengcheng Li, Xulong Zhang, Ning Cheng, Jing Xiao
Intent is defined for understanding spoken language in existing works. Both textual features and acoustic features involved in medical speech contain intent, which is important for symptomatic diagnosis. In this paper, we propose a medical speech classification model named DRSC that automatically learns to disentangle intent and content representations from textual-acoustic data for classification
-
Automatic and Universal Prompt Injection Attacks against Large Language Models arXiv.cs.AI Pub Date : 2024-03-07 Xiaogeng Liu, Zhiyuan Yu, Yizhe Zhang, Ning Zhang, Chaowei Xiao
Large Language Models (LLMs) excel in processing and generating human language, powered by their ability to interpret and follow instructions. However, their capabilities can be exploited through prompt injection attacks. These attacks manipulate LLM-integrated applications into producing responses aligned with the attacker's injected content, deviating from the user's actual requests. The substantial
-
A Safe Harbor for AI Evaluation and Red Teaming arXiv.cs.AI Pub Date : 2024-03-07 Shayne Longpre, Sayash Kapoor, Kevin Klyman, Ashwin Ramaswami, Rishi Bommasani, Borhane Blili-Hamelin, Yangsibo Huang, Aviya Skowron, Zheng-Xin Yong, Suhas Kotha, Yi Zeng, Weiyan Shi, Xianjun Yang, Reid Southen, Alexander Robey, Patrick Chao, Diyi Yang, Ruoxi Jia, Daniel Kang, Sandy Pentland, Arvind Narayanan, Percy Liang, Peter Henderson
Independent evaluation and red teaming are critical for identifying the risks posed by generative AI systems. However, the terms of service and enforcement strategies used by prominent AI companies to deter model misuse have disincentives on good faith safety evaluations. This causes some researchers to fear that conducting such research or releasing their findings will result in account suspensions