BENCHCOMPASS: From Scores to Signals for Training and Harness Decisions in Payment-Domain LLMs

2026-09-16

AI Summary

为了解决支付领域大语言模型的应用问题，本文提出了BENCHCOMPASS基准测试，通过构建基于场景的任务和质量检查来评估模型处理支付规则、证据利用及鲁棒性。

Abstract

Payment operations are a critical financial infrastructure, but the value of large language models in this domain remains unclear because payment rules change quickly, evidence is fragmented, and decisions depend on transaction state, participant role, region, and payment rail. Existing benchmarks do not isolate whether failures come from missing payment-rule knowledge, poor use of supplied evidence, or brittleness under imperfect harness inputs. We introduce BENCHCOMPASS, a payment-domain benchmark whose construction pipeline builds scenario-grounded tasks from typed evidence packs, applies LLM-based quality checks, creates task-input attack variants, and reserves final item admission for domain experts. The release contains an expert-reviewed Pro benchmark covering payment knowledge, context-grounded scenario reasoning, and Attacked Open robustness, plus a lower-assurance Normal pool for inspection and future curation. Across 16 model variants, BENCHCOMPASS shows qualitatively different failure modes: missing parametric payment knowledge, incomplete reasoning over supplied rules, and failure to reject plausible but invalid workflows. The benchmark remains unsaturated: the best frontier model reaches 89.6% on Open Context-Grounded Reasoning and 81.7% under attacked inputs, while a representative 32B open-weight model reaches 69.8% and 42.6%. Benchmark data and code are available at https://github.com/ant-intl/BenchCompass.

Problem

• payment-domain
• large language models
• benchmark
• payment rules
• evidence

Innovation

• BENCHCOMPASS
• payment-domain benchmark
• LLM-based quality checks
• task-input attack variants
• context-grounded scenario reasoning