We present the DEREK (Deep Extraction & Reasoning Engine for Knowledge) Module, a secure and scalable Retrieval-Augmented Generation pipeline designed specifically for enterprise document question answering. Designed and implemented by eSapiens, the system ingests heterogeneous content (PDF, Office, web), splits it into 1,000-token overlapping chunks, and indexes them in a hybrid HNSW+BM25 store. User queries are refined by GPT-4o, retrieved via combined vector+BM25 search, reranked with Cohere, and answered by an LLM using CO-STAR prompt engineering. A LangGraph verifier enforces citation overlap, regenerating answers until every claim is grounded. On four LegalBench subsets, 1000-token chunks improve Recall@50 by approximately 1 pp and hybrid+rerank boosts Precision@10 by approximately 7 pp; the verifier raises TRACe Utilization above 0.50 and limits unsupported statements to less than 3%. All components run in containers, enforce end-to-end TLS 1.3 and AES-256. These results demonstrate that the DEREK module delivers accurate, traceable, and production-ready document QA with minimal operational overhead. The module is designed to meet enterprise demands for secure, auditable, and context-faithful retrieval, providing a reliable baseline for high-stakes domains such as legal and finance.

Machine unlearning seeks to remove the influence of particular data or class from trained models to meet privacy, legal, or ethical requirements. Existing unlearning methods tend to forget shallowly: phenomenon of an unlearned model pretend to forget by adjusting only the model response, while its internal representations retain information sufficiently to restore the forgotten data or behavior. We empirically confirm the widespread shallowness by reverting the forgetting effect of various unlearning methods via training-free performance recovery attack and gradient-inversion-based data reconstruction attack. To address this vulnerability fundamentally, we define a theoretical criterion of ``deep forgetting'' based on one-point-contraction of feature representations of data to forget. We also propose an efficient approximation algorithm, and use it to construct a novel general-purpose unlearning algorithm: One-Point-Contraction (OPC). Empirical evaluations on image classification unlearning benchmarks show that OPC achieves not only effective unlearning performance but also superior resilience against both performance recovery attack and gradient-inversion attack. The distinctive unlearning performance of OPC arises from the deep feature forgetting enforced by its theoretical foundation, and recaps the need for improved robustness of machine unlearning methods.

Privacy and regulatory barriers often hinder centralized machine learning solutions, particularly in sectors like healthcare where data cannot be freely shared. Federated learning has emerged as a powerful paradigm to address these concerns; however, existing frameworks primarily support gradient-based models, leaving a gap for more interpretable, tree-based approaches. This paper introduces a federated learning framework for Random Forest classifiers that preserves data privacy and provides robust performance in distributed settings. By leveraging PySyft for secure, privacy-aware computation, our method enables multiple institutions to collaboratively train Random Forest models on locally stored data without exposing sensitive information. The framework supports weighted model averaging to account for varying data distributions, incremental learning to progressively refine models, and local evaluation to assess performance across heterogeneous datasets. Experiments on two real-world healthcare benchmarks demonstrate that the federated approach maintains competitive predictive accuracy - within a maximum 9\% margin of centralized methods - while satisfying stringent privacy requirements. These findings underscore the viability of tree-based federated learning for scenarios where data cannot be centralized due to regulatory, competitive, or technical constraints. The proposed solution addresses a notable gap in existing federated learning libraries, offering an adaptable tool for secure distributed machine learning tasks that demand both transparency and reliable performance. The tool is available at https://github.com/ieeta-pt/fed_rf.

The auditing of financial documents, historically a labor-intensive process, stands on the precipice of transformation. AI-driven solutions have made inroads into streamlining this process by recommending pertinent text passages from financial reports to align with the legal requirements of accounting standards. However, a glaring limitation remains: these systems commonly fall short in verifying if the recommended excerpts indeed comply with the specific legal mandates. Hence, in this paper, we probe the efficiency of publicly available Large Language Models (LLMs) in the realm of regulatory compliance across different model configurations. We place particular emphasis on comparing cutting-edge open-source LLMs, such as Llama-2, with their proprietary counterparts like OpenAI's GPT models. This comparative analysis leverages two custom datasets provided by our partner PricewaterhouseCoopers (PwC) Germany. We find that the open-source Llama-2 70 billion model demonstrates outstanding performance in detecting non-compliance or true negative occurrences, beating all their proprietary counterparts. Nevertheless, proprietary models such as GPT-4 perform the best in a broad variety of scenarios, particularly in non-English contexts.

In the era of big data applications, Federated Graph Learning (FGL) has emerged as a prominent solution that reconcile the tradeoff between optimizing the collective intelligence between decentralized datasets holders and preserving sensitive information to maximum. Existing FGL surveys have contributed meaningfully but largely focus on integrating Federated Learning (FL) and Graph Machine Learning (GML), resulting in early stage taxonomies that emphasis on methodology and simulated scenarios. Notably, a data centric perspective, which systematically examines FGL methods through the lens of data properties and usage, remains unadapted to reorganize FGL research, yet it is critical to assess how FGL studies manage to tackle data centric constraints to enhance model performances. This survey propose a two-level data centric taxonomy: Data Characteristics, which categorizes studies based on the structural and distributional properties of datasets used in FGL, and Data Utilization, which analyzes the training procedures and techniques employed to overcome key data centric challenges. Each taxonomy level is defined by three orthogonal criteria, each representing a distinct data centric configuration. Beyond taxonomy, this survey examines FGL integration with Pretrained Large Models, showcases realistic applications, and highlights future direction aligned with emerging trends in GML.

People with disabilities (PwD) experience disproportionately high levels of discrimination and hate online, particularly in India, where entrenched stigma and limited resources intensify these challenges. Large language models (LLMs) are increasingly used to identify and mitigate online hate, yet most research on online ableism focuses on Western audiences with Western AI models. Are these models adequately equipped to recognize ableist harm in non-Western places like India? Do localized, Indic language models perform better? To investigate, we adopted and translated a publicly available ableist speech dataset to Hindi, and prompted eight LLMs--four developed in the U.S. (GPT-4, Gemini, Claude, Llama) and four in India (Krutrim, Nanda, Gajendra, Airavata)--to score and explain ableism. In parallel, we recruited 175 PwD from both the U.S. and India to perform the same task, revealing stark differences between groups. Western LLMs consistently overestimated ableist harm, while Indic LLMs underestimated it. Even more concerning, all LLMs were more tolerant of ableism when it was expressed in Hindi and asserted Western framings of ableist harm. In contrast, Indian PwD interpreted harm through intention, relationality, and resilience--emphasizing a desire to inform and educate perpetrators. This work provides groundwork for global, inclusive standards of ableism, demonstrating the need to center local disability experiences in the design and evaluation of AI systems.

Can AI file your taxes? Not yet. Calculating US personal income taxes is a task that requires building an understanding of vast amounts of English text and using that knowledge to carefully compute results. We propose TaxCalcBench, a benchmark for determining models' abilities to calculate personal income tax returns given all of the necessary information. Our experiment shows that state-of-the-art models succeed in calculating less than a third of federal income tax returns even on this simplified sample set. Our analysis concludes that models consistently misuse tax tables, make errors in tax calculation, and incorrectly determine eligibility. Our findings point to the need for additional infrastructure to apply LLMs to the personal income tax calculation task.

Understanding what constitutes safety in AI-generated content is complex. While developers often rely on predefined taxonomies, real-world safety judgments also involve personal, social, and cultural perceptions of harm. This paper examines how annotators evaluate the safety of AI-generated images, focusing on the qualitative reasoning behind their judgments. Analyzing 5,372 open-ended comments, we find that annotators consistently invoke moral, emotional, and contextual reasoning that extends beyond structured safety categories. Many reflect on potential harm to others more than to themselves, grounding their judgments in lived experience, collective risk, and sociocultural awareness. Beyond individual perceptions, we also find that the structure of the task itself -- including annotation guidelines -- shapes how annotators interpret and express harm. Guidelines influence not only which images are flagged, but also the moral judgment behind the justifications. Annotators frequently cite factors such as image quality, visual distortion, and mismatches between prompt and output as contributing to perceived harm dimensions, which are often overlooked in standard evaluation frameworks. Our findings reveal that existing safety pipelines miss critical forms of reasoning that annotators bring to the task. We argue for evaluation designs that scaffold moral reflection, differentiate types of harm, and make space for subjective, context-sensitive interpretations of AI-generated content.

On Sunday, our thoughtful and reserved president reposted on his Truth Social site a video generated by artificial intelligence that falsely showed former President Obama being arrested and imprisoned. There are those among you who think this is high humor; those among you who who find it as tiresome as it is offensive; and those among you blissfully unaware of the mental morass that is Truth Social. Whatever camp you fall into, the video crosses all demographics by being expected -- just another crazy Trump stunt in a repetitive cycle of division and diversion so frequent it makes Groundhog Day seem fresh. But there are three reasons why this particular video -- not made by the president but amplified to thousands -- is worth noting, and maybe even worth fearing. First, it is flat-out racist. In it, Obama is ripped out of a chair in the Oval Office and forced onto his knees, almost bowing, to a laughing Trump.

We present the LLM Economist, a novel framework that uses agent-based modeling to design and assess economic policies in strategic environments with hierarchical decision-making. At the lower level, bounded rational worker agents -- instantiated as persona-conditioned prompts sampled from U.S. Census-calibrated income and demographic statistics -- choose labor supply to maximize text-based utility functions learned in-context. At the upper level, a planner agent employs in-context reinforcement learning to propose piecewise-linear marginal tax schedules anchored to the current U.S. federal brackets. This construction endows economic simulacra with three capabilities requisite for credible fiscal experimentation: (i) optimization of heterogeneous utilities, (ii) principled generation of large, demographically realistic agent populations, and (iii) mechanism design -- the ultimate nudging problem -- expressed entirely in natural language. Experiments with populations of up to one hundred interacting agents show that the planner converges near Stackelberg equilibria that improve aggregate social welfare relative to Saez solutions, while a periodic, persona-level voting procedure furthers these gains under decentralized governance. These results demonstrate that large language model-based agents can jointly model, simulate, and govern complex economic systems, providing a tractable test bed for policy evaluation at the societal scale to help build better civilizations.