Financial reporting systems increasingly use large language models (LLMs) to extract and summarize corporate disclosures. However, most assume a single-market setting and do not address structural differences across jurisdictions. Variations in accounting taxonomies, tagging infrastructures (e.g., XBRL vs. PDF), and aggregation conventions make cross-jurisdiction reporting a semantic alignment and verification challenge. We present FinReporting, an agentic workflow for localized cross-jurisdiction financial reporting. The system builds a unified canonical ontology over Income Statement, Balance Sheet, and Cash Flow, and decomposes reporting into auditable stages including filing acquisition, extraction, canonical mapping, and anomaly logging. Rather than using LLMs as free-form generators, FinReporting deploys them as constrained verifiers under explicit decision rules and evidence grounding. Evaluated on annual filings from the US, Japan, and China, the system improves consistency and reliability under heterogeneous reporting regimes. We release an interactive demo supporting cross-market inspection and structured export of localized financial statements. Our demo is available at https://huggingface.co/spaces/BoomQ/FinReporting-Demo . The video describing our system is available at https://www.youtube.com/watch?v=f65jdEL31Kk

Multi-step symbolic reasoning is essential for robust financial analysis; yet, current benchmarks largely overlook this capability. Existing datasets such as FinQA and ConvFinQA emphasize final numerical answers while neglecting the intermediate reasoning steps required for transparency and verification. To address this gap, we introduce FinChain, the first benchmark specifically designed for verifiable Chain-of-Thought evaluation in finance. FinChain spans 58 topics across 12 financial domains, each represented by parameterized symbolic templates with executable Python code that enable fully machine-verifiable reasoning and scalable, contamination-free data generation.To assess reasoning capacity, we propose ChainEval, a dynamic alignment measure that jointly evaluates both the final-answer correctness and the step-level reasoning consistency. Our evaluation of 26 leading LLMs reveals that even frontier LLMs exhibit clear limitations in symbolic financial reasoning, while domain-adapted and math-enhanced fine-tuned models can substantially narrow this gap.Overall, FinChain exposes persistent weaknesses in multi-step financial reasoning and provides a foundation for developing trustworthy, interpretable, and verifiable financial AI. This project is available at https://github.com/mbzuai-nlp/finchain.git.

FinMMEval 2026 Task 2 evaluates short-answer financial question answering over multilingual evidence. Each final-test item pairs an English question with financial statements and news in English, Chinese, Japanese, Spanish, and Greek. Participating systems submit one concise answer per item in JSONL format. The final-test set contains 256 items, split evenly between easy and expert tiers; each tier contains four question templates instantiated over 32 company-report groups. Gold answers were withheld during submission, and systems were ranked by macro-averaged item-level ROUGE-1 F1 against organizer-held reference answers. The final leaderboard includes 12 ranked submissions. The strongest systems are closely clustered, with the top four separated by less than one percentage point in ROUGE-1 F1. The submitted system papers document retrieval-augmented generation, cross-lingual evidence handling, structured prompting, answer compression, and validation strategies.

We present the setup and the tasks of the FinMMEval Lab at CLEF 2026, which introduces the first multilingual and multimodal evaluation framework for financial Large Language Models (LLMs). While recent advances in financial natural language processing have enabled automated analysis of market reports, regulatory documents, and investor communications, existing benchmarks remain largely monolingual, text-only, and limited to narrow subtasks. FinMMEval 2026 addresses this gap by offering three interconnected tasks that span financial understanding, reasoning, and decision-making: Financial Exam Question Answering, Multilingual Financial Question Answering (PolyFiQA), and Financial Decision Making. Together, these tasks provide a comprehensive evaluation suite that measures models' ability to reason, generalize, and act across diverse languages and modalities. The lab aims to promote the development of robust, transparent, and globally inclusive financial AI systems, with datasets and evaluation resources publicly released to support reproducible research.

FinMMEval 2026 Task 1 evaluates multilingual financial multiple-choice question answering in English, Chinese, Arabic, and Hindi. The task tests whether systems can select the correct answer to finance questions involving domain terminology, numerical interpretation, and conceptual financial reasoning across languages and scripts. The final-test set contains 800 questions, with 200 questions per language; gold answers were withheld during submission, and each language was ranked independently by accuracy. The final leaderboards contain 13 English, 11 Chinese, 11 Arabic, and 10 Hindi ranked submissions. Top accuracies range from 92.0

The increased use of large language models (LLMs) across a variety of real-world applications calls for mechanisms to verify the factual accuracy of their outputs. Difficulties lie in assessing the factuality of free-form responses in open domains. Also, different papers use disparate evaluation benchmarks and measurements, which renders them hard to compare and hampers future progress. To mitigate these issues, we propose OpenFactCheck, a unified framework for building customized automatic fact-checking systems, benchmarking their accuracy, evaluating factuality of LLMs, and verifying claims in a document. OpenFactCheck consists of three modules: (i) CUSTCHECKER allows users to easily customize an automatic fact-checker and verify the factual correctness of documents and claims, (ii) LLMEVAL, a unified evaluation framework assesses LLM's factuality ability from various perspectives fairly, and (iii) CHECKEREVAL is an extensible solution for gauging the reliability of automatic fact-checkers' verification results using human-annotated datasets. Data and code are publicly available at https://github.com/yuxiaw/openfactcheck.

An efficient scheduler (algorithm) as a part of batch processing, implemented in a real warehouse management system is considered. The goal is not completion time but rather the fairness of the schedule expressed as a minimal overload of working places (machines, workers, etc.) used. As a combinatorial optimization problem, the objective is to find the permutation of the rows of a n x k boolean matrix B that minimizes the sum of the scalar products of each two consecutive rows. For the above-mentioned warehouse, the size n of a batch is in thousands and the number of working places is up to ten. The problem is modeled as many visits traveling salesman problem over the vertices of k dimensional unit hypercube with distances equal to the scalar products of the coordinate vectors of the vertices. The case n= 2^k is proven NP-hard and for the needs of the practice, where n >> k a heuristic greedy algorithm with a good, experimentally proven precision is proposed.

Testing with quiz questions has proven to be an effective way to assess and improve the educational process. However, manually creating quizzes is tedious and time-consuming. To address this challenge, we present Leaf, a system for generating multiple-choice questions from factual text. In addition to being very well suited for the classroom, Leaf could also be used in an industrial setting, e.g., to facilitate onboarding and knowledge sharing, or as a component of chatbots, question answering systems, or Massive Open Online Courses (MOOCs). The code and the demo are available on GitHub (https://github.com/KristiyanVachev/Leaf-Question-Generation).

In education, quiz questions have become an important tool for assessing the knowledge of students. Yet, manually preparing such questions is a tedious task, and thus automatic question generation has been proposed as a possible alternative. So far, the vast majority of research has focused on generating the question text, relying on question answering datasets with readily picked answers, and the problem of how to come up with answer candidates in the first place has been largely ignored. Here, we aim to bridge this gap. In particular, we propose a model that can generate a specified number of answer candidates for a given passage of text, which can then be used by instructors to write questions manually or can be passed as an input to automatic answer-aware question generators. Our experiments show that our proposed answer candidate generation model outperforms several baselines.

Gamification has been a leading global phenomenon since 2010 and represented in a variety of domains including education. Yet whether the application of game elements in non-entertaining contexts is effective, still sparkles an ongoing debate which aims to be solved by the application of gamification frameworks. A gamification framework analyses the core drives in human motivation in a system that can be easily applied to produce an effective strategy for successful implementation of gamification. On our journey to design and develop an educational application, implementing game design elements, that supports university students enrolled in a Web development course, we analyzed a variety of gamification frameworks in order to define the right one for our needs. In this paper, we present an in-depth analysis of the different gamification frameworks, leading towards a justified choice in the context of our research. Outcomes of our study and a work-in-progress implementation of the educational application are also summarized.

Nowadays the technology evolves rapidly and with it, the computing devices are becoming more powerful, flexible and capable of performing complicated and tangled tasks. This results in a significant shift in the way applications are designed and developed. Yet modern web frameworks manage to cope with this client-side complexity by adopting a mindset oriented towards the design of robust and complex applications that can be delivered quickly with a high level of security, scaled easily, and extended simply. As part of our research on developing an educational application, that supports university students enrolled in Web development course, we made an overview and comparison of the existing technologies, in terms of frameworks, libraries, programming languages and deployment options, adopting a practical approach. Apart from outlining the results, a sample blueprint of the application architecture of the educational application is also proposed in this paper.

Sensors provide valuable information about the surrounding environment. They are used to monitor the GPS location of objects or the temperature of the surrounding environment. Databases are typically used to store the data that these sensors provide in the increasing demand for sensor data storage platforms. Longtime SQL databases have proven their reliability in maintaining data for various kinds of applications. Over the last couple of years, NoSQL databases become a popular choice among developers because of their availability, scalability, dynamic schemas and storing different types of information in a fast manner. This paper compares various types of models for storing real-time sensor readings in the NoSQL database. For the current analysis, a microcomputer system was designed to send live GPS data and other sensor readings over the GPRS Network. A comparison is also made between NoSQL database running on a cloud server and physical machine. Concluding this article, we summarize the results obtained in the process of storing a huge amount of real-time sensor readings.

Exclusive flexibility in developing dynamic web applications, which PHP offers, makes it one of the most common Web programming languages today. The popularity of the language increases the number of web applications written in PHP and the questions with the security issues, which these applications arise. In this article we present strategies and best practices for developing secure code with PHP. We make brief overview of the main types of attacks, classified by CWE, which may affect the PHP applications and best practice how to avoid them.

We present experiments with part-of-speech tagging for Bulgarian, a Slavic language with rich inflectional and derivational morphology. Unlike most previous work, which has used a small number of grammatical categories, we work with 680 morpho-syntactic tags. We combine a large morphological lexicon with prior linguistic knowledge and guided learning from a POS-annotated corpus, achieving accuracy of 97.98%, which is a significant improvement over the state-of-the-art for Bulgarian.

The sensor data is heterogeneous, redundant, real-time, massive, streaming and is generated in high frequency. The increasing use of sensors leads to a rising demand on sensor data storage platforms. Appropriate data management is therefore, a key factor in making sure that the sensor data storage system becomes a reality. In this article we will focus on finding a data storage solution that is capable of storing huge amount of sensor data. The storage models in SQL and NoSQL databases are analyzed and compared, thus seeking an appropriate type of database for sensor data storage. Hypertable is identified to be the database that best suits the system requirements. It is therefore investigated how to implement the sensor data insertion and retrieval services. Query processing over distributed databases is more challenging than doing so in a centralized environment. Because NoSQL databases do not work with SQL, they require manual query programming which can be fast for simple tasks but time-consuming for others. This paper considers the extension of Hypertable query language with aggregate operations and describes the implementation of the query language interpreter.

Purpose The purpose of this paper is to explore the dark side of news community forums: the proliferation of opinion manipulation trolls. In particular, it explores the idea that a user who is called a troll by several people is likely to be one. It further demonstrates the utility of this idea for detecting accused and paid opinion manipulation trolls and their comments as well as for predicting the credibility of comments in news community forums. Design/methodology/approach The authors are aiming to build a classifier to distinguish trolls vs regular users. Unfortunately, it is not easy to get reliable training data. The authors solve this issue pragmatically: the authors assume that a user who is called a troll by several people is likely to be such, which are called accused trolls. Based on this assumption and on leaked reports about actual paid opinion manipulation trolls, the authors build a classifier to distinguish trolls vs regular users. Findings The authors compare the profiles of paid trolls vs accused trolls vs non-trolls, and show that a classifier trained to distinguish accused trolls from non-trolls does quite well also at telling apart paid trolls from non-trolls. Research limitations/implications The troll detection works even for users with about 10 comments, but it achieves the best performance for users with a sizable number of comments in the forum, e.g. 100 or more. Yet, there is not such a limitation for troll comment detection. Practical implications The approach would help forum moderators in their work, by pointing them to the most suspicious users and comments. It would be also useful to investigative journalists who want to find paid opinion manipulation trolls. Social implications The authors can offer a better experience to online users by filtering out opinion manipulation trolls and their comments. Originality/value The authors propose a novel approach for finding paid opinion manipulation trolls and their posts.

Users posting online expect to remain anonymous unless they have logged in, which is often needed for them to be able to discuss freely on various topics. Preserving the anonymity of a text's writer can be also important in some other contexts, e.g., in the case of witness protection or anonymity programs. However, each person has his/her own style of writing, which can be analyzed using stylometry, and as a result, the true identity of the author of a piece of text can be revealed even if s/he has tried to hide it. Thus, it could be helpful to design automatic tools that can help a person obfuscate his/her identity when writing text. In particular, here we propose an approach that changes the text, so that it is pushed towards average values for some general stylometric characteristics, thus making the use of these characteristics less discriminative. The approach consists of three main steps: first, we calculate the values for some popular stylometric metrics that can indicate authorship; then we apply various transformations to the text, so that these metrics are adjusted towards the average level, while preserving the semantics and the soundness of the text; and finally, we add random noise. This approach turned out to be very efficient, and yielded the best performance on the Author Obfuscation task at the PAN-2016 competition.

Linked data has emerged as an interesting technology for publishing structured data on the Web but also as a powerful mechanism for integrating disparate data sources. Various tools and approaches have been developed in the semantic Web community to produce and consume linked data, however little attention has been paid to monetization of linked data. In this paper we introduce a data marketplace – proDataMarket – that enables data providers to generate, advertise, and sell linked data, and data consumers to purchase linked data on the marketplace. The marketplace was originally designed with a focus on geospatial linked data (targeting property-related data providers and consumers) but its capabilities are generic and can be used for data in various domains. This demo will highlight the capabilities offered to the providers and consumers of the data made available on the marketplace.

Recently, much attention has been given to models for identifying rumors in social media. Features that are helpful for automatic inference of credibility, veracity, reliability of information have been described. The ultimate goal is to train classification models that are able to recognize future high-impact rumors as early as possible, before the event unfolds. The generalization power of the models is greatly hindered by the domain-dependent distributions of the features, an issue insufficiently discussed. Here we study a large dataset consisting of rumor and non-rumor tweets commenting on nine breakingnews stories taking place in different locations of the world. We found that the distribution of most features are specific to the event and that this bias naturally affects the performance of the model. The analysis of the domain-specific feature distributions is insightful and hints to the distinct characteristics of the underlying social network for different countries, social groups, cultures and others.