BenGER: Benchmarking LLM Systems on Subsumption-Based Legal Reasoning in German Law

arXiv:2605.28183 · cs.CL, cs.AI · Submitted 2026-05-27 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-05-27

Updated: 2026-08-31

Code: https://github.com/SebastianNagl/benger-platform

Terminology

• Benchmark — 31× in this paper · explained in 2 episodes
• Calibration — 22× in this paper · explained in 7 episodes
• LLM judge — 21× in this paper · explained in 2 episodes
• Core — 11× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 10× in this paper · explained in 3 episodes
• Benchmarking — 9× in this paper · explained in 3 episodes
• Accuracy — 7× in this paper · explained in 1 episode
• RAG — 7× in this paper · explained in 3 episodes
• Robustness — 7× in this paper · explained in 5 episodes
• Grounding — 5× in this paper · explained in 3 episodes
• Provenance — 4× in this paper · explained in 3 episodes
• Commentary — 3× in this paper · explained in 2 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Model Drift — 2× in this paper · explained in 4 episodes
• Multi-hop Reasoning — 2× in this paper · explained in 3 episodes
• Scaffolding — 2× in this paper · explained in 3 episodes
• Technical University of Munich — 2× in this paper
• Adam — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Ludwig Maximilian University of Munich — 1× in this paper

Sources

• Legal RAG Bench: an end-to-end benchmark for legal RAG
• The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs
• GreekBarBench: A Challenging Benchmark for Free-Text Legal Reasoning and Citations
• Better Call CLAUSE: A Discrepancy Benchmark for Auditing LLMs Legal Reasoning Capabilities
• LEXam: Benchmarking Legal Reasoning on 340 Law Exams
• AI for Statutory Simplification: A Comprehensive State Legal Corpus and Labor Benchmark
• LLM Evaluators Recognize and Favor Their Own Generations
• Ready Jurist One: Benchmarking Language Agents for Legal Intelligence in Dynamic Environments
• LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain
• PLawBench: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice
• BERTScore: Evaluating Text Generation with BERT

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering