arXiv AI November 3, 2026 By G\"okberk \c{C}elikmasat, Atay \"Ozg\"ovde, Fatma Ba\c{s}ak Aydemir

Instruction-Tuning Open-Weight Language Models for BPMN Model Generation

The paper presents InstruBPM, an instruction‑tuned open‑weight large language model that generates BPMN process models from natural language descriptions. By preparing paired text‑diagram data and applying parameter‑efficient fine‑tuning with quantization, the authors demonstrate that the tuned model outperforms both untuned open‑weight baselines and strong proprietary models in sequence, structural, and guideline‑conformance metrics. The approach is cost‑effective, privacy‑preserving, and supports on‑prem deployment, with publicly released models and scripts for reproducibility.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Aug 7

MermaidSeqBench: An Evaluation Benchmark for NL-to-Mermaid Sequence Diagram Generation

arXiv:2511. 14967v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown great promise in generating structured diagrams from natural language descriptions, particularly Mermaid sequence diagrams for software engineering.

By Basel Shbita, Farhan Ahmed, Chad DeLuca

llms benchmarks

arXiv Machine Learning

Aug 3

Simulation Code Generation for Fluid Systems using Large Language Models: Benchmarking Models and Prompting Strategies

arXiv:2607. 29389v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated a strong ability to generate syntactically correct code from natural-language specifications.

By Jan Marius St\"urmer, Jascha Knack, Tobias Koch, Andreas Weinmann

llms benchmarks

arXiv Computation and Language

Oct 23

Beyond Prompt and Parser Engineering: Soft-Prompt Tuning for Automated LLM Evaluation

The paper introduces soft‑prompt tuning as a lightweight, automated method for evaluating large language models (LLMs). By optimizing only ten soft‑prompt vectors—about 0.0006% of a 7B model’s parameters—within 150 steps, the approach adapts models to specific benchmark formats, improving format compliance while preserving knowledge accuracy. Experiments across seven models and eleven datasets show that this method matches strong evaluation‑harness baselines, enhances evaluation signals on challenging datasets, and yields cleaner outputs that align better with exact‑match scoring and independent LLM judges.

By Selen Erkan, Bastian Boll, Kristian Kersting, Bj\"orn Deiseroth, Letitia Parcalabescu

llms benchmarks

arXiv Machine Learning

Jun 5

Can LLMs Write Correct TLA+ Specifications? Evaluating Natural-Language-to-TLA+ Generation

arXiv:2606. 05792v1 Announce Type: cross Abstract: TLA+ has supported industrial verification at companies such as Amazon and Microsoft, yet writing correct TLA+ specifications from natural language still requires time and expertise, which limits adoption.

By Arslan Bisharat, Brian Ortiz, Eric Spencer, Khushboo Bhadauria, TaiNing Wang, George K. Thiruvathukal, Konstantin Laufer, Mohammed Abuhamad

llms safety

arXiv AI

Jul 24

Learn2Zinc: Fine-tuning Small Language Models for Text-to-Model Translation in MiniZinc

arXiv:2607. 20456v1 Announce Type: cross Abstract: Large language models excel at code generation for mainstream programming languages but struggle with rare, domain-specific languages such as MiniZinc, a constraint modeling language for combinatorial problems.

By Serdar Kadioglu, Karthik Uppuluri

llms fine-tuning

Hugging Face Trending Papers

Aug 5

OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling

Context lengths of language models (LMs) have dramatically increased, driven by the demands for in-context learning, self-improvement, and long-horizon agentic workflows. Existing long-context corpora, however, are dominated by books, academic articles, and code repositories, which are finite resources and often scarce in long-distance dependencies.

llms agents fine-tuning benchmarks

One email a morning, machine-written

Related stories

MermaidSeqBench: An Evaluation Benchmark for NL-to-Mermaid Sequence Diagram Generation

Simulation Code Generation for Fluid Systems using Large Language Models: Benchmarking Models and Prompting Strategies

Beyond Prompt and Parser Engineering: Soft-Prompt Tuning for Automated LLM Evaluation

Can LLMs Write Correct TLA+ Specifications? Evaluating Natural-Language-to-TLA+ Generation

Learn2Zinc: Fine-tuning Small Language Models for Text-to-Model Translation in MiniZinc

OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling