The global economy relies on the flow of goods over supply chain networks, with nodes as firms and edges as transactions between firms. While we may observe these external transactions, they are governed by unseen production functions, which determine how firms internally transform the input products they receive into output products that they sell. In this setting, it can be extremely valuable to infer these production functions, to better understand and improve supply chains, and to forecast future transactions more accurately. However, existing graph neural networks (GNNs) cannot capture these hidden relationships between nodes’ inputs and outputs. Here, we introduce a new class of models for this setting, by combining temporal GNNs with a novel inventory module, which learns production functions via attention weights and a special loss function. We evaluate our models extensively on real supply chains data, along with data generated from our new open-source simulator, SupplySim. Our models successfully infer production functions, outperforming the strongest baseline by 6-50% (across datasets), and forecast future transactions, outperforming the strongest baseline by 11-62%.
论文检索
输入标题、作者或关键词，从 11,272 篇学术成果中精准定位
Phishing attacks are a major threat to online security, exploiting user vulnerabilities to steal sensitive information. Various methods have been developed to counteract phishing, each with varying levels of accuracy, but they also face notable limitations. In this study, we introduce PhishAgent, a multimodal agent that combines a wide range of tools, integrating both online and offline knowledge bases with Multimodal Large Language Models (MLLMs). This combination leads to broader brand coverage, which enhances brand recognition and recall. Furthermore, we propose a multimodal information retrieval framework designed to extract the relevant top k items from offline knowledge bases, using available information from a webpage, including logos and HTML. Our empirical results, based on three real-world datasets, demonstrate that the proposed framework significantly enhances detection accuracy and reduces both false positives and false negatives, while maintaining model efficiency. Additionally, PhishAgent shows strong resilience against various types of adversarial attacks.
FoMo: Multi-Modal, Multi-Scale and Multi-Task Remote Sensing Foundation Models for Forest Monitoring
PDF ↗Forests are vital to ecosystems, supporting biodiversity and essential services, but are rapidly changing due to land use and climate change. Understanding and mitigating negative effects requires parsing data on forests at global scale from a broad array of sensory modalities, and using them in diverse forest monitoring applications. Such diversity in data and applications can be effectively addressed through the development of a large, pre-trained foundation model that serves as a versatile base for various downstream tasks. However, remote sensing modalities, which are an excellent fit for several forest management tasks, are particularly challenging considering the variation in environmental conditions, object scales, image acquisition modes and spatio-temporal resolutions, etc. With that in mind, we present the first unified Forest Monitoring Benchmark (FoMo-Bench), carefully constructed to evaluate foundation models with such flexibility. FoMo-Bench consists of 15 diverse datasets encompassing satellite, aerial, and inventory data, covering a variety of geographical regions, and including multispectral, red-green-blue, synthetic aperture radar and LiDAR data with various temporal, spatial and spectral resolutions. FoMo-Bench includes multiple types of forest-monitoring tasks, spanning classification, segmentation, and object detection. To enhance task and geographic diversity in FoMo-Bench, we introduce TalloS, a global dataset combining satellite imagery with ground-based annotations for tree species classification across 1,000+ categories and hierarchical taxonomic levels. Finally, we propose FoMo-Net, a pre-training framework to develop foundation models with the capacity to process any combination of commonly used modalities and spectral bands in remote sensing. This work aims to inspire research collaborations between machine learning and forest biology researchers in exploring scalable multi-modal and multi-task models for forest monitoring and beyond. All code, data and appendices are published in the repository and on ArXiv.
In many applications of AI for Social Impact (e.g., when allocating spots in support programs for underserved communities), resources are scarce and an allocation policy is needed to decide who receives a resource. Before being deployed at scale, a rigorous evaluation of an AI-powered allocation policy is vital. In this paper, we introduce the methods necessary to evaluate index-based allocation policies, which allocate a limited number of resources to those who need them the most. Such policies create dependencies between agents, rendering standard statistical tests invalid and ineffective. Addressing the arising practical and technical challenges, we describe an efficient estimator and methods for drawing valid statistical conclusions. Our extensive experiments validate our methodology in practical settings while also showcasing its statistical power. We conclude by proposing and empirically verifying extensions of our methodology that enable us to reevaluate a past randomized control trial conducted with 10000 beneficiaries for a mHealth program for pregnant women. Our new methodology allows us to draw previously invisible conclusions when comparing two different ML allocation policies.
Fraudulent shopping websites pose a significant threat to online consumers and legitimate businesses: in 2023, victims of such scams reported $392 million in losses to the Federal Trade Commission. This alarming trend not only impacts individuals but also erodes societal trust in e-commerce, necessitating urgent countermeasures. While previous studies have attempted to identify these fraudulent websites at scale, they face limitations such as potential bias in data collection, overreliance on easily manipulated features, and the lack of explainable results. This study explores the potential of Large Language Models (LLMs) in identifying fraudulent shopping websites, revealing that current LLMs underperform compared to existing machine learning models. To address this, we propose ScamNet, a fine-tuned LLM for explainable fraudulent shopping website detection. Our experimental results on real-world datasets demonstrate a breakthrough in detection performance from 22.35% detection rate to 95.59%, particularly in identifying subtle deceptive tactics such as using a legitimate-looking website template. ScamNet offers interpretable insights into its decision-making process, enhancing transparency and overcoming a key limitation of previous approaches.
To Measure or Not: A Cost-Sensitive, Selective Measuring Environment for Agricultural Management Decisions with Reinforcement Learning
PDF ↗Farmers rely on in-field observations to make well-informed crop management decisions to maximize profit and minimize adverse environmental impact. However, obtaining real-world crop state measurements is labor-intensive, time-consuming and expensive. In most cases, it is not feasible to gather crop state measurements before every decision moment. Moreover, in previous research pertaining to farm management optimization, these observations are often assumed to be readily available without any cost, which is unrealistic. Hence, enabling optimization without the need to have *temporally complete* crop state observations is important. An approach to that problem is to include measuring as part of decision making. As a solution, we apply reinforcement learning (RL) to recommend opportune moments to simultaneously measure crop features and apply nitrogen fertilizer. With realistic considerations, we design an RL environment with explicit crop feature measuring costs. While balancing costs, we find that an RL agent, trained with recurrent PPO, discovers adaptive measuring policies that follow critical crop development stages, with results aligned by what domain experts would consider a sensible approach. Our results highlight the importance of measuring when crop feature measurements are not readily available.
Rethinking and Improving Student Learning and Forgetting Processes for Attention based Knowledge Tracing Models
PDF ↗Knowledge tracing (KT) models students' knowledge states and predicts their future performance based on their historical interaction data. However, attention based KT models struggle to accurately capture diverse forgetting behaviors in ever-growing interaction sequences. First, existing models use uniform time decay matrices, conflating forgetting representations with problem relevance. Second, the fixed-length window prediction paradigm fails to model continuous forgetting processes in expanding sequences. To address these challenges, this paper introduces LefoKT, a unified architecture that enhances attention based KT models by incorporating proposed relative forgetting attention. LefoKT improves forgetting modeling through relative forgetting attention to decouple forgetting patterns from problem relevance. It also enhances attention based KT models' length extrapolation capability for capturing continuous forgetting processes in ever-growing interaction sequences. Extensive experimental results on three datasets validate the effectiveness of LefoKT.
Accurate detection of dust storms is challenging due to complex meteorological interactions. With the development of deep learning, deep neural networks have been increasingly applied to dust storm detection, offering better learning and generalization capabilities compared to traditional physical modeling. However, existing methods face some limitations, leading to performance bottlenecks in dust storm detection. From the task perspective, existing research focuses on occurrence detection while neglecting intensity detection. From the data perspective, existing research fails to explore the utilization of multi-source data. From the model perspective, most models are built on convolutional neural networks, which have an inherent limitation in capturing long-range dependencies. To address the challenges mentioned, this study proposes Dust-Mamba. To the best of our knowledge, this study is the first attempt to accomplish both the occurrence and intensity detection of dust storms with advanced deep learning technology. In Dust-Mamba, multi-source data is introduced to provide a comprehensive perspective, Mamba and attention are applied to boost feature selection while maintaining long-range modeling capability. Additionally, this study proposes Structure Sharing Transfer Learning Strategies for intensity detection, which further enhances the performance of Dust-Mamba with minimal time cost. As shown by experiments, Dust-Mamba achieves Dice scores of 0.963 for occurrence detection and 0.560 for intensity detection, surpassing several baseline models. In conclusion, this study offers valuable baselines for dust storm detection, with significant reference value and promising application potential.
Bridging the Gap: Enhancing LLM Performance for Low-Resource African Languages with New Benchmarks, Fine-Tuning, and Cultural Adjustments
PDF ↗Large Language Models (LLMs) have shown remarkable performance across various tasks, yet significant disparities remain for non-English languages, and especially native African languages. This paper addresses these disparities by creating approximately 1 million human-translated words of new benchmark data in 8 low-resource African languages, covering a population of over 160 million speakers of: Amharic, Bambara, Igbo, Sepedi (Northern Sotho), Shona, Sesotho (Southern Sotho), Setswana, and Tsonga. Our benchmarks are translations of Winogrande and three sections of MMLU: college medicine, clinical knowledge, and virology. Using the translated benchmarks, we report previously unknown performance gaps between state-of-the-art (SOTA) LLMs in English and African languages. Finally, using results from over 400 fine-tuned models, we explore several methods to reduce the LLM performance gap, including high-quality dataset fine-tuning (using an LLM-as-an-Annotator), cross-lingual transfer, and cultural appropriateness adjustments. Key findings include average mono-lingual improvements of 5.6% with fine-tuning (with 5.4% average mono-lingual improvements when using high-quality data over low-quality data), 2.9% average gains from cross-lingual transfer, and a 3.0% out-of-the-box performance boost on culturally appropriate questions. The publicly available benchmarks, translations, and code from this study support further research and development aimed at creating more inclusive and effective language technologies.
During the COVID-19 pandemic, a major driver of new surges has been the emergence of new variants. When a new variant emerges in one or more countries, other nations monitor its spread in preparation for its potential arrival. The impact of the new variant and the timings of epidemic peaks in a country highly depend on when the variant arrives. The current methods for predicting the spread of new variants rely on statistical modeling, however, these methods work only when the new variant has already arrived in the region of interest and has a significant prevalence. Can we predict when a variant existing elsewhere will arrive in a given region? To address this question, we propose a variant-dynamics-informed Graph Neural Network (GNN) approach. First, we derive the dynamics of variant prevalence across pairs of regions (countries) that apply to a large class of epidemic models. The dynamics motivate the introduction of certain features in the GNN. We demonstrate that our proposed dynamics-informed GNN outperforms all the baselines, including the currently pervasive framework of Physics-Informed Neural Networks (PINNs). To advance research in this area, we introduce a benchmarking tool to assess a user-defined model's prediction performance across 87 countries and 36 variants.
The increasing frequency and intensity of natural disasters call for rapid and accurate damage assessment. In response, disaster benchmark datasets from high-resolution satellite imagery have been constructed to develop methods for detecting damaged areas. However, these methods face significant challenges when applied to previously unseen regions due to the limited geographical and disaster-type diversity in the existing datasets. We introduce DAVI (Disaster Assessment with VIsion foundation model), a novel approach that addresses domain disparities and detects structural damage at the building level without requiring ground-truth labels for target regions. DAVI combines task-specific knowledge from a model trained on source regions with task-agnostic knowledge from an image segmentation model to generate pseudo labels indicating potential damage in target regions. It then utilizes a two-stage refinement process, which operate at both pixel and image levels, to accurately identify changes in disaster-affected areas. Our evaluation, including a case study on the 2023 Türkiye earthquake, demonstrates that our model achieves exceptional performance across diverse terrains (e.g., North America, Asia, and the Middle East) and disaster types (e.g., wildfires, hurricanes, and tsunamis). This confirms its robustness in disaster assessment without dependence on ground-truth labels and highlights its practical applicability.
Citizen science biodiversity data present great opportunities for ecology and conservation across vast spatial and temporal scales. However, the opportunistic nature of these data lacks the sampling structure required by modeling methodologies that address a pervasive challenge in ecological data collection: imperfect detection, i.e., the likelihood of under-observing species on field surveys. Occupancy modeling is an example of an approach that accounts for imperfect detection by explicitly modeling the observation process separately from the biological process of habitat selection. This produces species distribution models that speak to the pattern of the species on a landscape after accounting for imperfect detection in the data, rather than the pattern of species observations corrupted by errors. To achieve this benefit, occupancy models require multiple surveys of a site across which the site's status (i.e., occupied or not) is assumed constant. Since citizen science data are not collected under the required repeated-visit protocol, observations may be grouped into sites post hoc. Existing approaches for constructing sites discard some observations and/or consider only geographic distance and not environmental similarity. In this study, we compare ten approaches for site construction in terms of their impact on downstream species distribution models for 31 bird species in Oregon, using observations recorded in the eBird database. We find that occupancy models built on sites constructed by spatial clustering algorithms perform better than existing alternatives.
Aligning the behavior of Large language models (LLMs) with human intentions and values remains a critical challenge. Reinforcement learning from human feedback (RLHF) aligns LLMs by training a reward model (RM) on human preferences and fine-tuning the LLMs to maximize RM feedback. Despite its effectiveness and popularity, RLHF is prone to biased local optimization. It means RM fails to provide feedback that accurately aligns with human preference, causing LLMs to explore unexpected generalizations, and failing to achieve alignment objectives. To mitigate this issue, we propose a novel sequence-to-sequence (seq2seq) reward modeling method. Its key insight is that learning from language feedback rather than scalar feedback improves RLHF without additional annotations. We replaced the reward modeling target from binary maximum likelihood estimation (MLE) with sequence MLE. This method enables richer and fine-grained language feedback without additional annotations, models, or training stages. Our experiments demonstrated its effectiveness, specifically, reducing the refusal-to-response paradigm in single-turn safety dialogues and the long-response bias in text summarization tasks. We provide further analysis that seq2seq RM improves RLHF performance across 2B and 7B LLMs on 3 NLP tasks, achieving an average win rate of 76.9%. We further show that seq2seq RM can still improve the performance of RLHF under out-of-distribution prompts.
Auditing Large Language Models (LLMs) is a crucial and challenging task. In this study, we focus on auditing black-box LLMs without access to their parameters, only to the provided service. We treat this type of auditing as a black-box optimization problem where the goal is to automatically uncover input-output pairs of the target LLMs that exhibit illegal, immoral, or unsafe behaviors. For instance, we may seek a non-toxic input that the target LLM responds to with a toxic output or an input that induces the hallucinative response from the target LLM containing politically sensitive individuals. This black-box optimization is challenging due to the scarcity of feasible points, the discrete nature of the prompt space, and the large search space. To address these challenges, we propose Curiosity-Driven Auditing for Large Language Models (CALM), which uses intrinsically motivated reinforcement learning to finetune an LLM as the auditor agent to uncover potential harmful and biased input-output pairs of the target LLM. CALM successfully identifies derogatory completions involving celebrities and uncovers inputs that elicit specific names under the black-box setting. This work offers a promising direction for auditing black-box LLMs.
Large Language Models (LLMs) have demonstrated impressive capabilities in complex reasoning tasks. However, they can be easily misled by unfaithful arguments during conversations, even when their original statements are correct. To this end, we investigate the problem of maintaining faithful integrity in LLMs. This involves ensuring that LLMs adhere to their faithful statements in the face of opposing arguments and are able to correct their incorrect statements when presented with faithful arguments. In this work, we propose a novel framework, named Alignment for Faithful Integrity with Confidence Estimation (AFICE), which aims to align the LLM responses with faithful integrity. Specifically, AFICE first designs a Bilateral Confidence Estimation (BCE) approach for estimating the uncertainty of each response generated by the LLM given a specific context, which simultaneously estimate the model's confidence to the question based on the internal states during decoding as well as to the answer based on cumulative probability ratios. With the BCE, we construct a conversational preference dataset composed of context, original statement, and argument, which is adopted for aligning the LLM for faithful integrity using Direct Preference Optimization (DPO). Extensive experimental results on a wide range of benchmarks demonstrate significant improvements in the LLM's ability to maintain faithful responses when encountering opposing arguments, ensuring both the practical utility and trustworthiness of LLMs in complex interactive settings.
Converting different modalities into generalized text, which then serves as input prompts for large language models (LLMs), is a common approach for aligning multimodal models, particularly when pairwise data is limited. Text-centric alignment method leverages the unique properties of text as a modality space, transforming diverse inputs into a unified textual representation, thereby enabling downstream models to effectively interpret various modal inputs. This study evaluates the quality and robustness of multimodal representations in the face of noise imperfections, dynamic input order permutations, and missing modalities, revealing that current text-centric alignment methods can compromise downstream robustness. To address this issue, we propose a new text-centric adversarial training approach that significantly enhances robustness compared to traditional robust training methods and pre-trained multimodal foundation models. Our findings underscore the potential of this approach to improve the robustness and adaptability of multimodal representations, offering a promising solution for dynamic and real-world applications.
Given that AI systems are set to play a pivotal role in future decision-making processes, their trustworthiness and reliability are of critical concern. Due to their scale and complexity, modern AI systems resist direct interpretation, and alternative ways are needed to establish trust in those systems, and determine how well they align with human values. We argue that good measures of the information processing similarities between AI and humans, may be able to achieve these same ends. While Representational alignment (RA) approaches measure similarity between the internal states of two systems, the associated data can be expensive and difficult to collect for human systems. In contrast, Behavioural alignment (BA) comparisons are cheaper and easier, but questions remain as to their sensitivity and reliability. We propose two new behavioural alignment metrics misclassification agreement which measures the similarity between the errors of two systems on the same instances, and class-level error similarity which measures the similarity between the error distributions of two systems. We show that our metrics correlate well with RA metrics, and provide complementary information to another BA metric, within a range of domains, and set the scene for a new approach to value alignment.
The leaderboard of Large Language Models (LLMs) in mathematical tasks has been continuously updated. However, the majority of evaluations focus solely on the final results, neglecting the quality of the intermediate steps. This oversight can mask underlying problems, such as logical errors or unnecessary steps in the reasoning process. To measure reasoning beyond final-answer accuracy, we introduce ReasonEval, a new methodology for evaluating the quality of reasoning steps. ReasonEval employs validity and redundancy to characterize the reasoning quality, as well as accompanying LLMs to assess them automatically. We explore different design options for the LLM-based evaluators and empirically demonstrate that ReasonEval, when instantiated with base models possessing strong mathematical knowledge and trained with high-quality labeled data, consistently outperforms baseline methods in the meta-evaluation datasets. We also highlight the strong generalization capabilities of ReasonEval. By utilizing ReasonEval to evaluate LLMs specialized in math, we find that an increase in final-answer accuracy does not necessarily guarantee an improvement in the overall quality of the reasoning steps for challenging mathematical problems. Additionally, we observe that ReasonEval can play a significant role in data selection. We open-source the best-performing model, meta-evaluation script, and all evaluation results to facilitate future research.
Split learning, as a distributed learning framework, effectively addresses the issue of limited computing resources. However, despite achieving a separation of data and computation, recent studies have pointed out that this framework still faces two major security challenges: privacy leakage and model security. Most current research focuses on the problem of privacy leakage, emphasizing how to prevent malicious servers from recovering or inferring the client's private data. However, the issue of model security in split learning has not received sufficient attention. This paper reveals the vulnerability of split learning to backdoor attacks. Since split learning cannot access client data directly, it can only guide the client model to incorporate backdoors through gradients. To address this issue, we design an attack framework that modifies intermediate activations to influence the gradients. We designed a parrot model that learns the client’s feature space, enabling the server to obtain the intermediate activations of poisoned data. During the forward pass, some of the intermediate activations and labels transmitted from the client to the server are replaced with poisoned activations and target labels. This replacement method effectively integrates the backdoor task into the model while partially retaining the main task. This approach ensures that the main task is preserved while seamlessly embedding the backdoor task. Our attack framework minimizes reliance on client knowledge and ensures that the attack process remains undetectable by the client. Through extensive experiments, we demonstrated high attack success rates using triggers such as BadNet, SIG, Blended, and WaNet, while minimizing the impact on the main task.
DR-Encoder: Encode Low-rank Gradients with Random Prior for Large Language Models Differentially Privately
PDF ↗The emergence of the large language model (LLM) has shown its superiority in a wide range of disciplines, including language understanding and translation, relational logic reasoning, and even partial differential equations solving. The transformer is the pervasive backbone architecture for the foundation model construction. It is vital to research how to adjust the Transformer architecture to achieve an end-to-end privacy guarantee in LLM fine-tuning. This paper investigates three potential information leaks during a federated fine-tuning procedure for LLM (FedLLM). Based on the potential information leakage, we insert two-stage randomness into FedLLM to provide an end-to-end privacy guarantee solution. The first stage is to train a gradient auto-encoder with a Gaussian random prior based on the statistical information of the gradients generated by local clients. The second stage is fine-tuning the overall LLM with a differential privacy guarantee by adopting appropriate Gaussian noises. We show our proposed method's efficiency and accuracy gains with several foundation models and two popular evaluation benchmarks. Furthermore, we present a comprehensive privacy analysis with Gaussian Differential Privacy (GDP) and Renyi Differential Privacy (RDP).