4arXiv cs.CL (Computation and Language)·
SINT-Flow: LLM workflow framework for automated schema integration with new SINT-Bench benchmark
SINT-Flow is a schema integration framework using five LLM-based operators composed into workflows to perform fully automated end-to-end schema integration, including decomposition of denormalized tables describing multiple entity types. The authors also introduce SINT-Bench, a benchmark of 10 schema integration tasks across 93 relational tables. Evaluation using GPT-5.2 and Qwen-3.6-27B as backbone models achieves F1 scores of 96%+ for entity-type detection, 85% for attribute detection, and 83% for schema mapping. The work demonstrates LLM applicability to a classical database integration problem with a self-consistency strategy and review loop ablation.
Related guides (2)
Related events (8)
MaDI-Bench: First end-to-end benchmark for relational table data integration
Researchers introduce MaDI-Bench (Mannheim Data Integration Benchmark), the first benchmark covering the full data integration pipeline for relational tables, including schema matching, value normalization, entity matching, and conflict resolution. Prior benchmarks evaluated these steps in isolation or omitted stages, limiting research on holistic integration methods. The benchmark includes base tasks across multiple domains, a mechanism to generate variants to prevent saturation, and is validated against human-engineered, best-of-breed, and LLM-based pipelines. All artifacts are publicly available.
FlowPipe: LLM-conditioned Generative Flow Networks for automated data preparation pipeline construction
FlowPipe is a new framework that frames ML data preparation pipeline synthesis as conditional probabilistic flow generation over a directed acyclic graph, using Conditional Generative Flow Networks (C-GFlowNets) with a Trajectory Balance objective. LLM-derived semantic priors are injected into the policy via Feature-wise Linear Modulation (FiLM), and a failure-aware flow objective steers search away from invalid states. Evaluated on 74 real-world datasets across two benchmark suites, FlowPipe improves accuracy by 11.96% on average over SOTA baselines and achieves 12.5x faster training convergence. The work addresses long-standing limitations in automated data pipeline construction including weak credit assignment and inefficient exploration.
Constrained LLM interface for multi-physics finite element simulations in FEniCS
Researchers present a natural-language interface for FEniCS finite element simulations that deliberately constrains LLM involvement to front-end parsing and geometry generation, while a deterministic dispatcher routes validated specifications to human-written solver templates. The system achieves 100% final valid parse rate on a 15-prompt benchmark and 90% success on custom geometry generation. Validation against analytical solutions shows sub-percent agreement for smooth cases and 2-5% for harder nonlinear cases. The architecture is positioned as a reliability-focused alternative to open-ended LLM code generation for scientific computing.
EdgeFlow: Edge-Map Augmented VLM-Based Flowchart Processing for Industrial Requirements Engineering
EdgeFlow augments Vision Language Models with deterministically extracted Canny edge maps as structural priors to improve flowchart-to-Mermaid conversion in industrial requirements engineering, requiring no annotated training data or fine-tuning. Evaluated on IndusReqFlow, a real-world industrial dataset, it achieves +17.39 pp node-level F1 and +16.94 pp edge-level F1 over off-the-shelf VLMs. Cross-dataset evaluation on a synthetic benchmark shows no significant gains, highlighting the gap between synthetic and industrial benchmarks for VLM-based RE tools.
Flowise: open-source visual builder for AI agents gains traction on GitHub
Flowise is an open-source TypeScript project for building AI agents and LLM workflows through a visual drag-and-drop interface. The repository has accumulated over 53,000 GitHub stars with 107 new stars on the day of observation. It represents a no-code/low-code approach to agent and chain construction in the LangChain ecosystem.
Closed-loop validation-repair achieves 99% schema compliance for clinical LLMs across healthcare standards
A new arXiv paper evaluates three open-source models (Qwen2.5 7B, Llama 3.1 8B, Gemma2 9B) on schema compliance with ICD-10, CPT, and HL7 FHIR standards across 960 clinical scenario-model pairs. Baseline compliance ranged from 85.9–91.6%, with 96% of failures being representation-level format violations rather than clinical reasoning errors. A closed-loop validation-repair framework raised overall compliance to 99.0%, with most errors resolving in one or two iterations, suggesting this system-level approach is a viable safeguard for healthcare EHR integration.
SupraBench: First benchmark for evaluating LLMs on supramolecular chemistry reasoning
Researchers introduce SupraBench, the first benchmark designed to systematically evaluate LLMs on supramolecular chemistry tasks including binding affinity prediction, top-binder selection, solvent identification, and host-guest description. The work also releases SupraPMC, a 16M-token corpus of supramolecular chemistry articles from Europe PMC to support domain adaptation. Evaluation of broad open and proprietary LLMs reveals substantial headroom across all tasks, with domain pretraining improving in-distribution regression but creating format compliance tradeoffs. The benchmark targets a narrow but practically important scientific domain where LLM acceleration could reduce days-long dry-lab verification cycles.
Langfuse: Open Source LLM Engineering Platform Trending on GitHub
Langfuse is an open-source LLM engineering platform providing observability, metrics, evaluations, prompt management, and dataset tooling. It integrates with OpenTelemetry, LangChain, OpenAI SDK, and LiteLLM. The project has accumulated 28,075 GitHub stars with 89 new stars today, indicating sustained community traction. Backed by Y Combinator (W23), it represents a notable entry in the LLM ops/tooling ecosystem.