arXiv subjects

Marek Šuppa

Publications and source records attributed to Marek Šuppa.

At least 19 recordsLinked to original sources

arXiv2026

sk-bench: A Native-First Benchmark for Evaluating Large Language Models in Slovak

Multilingual LLM benchmarks omit Slovak, a morphologically rich West Slavic language of five million speakers, or cover it only by machine translation. We present sk-bench, a native-first Slovak benchmark with 30 datasets (33 scored task variants) across ten skill categories. Eleven resources are introduced or first packaged for generative-LLM evaluation, including IFEval-SK with Slovak-adapted instruction checkers and native Chiby/SKJ1 resources for Slovak grammar and morphology. We evaluate 55 open- and closed-weights models under one harness. The best open model trails proprietary APIs by 12.6 points. Model rankings are similar for native and translated closed-form data ($ρ\geq0.98$), though translation separates the strongest models less well. By contrast, human-authored and LLM-generated QA questions rank models differently ($ρ=0.72$). For Qwen3-14B, continued Slovak pretraining lowers the overall score by 13.9 points. A small instruction set restores three quarters of that loss. Test-time reasoning improves scores by 8.5 to 12.5 points for models of 9B and above. Together, these findings suggest four design lessons for other under-resourced languages: use native data where translation fails, plan instruction repair after language adaptation, enable test-time reasoning before scaling up, and avoid overinvesting in target-language prompts. We release the data and code at https://github.com/slovak-nlp/sk-bench

cs.CL↗

arXiv2026

Last Translation Benchmark

For scientific progress, we need benchmarks that test the limits of state-of-the-art models, and evaluation methods that inform us about failure cases. As models get stronger, standard benchmarks for machine translation are approaching saturation. Further, automatic translation metrics are unreliable, opaque, and vulnerable to reward-hacking. Even gold human evaluation is not problem-free, because it often lacks reproducibility, objectivity, and scalability. Overall, this prevents us from tracking progress in the field and identifying pathways for improvement. We introduce the Last Translation Benchmark, a collection of human-authored and peer-reviewed examples (texts, images, audio, videos) that break leading machine translation models. We also present a new evaluation approach: each example comes with handcrafted verification rules describing concrete failure cases on that example, therefore allowing reliable and actionable future evaluation. The Last Translation Benchmark is a live dataset that accepts ongoing contributions. The latest version is LTBv1, containing accepted contributions prior to September 1st 2026, with future releases planned as new data is continuously collected.

cs.CL↗

arXiv2026

When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation

Artificial intelligence benchmarks are an important mechanism to measure model progress and guide deployment decisions. However, benchmarks quickly "saturate", making it difficult to differentiate models and diminishing their long-term value. In this study, we define benchmark saturation and analyze it across 60 language model benchmarks using 14 properties that relate to saturation. We find that nearly half of our benchmarks exhibit saturation, with rates increasing with age. Further, we find that resilience to saturation is impacted by expert-curation, not by public test data. Our results suggest that design choices can extend benchmark longevity and inform more durable evaluation approaches.

cs.AI↗

arXiv2026

RAGthoven at SemEval-2026 Task 1: A Multi-Stage Pipeline Walks Into a Benchmark and Barely Clears the Bar

We present RAGthoven, our system for SemEval-2026 Task 1 (MWAHAHA), Subtask A (multilingual constrained humor generation in English, Spanish, and Chinese). RAGthoven decomposes creative text generation into a multi-stage large language model (LLM) pipeline (Planner, Best-of-N Writer, Reflector for self-critique, LLM-as-a-judge Judge) grounded in computational humor theory (Benign Violation Theory, Script-based Semantic Theory of Humor) and refined across ten experiments. In our final configuration, we augment the Planner with retrieval-augmented generation (RAG) from a curated joke corpus, seeding generation with diverse joke mechanisms. We also evaluate two agentic variants -- ReAct-style sequential tool-calling (Exp09) and autonomous multi-branch orchestration (Exp10) -- that expose the same four stages with a deterministic ConstraintAudit checker. Across four frontier models on a held-out 12-instance English sample, neither agentic variant produced outputs we judged superior to the non-agentic pipeline despite substantially higher tool-call budgets. RAGthoven shares Rank 1 with the Gemini 2.5 Flash baseline in all three languages, with overlapping organizer-reported confidence intervals. In Spanish, it leads the baseline by 42 raw Elo points (1182 vs. 1140), while in English (1045 vs. 1081) and Chinese (1045 vs. 1053) the baseline holds the higher raw rating within the same statistical tie. Together, these results suggest language-dependent diminishing returns from elaborate multi-stage prompt engineering and agentic scaffolding once a strong frontier model is in the loop.

cs.CL↗

arXiv2026

Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results

AI evaluations are widely used for testing and understanding progress. However, the diverse evaluators bring with them inconsistencies that challenge analysis and comparison. First, results are saved in incompatible formats, scattered across leaderboards, papers, blog posts, evaluation harness logs, and custom repositories. Second, results are created by different evaluation frameworks, which produce divergent scores for nominally identical evaluations and record metadata inconsistently, hindering comparison, cross-community evaluation science, cost reduction, and reuse. We introduce Every Eval Ever, the first shared schema and community-crowdsourced repository for AI evaluation results. The schema standardizes how evaluations are represented in a unified, single JSON document. It is source-agnostic by design, ingesting results from evaluation harnesses and papers alike, and optionally stores per-instance outputs for fine-grained analysis. We contribute: (i) a community-governed metadata schema with a companion instance-level schema, the first standardization effort of its kind; (ii) automatic converters from popular formats, evaluation harnesses, and leaderboards to the unified schema; and (iii) a crowdsourced community database hosted on Hugging Face, currently spanning to date 22,235 models, 2,273 unique benchmarks, and 31 evaluation formats.

cs.AI↗

arXiv2026

SkMTEB: Slovak Massive Text Embedding Benchmark and Model Adaptation

We introduce SkMTEB, the first comprehensive MTEB-style text embedding benchmark for Slovak, a low-resource West Slavic language, comprising 31 datasets across 7 task types -- nearly 4$\times$ the depth of existing multilingual benchmark coverage for Slovak. Our evaluation of 31 embedding models reveals that large instruction-tuned multilingual models achieve the strongest performance, while existing Slovak-specific models trained for NLU tasks transfer poorly to embedding tasks. To address the need for efficient, locally-deployable Slovak embeddings, we develop \texttt{e5-sk-small} (45M parameters) and \texttt{e5-sk-large} (365M) by applying vocabulary trimming and fine-tuning to Multilingual E5 models. Despite size reductions of up to 62\%, our open-source models achieve competitive performance with proprietary APIs while remaining locally deployable for semantic search and retrieval-augmented generation (RAG). We release the benchmark, models, datasets, and code openly, hoping our approach offers a replicable path for other under-resourced languages.

cs.CL↗

arXiv2026

SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?

AI agents are increasingly expected to complete long-horizon workflows that require sustained progress over hours, millions of tokens, and complex environments. Yet current agent benchmarks largely evaluate short-form tasks, such as single pull requests, small tickets, or 5-10 minute exercises, limiting our ability to measure agents' capabilities in planning, long-context understanding, and memory use. We introduce SWE-Marathon, a benchmark of 20 long-horizon tasks spanning software engineering and adjacent technical domains. Each task consists of a unique executable environment, a human-written reference solution, and a multi-layer verification suite. Logged agent attempts average 27.2M total tokens, making SWE-Marathon substantially longer-horizon than existing SWE and command-line agent benchmarks. Current frontier coding agents solve fewer than 30% of tasks. Failures often arise from poor self-verification, self-reported infeasibility, and premature termination. We also observe reward-hacking behavior in 13.8% of rollouts, where agents attempt to exploit the environment or verifier to bypass the intended workflow. SWE-Marathon includes adversarial review of test suites and execution environments, as well as multi-layer checks designed to prevent shortcut solutions. We release SWE-Marathon, evaluation code, and agent trajectories at https://swe-marathon.org/.

cs.SE↗

arXiv2026

Universal NER v2: Towards a Massively Multilingual Named Entity Recognition Benchmark

While multilingual language models promise to bring the benefits of LLMs to speakers of many languages, gold-standard evaluation benchmarks in most languages to interrogate these assumptions remain scarce. The Universal NER project, now entering its fourth year, is dedicated to building gold-standard multilingual Named Entity Recognition (NER) benchmark datasets. Inspired by existing massively multilingual efforts for other core NLP tasks (e.g., Universal Dependencies), the project uses a general tagset and thorough annotation guidelines to collect standardized, cross-lingual annotations of named entity spans. The first installment (UNER v1) was released in 2024, and the project has continued and expanded since then, with various organizers, annotators, and collaborators in an active community.

cs.CL↗

arXiv2026

SloPal: A 60-Million-Word Slovak Parliamentary Corpus with Aligned Speech and Fine-Tuned ASR Models

Slovak remains a low-resource language for automatic speech recognition (ASR), with fewer than 100 hours of publicly available training data. We present SloPal, a comprehensive Slovak parliamentary corpus comprising 330,000 speaker-segmented transcripts (66 million words, 220 million tokens) spanning 2001--2024, with rich metadata including speaker names, roles, and session information. From this collection, we derive SloPalSpeech, a 2,806-hour aligned speech dataset with segments up to 30 seconds, constructed using a language-agnostic anchor-based alignment pipeline and optimized for Whisper-based ASR training. Fine-tuning Whisper on SloPalSpeech reduces Word Error Rate (WER) by up to 70\%, with the fine-tuned small model (244M parameters) approaching base large-v3 (1.5B parameters) performance at 6$\times$ fewer parameters. We publicly release the SloPal text corpus, SloPalSpeech aligned audio, and four fine-tuned Whisper models at https://huggingface.co/collections/NaiveNeuron/slopal, providing the most comprehensive open Slovak parliamentary language resource to date.

cs.CL↗

arXiv2026

SlovKE: A Large-Scale Dataset and LLM Evaluation for Slovak Keyphrase Extraction

Keyphrase extraction for morphologically rich, low-resource languages remains understudied, largely due to the scarcity of suitable evaluation datasets. We address this gap for Slovak by constructing a dataset of 227,432 scientific abstracts with author-assigned keyphrases -- scraped and systematically cleaned from the Slovak Central Register of Theses -- representing a 25-fold increase over the largest prior Slovak resource and approaching the scale of established English benchmarks such as KP20K. Using this dataset, we benchmark three unsupervised baselines (YAKE, TextRank, KeyBERT with SlovakBERT embeddings) and evaluate KeyLLM, an LLM-based extraction method using GPT-3.5-turbo. Unsupervised baselines achieve at most 11.6\% exact-match $F1@6$, with a large gap to partial matching (up to 51.5\%), reflecting the difficulty of matching inflected surface forms to author-assigned keyphrases. KeyLLM narrows this exact--partial gap, producing keyphrases closer to the canonical forms assigned by authors, while manual evaluation on 100 documents ($κ= 0.61$) confirms that KeyLLM captures relevant concepts that automated exact matching underestimates. Our analysis identifies morphological mismatch as the dominant failure mode for statistical methods -- a finding relevant to other inflected languages. The dataset (https://huggingface.co/datasets/NaiveNeuron/SlovKE) and evaluation code (https://github.com/NaiveNeuron/SlovKE) are publicly available.

cs.CL↗

arXiv2025

Enhancing BERT Fine-Tuning for Sentiment Analysis in Lower-Resourced Languages

Limited data for low-resource languages typically yield weaker language models (LMs). Since pre-training is compute-intensive, it is more pragmatic to target improvements during fine-tuning. In this work, we examine the use of Active Learning (AL) methods augmented by structured data selection strategies which we term 'Active Learning schedulers', to boost the fine-tuning process with a limited amount of training data. We connect the AL to data clustering and propose an integrated fine-tuning pipeline that systematically combines AL, clustering, and dynamic data selection schedulers to enhance model's performance. Experiments in the Slovak, Maltese, Icelandic and Turkish languages show that the use of clustering during the fine-tuning phase together with AL scheduling can simultaneously produce annotation savings up to 30% and performance improvements up to four F1 score points, while also providing better fine-tuning stability.

cs.CL↗

arXiv2025

MMTEB: Massive Multilingual Text Embedding Benchmark

Text embeddings are typically evaluated on a limited set of tasks, which are constrained by language, domain, and task diversity. To address these limitations and provide a more comprehensive evaluation, we introduce the Massive Multilingual Text Embedding Benchmark (MMTEB) - a large-scale, community-driven expansion of MTEB, covering over 500 quality-controlled evaluation tasks across 250+ languages. MMTEB includes a diverse set of challenging, novel tasks such as instruction following, long-document retrieval, and code retrieval, representing the largest multilingual collection of evaluation tasks for embedding models to date. Using this collection, we develop several highly multilingual benchmarks, which we use to evaluate a representative set of models. We find that while large language models (LLMs) with billions of parameters can achieve state-of-the-art performance on certain language subsets and task categories, the best-performing publicly available model is multilingual-e5-large-instruct with only 560 million parameters. To facilitate accessibility and reduce computational cost, we introduce a novel downsampling method based on inter-task correlation, ensuring a diverse selection while preserving relative model rankings. Furthermore, we optimize tasks such as retrieval by sampling hard negatives, creating smaller but effective splits. These optimizations allow us to introduce benchmarks that drastically reduce computational demands. For instance, our newly introduced zero-shot English benchmark maintains a ranking order similar to the full-scale version but at a fraction of the computational cost.

cs.CL↗

arXiv2025

FractalBench: Diagnosing Visual-Mathematical Reasoning Through Recursive Program Synthesis

Mathematical reasoning requires abstracting symbolic rules from visual patterns -- inferring the infinite from the finite. We investigate whether multimodal AI systems possess this capability through FractalBench, a benchmark evaluating fractal program synthesis from images. Fractals provide ideal test cases: Iterated Function Systems with only a few contraction maps generate complex self-similar patterns through simple recursive rules, requiring models to bridge visual perception with mathematical abstraction. We evaluate four leading MLLMs -- GPT-4o, Claude 3.7 Sonnet, Gemini 2.5 Flash, and Qwen 2.5-VL -- on 12 canonical fractals. Models must generate executable Python code reproducing the fractal, enabling objective evaluation. Results reveal a striking disconnect: 76% generate syntactically valid code but only 4% capture mathematical structure. Success varies systematically -- models handle geometric transformations (Koch curves: 17-21%) but fail at branching recursion (trees: <2%), revealing fundamental gaps in mathematical abstraction. FractalBench provides a contamination-resistant diagnostic for visual-mathematical reasoning and is available at https://github.com/NaiveNeuron/FractalBench

cs.AI↗

arXiv2025

skLEP: A Slovak General Language Understanding Benchmark

In this work, we introduce skLEP, the first comprehensive benchmark specifically designed for evaluating Slovak natural language understanding (NLU) models. We have compiled skLEP to encompass nine diverse tasks that span token-level, sentence-pair, and document-level challenges, thereby offering a thorough assessment of model capabilities. To create this benchmark, we curated new, original datasets tailored for Slovak and meticulously translated established English NLU resources. Within this paper, we also present the first systematic and extensive evaluation of a wide array of Slovak-specific, multilingual, and English pre-trained language models using the skLEP tasks. Finally, we also release the complete benchmark data, an open-source toolkit facilitating both fine-tuning and evaluation of models, and a public leaderboard at https://github.com/slovak-nlp/sklep in the hopes of fostering reproducibility and drive future research in Slovak NLU.

cs.CL↗

arXiv2025

LCDC: Bridging Science and Machine Learning for Light Curve Analysis

The characterization and analysis of light curves are vital for understanding the physical and rotational properties of artificial space objects such as satellites, rocket stages, and space debris. This paper introduces the Light Curve Dataset Creator (LCDC), a Python-based toolkit designed to facilitate the preprocessing, analysis, and machine learning applications of light curve data. LCDC enables seamless integration with publicly available datasets, such as the newly introduced Mini Mega Tortora (MMT) database. Moreover, it offers data filtering, transformation, as well as feature extraction tooling. To demonstrate the toolkit's capabilities, we created the first standardized dataset for rocket body classification, RoBo6, which was used to train and evaluate several benchmark machine learning models, addressing the lack of reproducibility and comparability in recent studies. Furthermore, the toolkit enables advanced scientific analyses, such as surface characterization of the Atlas 2AS Centaur and the rotational dynamics of the Delta 4 rocket body, by streamlining data preprocessing, feature extraction, and visualization. These use cases highlight LCDC's potential to advance space debris characterization and promote sustainable space exploration. Additionally, they highlight the toolkit's ability to enable AI-focused research within the space debris community.

astro-ph.IM↗

arXiv2024

RoBo6: Standardized MMT Light Curve Dataset for Rocket Body Classification

Space debris presents a critical challenge for the sustainability of future space missions, emphasizing the need for robust and standardized identification methods. However, a comprehensive benchmark for rocket body classification remains absent. This paper addresses this gap by introducing the RoBo6 dataset for rocket body classification based on light curves. The dataset, derived from the Mini Mega Tortora database, includes light curves for six rocket body classes: CZ-3B, Atlas 5 Centaur, Falcon 9, H-2A, Ariane 5, and Delta 4. With 5,676 training and 1,404 test samples, it addresses data inconsistencies using resampling, normalization, and filtering techniques. Several machine learning models were evaluated, including CNN and transformer-based approaches, with Astroconformer reporting the best performance. The dataset establishes a common benchmark for future comparisons and advancements in rocket body classification tasks.

cs.CV↗

arXiv2024

Universal NER: A Gold-Standard Multilingual Named Entity Recognition Benchmark

We introduce Universal NER (UNER), an open, community-driven project to develop gold-standard NER benchmarks in many languages. The overarching goal of UNER is to provide high-quality, cross-lingually consistent annotations to facilitate and standardize multilingual NER research. UNER v1 contains 18 datasets annotated with named entities in a cross-lingual consistent schema across 12 diverse languages. In this paper, we detail the dataset creation and composition of UNER; we also provide initial modeling baselines on both in-language and cross-lingual learning settings. We release the data, code, and fitted models to the public.

cs.CL↗

arXiv2024

Bryndza at ClimateActivism 2024: Stance, Target and Hate Event Detection via Retrieval-Augmented GPT-4 and LLaMA

This study details our approach for the CASE 2024 Shared Task on Climate Activism Stance and Hate Event Detection, focusing on Hate Speech Detection, Hate Speech Target Identification, and Stance Detection as classification challenges. We explored the capability of Large Language Models (LLMs), particularly GPT-4, in zero- or few-shot settings enhanced by retrieval augmentation and re-ranking for Tweet classification. Our goal was to determine if LLMs could match or surpass traditional methods in this context. We conducted an ablation study with LLaMA for comparison, and our results indicate that our models significantly outperformed the baselines, securing second place in the Target Detection task. The code for our submission is available at https://github.com/NaiveNeuron/bryndza-case-2024

cs.CL↗