Our study of 20 knowledge workers revealed a common challenge: the difficulty of synthesizing unstructured information scattered across multiple platforms to make informed decisions. Drawing on their vision of an ideal knowledge synthesis tool, we developed Yodeai, an AI-enabled system, to explore both the opportunities and limitations of AI in knowledge work. Through a user study with 16 product managers, we identified three key requirements for Generative AI in knowledge work: adaptable user control, transparent collaboration mechanisms, and the ability to integrate background knowledge with external information. However, we also found significant limitations, including overreliance on AI, user isolation, and contextual factors outside the AI's reach. As AI tools become increasingly prevalent in professional settings, we propose design principles that emphasize adaptability to diverse workflows, accountability in personal and collaborative contexts, and context-aware interoperability to guide the development of human-centered AI systems for product managers and knowledge workers.

Visual Question Answering (VQA) requires reasoning across visual and textual modalities, yet Large Vision-Language Models (LVLMs) often lack integrated commonsense knowledge, limiting their robustness in real-world scenarios. To address this, we introduce MAGIC-VQA, a novel framework that enhances VQA by systematically integrating commonsense knowledge with LVLMs. MAGIC-VQA employs a three-stage process: (1) Explicit Knowledge Integration from external sources, (2) By-Type Post-Processing for contextual refinement, and (3) Implicit Knowledge Augmentation using a Graph Neural Network (GNN) for structured reasoning. While GNNs bring greater depth to structured inference, they enable superior relational inference beyond LVLMs. MAGIC-VQA bridges a key gap by unifying commonsensse knowledge with LVLM-driven reasoning, eliminating the need for extensive pre-training or complex prompt tuning. Our framework achieves state-of-the-art performance on benchmark datasets, significantly improving commonsense reasoning in VQA.

Air pollution has become a major threat to human health, making accurate forecasting crucial for pollution control. Traditional physics-based models forecast global air pollution by coupling meteorology and pollution processes, using either online or offline methods depending on whether fully integrated with meteorological models and run simultaneously. However, the high computational demands of both methods severely limit real-time prediction efficiency. Existing deep learning (DL) solutions employ online coupling strategies for global air pollution forecasting, which finetune pollution forecasting based on pretrained atmospheric models, requiring substantial training resources. This study pioneers a DL-based offline coupling framework that utilizes bilinear pooling to achieve offline coupling between meteorological fields and pollutants. The proposed model requires only 13% of the parameters of DL-based online coupling models while achieving competitive performance. Compared with the state-of-the-art global air pollution forecasting model CAMS, our approach demonstrates superiority in 63% variables across all forecast time steps and 85% variables in predictions exceeding 48 hours. This work pioneers experimental validation of the effectiveness of meteorological fields in DL-based global air pollution forecasting, demonstrating that offline coupling meteorological fields with pollutants can achieve a 15% relative reduction in RMSE across all pollution variables. The research establishes a new paradigm for real-time global air pollution warning systems and delivers critical technical support for developing more efficient and comprehensive AI-powered global atmospheric forecasting frameworks.

President Donald Trump's envoy to Russia and Ukraine says he doesn't believe Russian President Vladimir Putin wants to invade Europe. Envoy Steve Witkoff made the statement during a Sunday morning appearance on "Fox News Sunday," commenting on Putin's motives on a "larger scale." "Now I've been asked my opinion about what President Putin's motives are on a larger scale. And I simply have said that I just don't see that he wants to take all of Europe," Witkoff said. "This is a much different situation than it was in World War II. There was no NATO," he added.

In this paper, we evaluate the ability of Large Language Models (LLMs) to assess the veracity of claims in ''news reports'' generated by themselves or other LLMs. Our goal is to determine whether LLMs can effectively fact-check their own content, using methods similar to those used to verify claims made by humans. Our findings indicate that LLMs are more effective at assessing claims in national or international news stories than in local news stories, better at evaluating static information than dynamic information, and better at verifying true claims compared to false ones. We hypothesize that this disparity arises because the former types of claims are better represented in the training data. Additionally, we find that incorporating retrieved results from a search engine in a Retrieval-Augmented Generation (RAG) setting significantly reduces the number of claims an LLM cannot assess. However, this approach also increases the occurrence of incorrect assessments, partly due to irrelevant or low-quality search results. This diagnostic study highlights the need for future research on fact-checking machine-generated reports to prioritize improving the precision and relevance of retrieved information to better support fact-checking efforts. Furthermore, claims about dynamic events and local news may require human-in-the-loop fact-checking systems to ensure accuracy and reliability.

Scene graphs capture complex relationships among objects, serving as strong priors for content generation and manipulation. Yet, reasonably manipulating scene graphs -- whether by adding nodes or modifying edges -- remains a challenging and untouched task. Tasks such as adding a node to the graph or reasoning about a node's relationships with all others are computationally intractable, as even a single edge modification can trigger conflicts due to the intricate interdependencies within the graph. To address these challenges, we introduce SG-Tailor, an autoregressive model that predicts the conflict-free relationship between any two nodes. SG-Tailor not only infers inter-object relationships, including generating commonsense edges for newly added nodes but also resolves conflicts arising from edge modifications to produce coherent, manipulated graphs for downstream tasks. For node addition, the model queries the target node and other nodes from the graph to predict the appropriate relationships. For edge modification, SG-Tailor employs a Cut-And-Stitch strategy to solve the conflicts and globally adjust the graph. Extensive experiments demonstrate that SG-Tailor outperforms competing methods by a large margin and can be seamlessly integrated as a plug-in module for scene generation and robotic manipulation tasks.

The fact that everyone with a social media account can create and share content, and the increasing public reliance on social media platforms as a news and information source bring about significant challenges such as misinformation, fake news, harmful content, etc. Although human content moderation may be useful to an extent and used by these platforms to flag posted materials, the use of AI models provides a more sustainable, scalable, and effective way to mitigate these harmful contents. However, low-resourced languages such as the Somali language face limitations in AI automation, including scarce annotated training datasets and lack of language models tailored to their unique linguistic characteristics. This paper presents part of our ongoing research work to bridge some of these gaps for the Somali language. In particular, we created two human-annotated social-media-sourced Somali datasets for two downstream applications, fake news \& toxicity classification, and developed a transformer-based monolingual Somali language model (named SomBERTa) -- the first of its kind to the best of our knowledge. SomBERTa is then fine-tuned and evaluated on toxic content, fake news and news topic classification datasets. Comparative evaluation analysis of the proposed model against related multilingual models (e.g., AfriBERTa, AfroXLMR, etc) demonstrated that SomBERTa consistently outperformed these comparators in both fake news and toxic content classification tasks while achieving the best average accuracy (87.99%) across all tasks. This research contributes to Somali NLP by offering a foundational language model and a replicable framework for other low-resource languages, promoting digital and AI inclusivity and linguistic diversity.

In this digital world, people freely express their emotions using different social media platforms. As a result, modeling and integrating emotion-understanding models are vital for various human-computer interaction tasks such as decision-making, product and customer feedback analysis, political promotions, marketing research, and social media monitoring. As users express different emotions simultaneously in a single instance, annotating emotions in a multilabel setting such as the EthioEmo (Belay et al., 2025) dataset effectively captures this dynamic. Additionally, incorporating intensity, or the degree of emotion, is crucial, as emotions can significantly differ in their expressive strength and impact. This intensity is significant for assessing whether further action is necessary in decision-making processes, especially concerning negative emotions in applications such as healthcare and mental health studies. To enhance the EthioEmo dataset, we include annotations for the intensity of each labeled emotion. Furthermore, we evaluate various state-of-the-art encoder-only Pretrained Language Models (PLMs) and decoder-only Large Language Models (LLMs) to provide comprehensive benchmarking.

In this paper, we establish a benchmark for evaluating large language models (LLMs) on multi-step geospatial tasks relevant to commercial GIS practitioners. We assess seven leading commercial LLMs (Sonnet 3.5 and 3.7, Haiku 3.5, Gemini 2.0, GPT-4o, GPT-4o mini, and o3-mini) using a simple tool-calling agent equipped with 23 geospatial functions. Our benchmark comprises tasks across four categories of increasing complexity, with both solvable and intentionally unsolvable tasks to test hallucination rejection. We develop an LLM-as-Judge evaluation framework to compare agent solutions against reference implementations. Results show Sonnet 3.5 and GPT-4o achieve the best overall performance, with Claude models excelling on solvable tasks while OpenAI models better identify unsolvable scenarios. We observe significant differences in token usage, with Anthropic models consuming substantially more tokens than competitors. Common errors include misunderstanding geometrical relationships, relying on outdated knowledge, and inefficient data manipulation. The resulting benchmark set, evaluation framework, and data generation pipeline are released as open-source resources, providing one more standardized method for ongoing evaluation of LLMs for GeoAI.

Pretrained Language Models (PLMs) built from various sources are the foundation of today's NLP progress. Language representations learned by such models achieve strong performance across many tasks with datasets of varying sizes drawn from various sources. We explore a thorough analysis of domain and task adaptive continual pretraining approaches for low-resource African languages and a promising result is shown for the evaluated tasks. We create AfriSocial, a corpus designed for domain adaptive finetuning that passes through quality pre-processing steps. Continual pretraining PLMs using AfriSocial as domain adaptive pretraining (DAPT) data, consistently improves performance on fine-grained emotion classification task of 16 targeted languages from 1% to 28.27% macro F1 score. Likewise, using the task adaptive pertaining (TAPT) approach, further finetuning with small unlabeled but similar task data shows promising results. For example, unlabeled sentiment data (source) for fine-grained emotion classification task (target) improves the base model results by an F1 score ranging from 0.55% to 15.11%. Combining the two methods, DAPT + TAPT, achieves also better results than base models. All the resources will be available to improve low-resource NLP tasks, generally, as well as other similar domain tasks such as hate speech and sentiment tasks.