Searcharxiv⌕ Search

arXiv subjects

Sören Auer

Publications and source records attributed to Sören Auer.

At least 19 recordsLinked to original sources
arXiv2026

VoiceNet: Fine-Grained Voice Understanding Beyond Emotion at Scale

Expressive speech synthesis has outpaced expressive speech perception: systems now render fine-grained vocal performances that no public benchmark can score. Most benchmarks for this inverse problem stop at six to nine basic emotion categories, largely on acted speech. This paper introduces VoiceNet, a human-annotated representation-level benchmark for voice performance understanding on permissively-licensed in-the-wild speech. VoiceNet has two subsets: VoiceNet-Emo applies a 40-emotion taxonomy with three expert ratings per item, and VoiceNet-Ext, a preliminary subset, scores 57 talking-style attributes including speaking rate, vocal tension, breathiness, and register. The paper also releases Emolia, an emotion-annotated version of the Emilia corpus, with a curated rebalanced subset enriched by dense MOSS-Audio Thinking annotations. Two voice-text contrastive baselines train on this data: a 110M-parameter VoiceCLAP-Small for fast large-scale data filtering and a 7B VoiceCLAP-Large for state-of-the-art performance. Both outperform existing CLAP baselines, which sit near chance on VoiceNet-Emo. On VoiceNet-Emo, VoiceCLAP-Large aligns more closely with the aggregate expert consensus than individual experts agree with one another: a comparison against the majority label rather than evidence of surpassing human emotion perception. All systems evaluated here are voice-text embedding models: VoiceNet scores representation-level attribute recognition and retrieval, not end-to-end spoken-dialogue behaviour. Clustering and filtering uncurated speech corpora into subsets that span diverse talking styles and emotions remains an open challenge; VoiceCLAP embeddings offer a promising tool for this task. VoiceNet, Emolia, and VoiceCLAP are publicly available for research use.

cs.SD↗
arXiv2026

Mined from Scientific Literature: Process Schemas for Atomic Layer Deposition and Etching in Materials Science

Atomic layer deposition (ALD) and atomic layer etching (ALE) are reported heterogeneously across experimental and simulation literature in materials science, hindering comparison and machine-actionable reuse. We present four domain-expert-reviewed JSON Schemas for ALD and ALE experimental and simulation processes. Curated with schema-miner and grounded in QUDT using schema-miner pro, the schemas structure materials, process conditions, configurations , and measured or predicted results. We compare their scope, structure, and semantic grounding, and demonstrate their use for schema-guided literature extraction and publication of structured records through ORKG templates.

cs.AI↗
arXiv2026

When Does Bigger Help? A Controlled Study of LLM Scale for Ontology Learning

The effect of Large Language Model (LLM) scale on ontology learning (OL) performance remains insufficiently characterized. We present a controlled evaluation of 13 models spanning dense and Mixture-of-Experts variants from the Qwen3.5 and Qwen3.6 lineages, together with proprietary GPT release variants, using the OntoLearner retrieval-augmented generation pipeline. All models are evaluated with the same embedding model, retrieval configuration, prompt templates, decoding settings, datasets, and metrics on term typing, taxonomy discovery, and non-taxonomic relationship extraction across four biomedical and materials science and engineering ontologies. Within the dense Qwen3.5 lineage, increasing parameter count primarily improves precision rather than recall, with the largest gains occurring between 9B and 27B parameters. However, the effect of scale is neither monotonic nor uniform across tasks and domains. Dense 27B models outperform substantially larger sparse models on term typing, whereas larger Mixture-of-Experts models achieve the strongest open-weight results on taxonomy discovery. Non-taxonomic relationship extraction remains difficult across model scales, particularly for the Materials Data Science ontology. Performance differences across matched Qwen variants and proprietary GPT releases further indicate that architecture and model lineage can outweigh nominal parameter count. These findings show that model size alone is an insufficient selection criterion for OL and provide empirical guidance for reproducible LLM-assisted ontology engineering.

cs.AI↗
arXiv2026

OntoAligner-Ensemble: Voting-Based Fusion across Heterogeneous Ontology Alignment Techniques

Ontology alignment (OA) has evolved through several methodological paradigms, ranging from lexical and structural aligners to knowledge graph embedding (KGE) models and, more recently, Large Language Model (LLM)-based approaches. Although modern OA frameworks provide unified ecosystems for deploying these heterogeneous aligners, mechanisms for systematically reconciling their complementary and sometimes conflicting predictions remain relatively underexplored. We present OntoAligner-Ensemble, a modular and aligner-agnostic framework that combines candidate correspondences through a configurable two-stage process comprising voting-based fusion strategies followed by post-fusion selection policies. The framework supports any aligner implemented within OntoAligner that produces candidate correspondences, enabling diverse alignment paradigms to be integrated through a unified decision process. To demonstrate its effectiveness, we instantiate the framework using representative lightweight string-aligner, KGE-based, and Retrieval-Augmented Generation aligners powered by both open-weight and API-based LLMs. We evaluate individual aligners and ensemble configurations across eight benchmark tasks from five OAEI tracks spanning biomedical to beyond-equivalence. The results show that ensemble fusion consistently improves the balance between precision and recall and frequently outperforms standalone aligners across diverse domains. Furthermore, our analysis reveals that ensemble composition directly affects the precision-recall trade-off: heterogeneous cross-paradigm ensembles generally improve precision, whereas homogeneous LLM ensembles more often achieve higher overall F1-scores. These findings demonstrate that systematic ensemble learning offers a robust and reproducible strategy for OA while providing practical guidance for selecting ensemble compositions under different alignment scenarios.

cs.AI↗
arXiv2026

Do General NLP Embeddings Capture Ontological Reasoning?

General-purpose NLP embedding models perform well on linguistic tasks, but their ability to capture symbolic ontological structure remains unclear. We introduce AVA, a systematic framework for evaluating whether embeddings distinguish logic-sensitive relational semantics in ontologies and knowledge graphs. AVA comprises 171,007 contrastive triplets derived from 163 heterogeneous ontologies using hierarchy inversion, relation substitution, and disjointness injection. Each triplet contains an ontology statement, a semantically equivalent paraphrase, and a logic-sensitive hard negative with contradictory relational meaning. We evaluate more than 25 state-of-the-art embedding models and find substantial limitations: the best model achieves only 0.739 triplet accuracy, while hard negative accuracy falls to 0.135. Fine-tuning improves discrimination by a large margin but transfers poorly to downstream Semantic Web tasks, including taxonomy discovery and ontology alignment. Further analysis suggests that improvements stem partly from perturbation-specific pattern recognition rather than robust ontological understanding. These findings reveal a persistent gap between linguistic representation learning and ontology-level discrimination, challenging the assumption that strong NLP benchmark performance translates to Semantic Web competence.

cs.CL↗
arXiv2026

When Graph-JEPA Learns the Wrong Thing: Diagnosing and Repairing Category-Conditional Collapse

Joint-embedding predictive architectures are selected almost universally by linear probing and effective rank. We report a case where both read healthily while the representation carries zero usable instance information. We repair it, and a second failure appears: the repaired metric saturates on a target carrying no structural information. Our corpus is a scientific-reasoning graph over 57,903 articles, each a subgraph. A Graph-JEPA predicts one masked aspect from a subgraph's remaining aspects, attaining linear-probe accuracy 0.871 and effective rank 18-47, yet retrieval recovers 0.00 of 14.4 bits (MRR 1.9e-4 vs chance 1.99e-4, p=0.98). Three upper bounds on the same pool and code recover nearly everything (+14.28, +14.34, +14.22 bits), ruling out corpus, masking, pool, and metric as causes. We trace this to variance allocation - frozen inputs place 86.05% of variance on subgraph identity and 0.40% on aspect identity, while trained latents place 0.39% and 99.61%. This is a property of the objective's optimum: the degenerate solution is a global minimum of the coupled predictor/EMA-target objective, present already at init. A repaired configuration reaches 14.377 of 14.379 bits, above the 13.865-bit oracle; reverting the loss to regression drops it to 0.307 bits, confirming it. Yet the repair licenses nothing about reasoning: the target is reducible, since intra-subgraph edges are a deterministic function of node census. The oracle reaches 96.4% of the ceiling, and our largest effect is the learning-rate schedule, not architecture. Bits and a reasoning probe show no relation across ten cells. A data-derived target fails a quality gate - 25.96% of nodes are duplicate placeholders, and the rest is more generic than supporting evidence. Rank, probes, and metrics can all saturate on an unsupportive evaluation. We release a harness with a reducibility audit and target gate.

cs.LG↗
arXiv2026

ICDAR 2026 Competition on Information Extraction from Atomic Layer Deposition/Etching (ALD/E) Scientific Figures

Scientific figure comprehension and reasoning using multimodal AI requires integrating visual perception with domain-specific reasoning to extract meaningful knowledge, often not presented in the text of a research publication. The Sci-ImageMiner benchmark dataset, accompanied by a community-driven competition, raises the bar over prior scientific competitions by curating a comprehensive, expert-annotated dataset across four end-to-end complementary tasks. The competition attracted 68 active participants and 1,263 public/private submissions from 9th January 2026 to 8th April 2026. Our results show that state-of-the-art multimodal models perform well on classification and summarization tasks but struggle with data extraction and scientific reasoning, particularly in visual question-answering. These findings reveal key limitations and highlight challenges and opportunities for improving domain-aware multimodal AI systems. Overall, the Sci-ImageMiner benchmark and competition establish a rigorous platform for advancing research in scientific figure comprehension and reasoning and demonstrate the potential of state-of-the-art approaches for a challenging and complex research area.

cs.CV↗
arXiv2026

Addressing Predicate Redundancy in Research Knowledge Graphs: Duplicate Detection, Resolution, and Prevention

Research Knowledge Graphs (RKGs) enable the structured representation of scientific knowledge, but their weakly enforced schemas make them prone to inconsistencies, particularly in how predicates are defined and used. Duplicate predicates, i.e., distinct identifiers expressing the same or highly similar relationships, introduce semantic redundancy, hinder reuse, and reduce RKG quality. While prior work has addressed duplicate detection for downstream tasks such as query answering or schema alignment, predicate redundancy as a data quality challenge, remains underexplored, particularly in terms of resolution, prevention, and semi-automated curator support. In this paper, we propose a framework for managing duplicate predicates in RKGs that covers detection, resolution, and prevention. The framework combines automated similarity-based methods with human validation and is designed for integration into the lifecycle of evolving, crowdsourced RKGs. We implement the framework in the context of the Open Research Knowledge Graph (ORKG) by extending its existing curation dashboard SciKGDash with embedding-based clustering, interactive inspection, and resolution actions such as merging and deleting. We evaluate the framework on the ORKG, where clustering reveals that up to 30% of predicates are potentially redundant. The analysis also shows recurring modeling patterns that lead to predicate redundancy, user-induced duplication, inconsistent identifier usage, and a lack of standardization in predicate naming and usage. Our findings demonstrate that duplicate predicates arise from user behavior and interface design. Addressing this, requires combining automated methods with human-centered curation and preventive mechanisms. This work positions predicate redundancy as a central data quality challenge and provides a foundation for more systematic and proactive RKG curation.

cs.DL↗
arXiv2026

OntoLearner: A Modular Python Library for Ontology Learning with Large Language Models

Ontology learning (OL) aims to automatically construct structured knowledge models from text, yet progress remains fragmented across methods, domains, and evaluation practices. Despite decades of research, OL lacks a shared infrastructure for systematic evaluation and ontology access. This absence has hindered progress and fragmented research, leaving the central challenges of OL largely unaddressed. We introduce OntoLearner, a modular, cross-domain, and first-of-its-kind framework that unifies ontology access, large language model (LLM)-driven learning pipelines, and standardized benchmarking. OntoLearner releases 180 machine-readable ontologies spanning 22 domains and provides pipeline-ready datasets with train/dev/test splits for three core OL tasks: term typing, taxonomy discovery, and non-taxonomic relation extraction. Using this infrastructure, we conduct a large-scale empirical study of OL, evaluating 22 retrieval models and 12 LLMs across domains and tasks. The results converge on a finding that reframes the central challenge of OL: failure modes scale with ontological complexity rather than model size or architectural sophistication. The primary bottleneck is not model capability, but a structural mismatch between how models encode knowledge and how ontologies organize it. These findings establish that effective OL is reachable through the cross-domain, multi-task benchmarking enabled by OntoLearner. OntoLearner is open-source (MIT license) at https://github.com/sciknoworg/OntoLearner/.

cs.AI↗
arXiv2026

Charting the Future of Scholarly Knowledge with AI: A Community Perspective

Despite the growing availability of tools designed to support scholarly knowledge extraction and organization, many researchers still rely on manual methods, sometimes due to unfamiliarity with existing technologies or limited access to domain-adapted solutions. Meanwhile, the rapid increase in scholarly publications across disciplines has made it increasingly difficult to stay current, further underscoring the need for scalable, AI-enabled approaches to structuring and synthesizing scholarly knowledge. Various research communities have begun addressing this challenge independently, developing tools and frameworks aimed at building reliable, dynamic, and queryable scholarly knowledge bases. However, limited interaction across these communities has hindered the exchange of methods, models, and best practices, slowing progress toward more integrated solutions. This manuscript identifies ways to foster cross-disciplinary dialogue, identify shared challenges, categorize new collaboration and shape future research directions in scholarly knowledge and organization.

cs.DL↗
arXiv2026

Speaker Mining -- FAIR Data on Public Broadcasts for Question Answering

Public broadcasts are at the center of civic discourse: Traditional television talk shows, alongside emerging podcast and web video formats, capture and guide the attention of our societies, shaping how citizens encounter politics, science, and societal issues. Yet, systematic or even simple analyses of these formats face similar challenges: guest and content metadata are scarce, fleeting, fragmented, and not standardized. Research conducted and questions answered are based on extensive, laborious, yet isolated data-curation efforts that capture only a fraction of the relevant landscape. This work seeks to address this issue using a scaling-oriented framework for FAIR data curation in public broadcasting. Evaluated on 15 broadcasting programs, the pipeline aggregates ZDF Archive PDFs, fernsehserien.de, and Wikidata into a unified knowledge graph. Of the 31,817 candidate guest mentions from these three sources, 17,729 could be automatically disambiguated, further 5,958 via 64 hours of manual reconciling using OpenRefine. Results are published at speakermining.wikibase.cloud and linked to Wikidata, enabling SPARQL-based question answering based on gender, age, occupation, or institutional affiliation across 8,436 canonical persons with 23,527 appearances in 6,469 aligned episodes. Our iterative experience reveals that correctly disambiguating and deduplicating speaker data from heterogeneous sources demands dedicated effort on sustainable infrastructure. For scalable and reliable question answering on public broadcasts to be accessible to everyone, we recommend fostering the potential of linked open data: Advancing alignment and utilization approaches like this work, particularly towards crowdsourced development and curation, but also more FAIR data interfaces from public broadcast service providers.

cs.DL↗
arXiv2026

MLReplicate: Benchmarking Autonomous Research Systems for Machine Learning Reproducibility

Autonomous research systems capable of generating complete scientific manuscripts have advanced rapidly, yet robust and realistic evaluation frameworks have failed to keep pace. To bridge this gap, we introduce MLReplicate, an end-to-end benchmark evaluating autonomous research systems on machine learning reproducibility. The benchmark was constructed from ICML 2025 outstanding papers reformulated into standardized input specifications and evaluated across 6 state-of-the-art research systems: AI SCIENTIST-V1, AI SCIENTIST-V2, AGENT LABORATORY, CYCLERESEARCHER, AI RESEARCHER, and TINY SCIENTIST, yielding 45 generated manuscripts, with 3 failed experiments. Outputs are assessed using a dual-protocol approach that combines automated conference-style review and structured expert human evaluation, while tracking computational cost, runtime, and the amount of required human intervention. The automated conference-style review accepted 10 out of 37 valid submissions. An additional 8 submissions were desk-rejected before review for failing to meet the minimum page threshold. In contrast to automated reviews, human reviewers consistently identified methodological flaws, hallucinated experimental results, and reproducibility failures across all systems, and 59% of accepted automated reviews contained fabricated or unsupported claims. We further find that neither token budget nor computational cost predicts output quality: the cheapest system outperforms the most resource-intensive system in human evaluation, despite a 38-fold difference in input tokens. We thus demonstrate that autonomous research workflow design matters more than the scale of compute. MLReplicate exposes a substantial gap between current autonomous research systems and genuine scientific rigor, and establishes a practical, extensible evaluation framework for systematic progress toward trustworthy AI-driven scientific discovery.

cs.LG↗
arXiv2026

From Knowledge to Action: Outcomes of the 2025 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry

Large language models (LLMs) are rapidly changing how researchers in materials science and chemistry discover, organize, and act on scientific knowledge. This paper analyzes a broad set of community-developed LLM applications in an effort to identify emerging patterns in how these systems can be used across the scientific research lifecycle. We organize the projects into two complementary categories: Knowledge Infrastructure, systems that structure, retrieve, synthesize, and validate scientific information; and Action Systems, systems that execute, coordinate, or automate scientific work across computational and experimental environments. The submissions reveal a shift from single-purpose LLM tools toward integrated, multi-agent workflows that combine retrieval, reasoning, tool use, and domain-specific validation. Prominent themes include retrieval-augmented generation as grounding infrastructure, persistent structured knowledge representations, multimodal and multilingual scientific inputs, and early progress toward laboratory-integrated closed-loop systems. Together, these results suggest that LLMs are evolving from general-purpose assistants into composable infrastructure for scientific reasoning and action. This work provides a community snapshot of that transition and a practical taxonomy for understanding emerging LLM-enabled workflows in materials science and chemistry.

cond-mat.mtrl-sci↗
arXiv2026

AISSISTANT: Human-AI Collaborative Review and Perspective Research Workflows in Data Science

High-quality scientific review and perspective papers require substantial time and effort, limiting researchers' ability to synthesize emerging knowledge. While Large Language Models (LLMs) leverage AI Scientists for scientific workflows, existing frameworks focus primarily on autonomous workflows with very limited human intervention. We introduce AIssistant, the first open-source agentic framework for Human--AI collaborative generation of scientific perspectives and review research in data science. AIssistant employs specialized LLM-driven agents augmented with external scholarly tools and allows human intervention throughout the workflow. The framework consists of two main multi-agent systems: Research Workflow with seven agents and a Paper Writing Workflow with eight agents. We conducted a comprehensive evaluation with both human expert reviewers and LLM-based assessment following NeurIPS standards. Our experiments show that OpenAI o1 achieves the highest quality scores on chain-of-thought prompting with augmented Literature Search tools. We also conducted a Human--AI interaction survey with results showing a 65.7\% time savings. We believe that our work establishes a baseline for Human--AI collaborative scientific workflow for review and perspective research in data science, demonstrating that agent-augmented pipelines substantially reduce effort while maintaining research integrity through strategic human oversight.

cs.AI↗
arXiv2026

SciKGDash: The Scientific Knowledge Graph Dashboard for Supporting Knowledge Curation

Research knowledge graphs (RKGs) have emerged as essential technology for organizing scientific knowledge, but their success depends heavily on the quality of their underlying content. Knowledge curation is a critical task to ensure the quality of (research) knowledge graphs ((R)KGs), with human curation being the gold standard despite its time- and resource-intensive nature. Automated methods, while efficient, lack the precision of human expertise. Hybrid approaches, combining automated processes with human oversight, offer a promising solution to this challenge. Dashboards can act as supportive tools in hybrid curation approaches, offering real-time updates and visual overviews. This paper presents an action research study, conducted in collaboration with the Curation and Community Building (C&CB) team of the Open Research Knowledge Graph (ORKG), to explore the development of a dashboard, called SciKGDash, designed to support knowledge curation of the ORKG. SciKGDash serves as a minimum viable product (MVP) tailored to the needs of the C&CB team, with potential for adaptation to other (R)KGs. An experiment with 15 participants demonstrated the usability of SciKGDash, with successful completion of 4 out of 5 curation tasks in under 5 minutes. In addition, SciKGDash received a positive user experience rating (UEQ score of 1.93). While the tailored solution proved effective for the ORKG, the research also highlights limitations in applying specific quality metrics across diverse (R)KGs. Future work should focus on identifying common quality metrics and enhancing SciKGDash with user-friendly features for querying customized quality metrics. Overall, knowledge curation in RKGs remains an under-explored field, warranting further research.

cs.DL↗
arXiv2026

EmoNet-Voice: A Fine-Grained, Expert-Verified Benchmark for Speech Emotion Detection

Speech emotion recognition (SER) systems are constrained by existing datasets that typically cover only 6-10 basic emotions, lack scale and diversity, and face ethical challenges when collecting sensitive emotional states. We introduce EMONET-VOICE, a comprehensive resource addressing these limitations through two components: (1) EmoNet-Voice Big, a 5,000-hour multilingual pre-training dataset spanning 40 fine-grained emotion categories across 11 voices and 4 languages, and (2) EmoNet-Voice Bench, a rigorously validated benchmark of 4,7k samples with unanimous expert consensus on emotion presence and intensity levels. Using state-of-the-art synthetic voice generation, our privacy-preserving approach enables ethical inclusion of sensitive emotions (e.g., pain, shame) while maintaining controlled experimental conditions. Each sample underwent validation by three psychology experts. We demonstrate that our Empathic Insight models trained on our synthetic data achieve strong real-world dataset generalization, as tested on EmoDB and RAVDESS. Furthermore, our comprehensive evaluation reveals that while high-arousal emotions (e.g., anger: 95% accuracy) are readily detected, the benchmark successfully exposes the difficulty of distinguishing perceptually similar emotions (e.g., sadness vs. distress: 63% discrimination), providing quantifiable metrics for advancing nuanced emotion AI. EMONET-VOICE establishes a new paradigm for large-scale, ethically-sourced, fine-grained SER research.

cs.CL↗
arXiv2025

SelfCheck-Eval: A Multi-Module Framework for Zero-Resource Hallucination Detection in Large Language Models

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse applications, from open-domain question answering to scientific writing, medical decision support, and legal analysis. However, their tendency to generate incorrect or fabricated content, commonly known as hallucinations, represents a critical barrier to reliable deployment in high-stakes domains. Current hallucination detection benchmarks are limited in scope, focusing primarily on general-knowledge domains while neglecting specialised fields where accuracy is paramount. To address this gap, we introduce the AIME Math Hallucination dataset, the first comprehensive benchmark specifically designed for evaluating mathematical reasoning hallucinations. Additionally, we propose SelfCheck-Eval, a LLM-agnostic, black-box hallucination detection framework applicable to both open and closed-source LLMs. Our approach leverages a novel multi-module architecture that integrates three independent detection strategies: the Semantic module, the Specialised Detection module, and the Contextual Consistency module. Our evaluation reveals systematic performance disparities across domains: existing methods perform well on biographical content but struggle significantly with mathematical reasoning, a challenge that persists across NLI fine-tuning, preference learning, and process supervision approaches. These findings highlight the fundamental limitations of current detection methods in mathematical domains and underscore the critical need for specialised, black-box compatible approaches to ensure reliable LLM deployment.

cs.CL↗
arXiv2025

TIB AIssistant: a Platform for AI-Supported Research Across Research Life Cycles

The rapidly growing popularity of adopting Artificial Intelligence (AI), and specifically Large Language Models (LLMs), is having a widespread impact throughout society, including the academic domain. AI-supported research has the potential to support researchers with tasks across the entire research life cycle. In this work, we demonstrate the TIB AIssistant, an AI-supported research platform providing support throughout the research life cycle. The AIssistant consists of a collection of assistants, each responsible for a specific research task. In addition, tools are provided to give access to external scholarly services. Generated data is stored in the assets and can be exported as an RO-Crate bundle to provide transparency and enhance reproducibility of the research project. We demonstrate the AIssistant's main functionalities by means of a sequential walk-through of assistants, interacting with each other to generate sections for a draft research paper. In the end, with the AIssistant, we lay the foundation for a larger agenda of providing a community-maintained platform for AI-supported research.

cs.AI↗