SAHM: A Benchmark for Arabic Financial and Shari'ah-Compliant Reasoning

• URL: http://arxiv.org/abs/2604.19098v1
• Date: Tue, 21 Apr 2026 05:24:08 GMT
• Title: SAHM: A Benchmark for Arabic Financial and Shari'ah-Compliant Reasoning
• Abstract summary: We introduce SAHM, a document-grounded benchmark and instruction-tuning dataset for Arabic financial NLP and Shari'ah-compliant reasoning.<n> SAHM contains 14,380 expert-verified instances spanning seven tasks: AAOIFI standards QA, fatwa-based QA/MCQ, accounting and business exams, financial sentiment analysis, extractive summarization, and event-cause reasoning.<n>We find that Arabic fluency does not reliably translate to evidence-grounded financial reasoning.
• Score: 59.20983102634086
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: English financial NLP has progressed rapidly through benchmarks for sentiment, document understanding, and financial question answering, while Arabic financial NLP remains comparatively under-explored despite strong practical demand for trustworthy finance and Islamic-finance assistants. We introduce SAHM, a document-grounded benchmark and instruction-tuning dataset for Arabic financial NLP and Shari'ah-compliant reasoning. SAHM contains 14,380 expert-verified instances spanning seven tasks: AAOIFI standards QA, fatwa-based QA/MCQ, accounting and business exams, financial sentiment analysis, extractive summarization, and event-cause reasoning, curated from authentic regulatory, juristic, and corporate sources. We evaluate 19 strong open and proprietary LLMs using task-specific metrics and rubric-based scoring for open-ended outputs, and find that Arabic fluency does not reliably translate to evidence-grounded financial reasoning: models are substantially stronger on recognition-style tasks than on generation and causal reasoning, with the largest gaps on event-cause reasoning. We release the benchmark, evaluation framework, and an instruction-tuned model to support future research on trustworthy Arabic financial NLP.

Related papers

• FINESSE-Bench: A Hierarchical Benchmark Suite for Financial Domain Knowledge and Technical Analysis in Large Language Models [0.33504916505452914]
  FINESSE-Bench is a suite of eight specialized benchmarks comprising 3,993 questions for hierarchical evaluation of financial competencies in large language models.<n>We describe a unified evaluation protocol covering multiple-choice questions, numerical answers, and short open-ended responses.
  arXiv  Detail & Related papers  (2026-05-14T23:53:51Z)
• FinTrust: A Comprehensive Benchmark of Trustworthiness Evaluation in Finance Domain [54.06289302468199]
  FinTrust is a benchmark specifically designed for evaluating the trustworthiness of LLMs in finance applications.<n> proprietary models like o4-mini outperforms in most tasks such as safety.<n>Open-source models like DeepSeek-V3 have advantage in specific areas like industry-level fairness.
  arXiv  Detail & Related papers  (2025-10-17T01:45:49Z)
• FinLFQA: Evaluating Attributed Text Generation of LLMs in Financial Long-Form Question Answering [57.43420753842626]
  FinLFQA is a benchmark designed to evaluate the ability of Large Language Models to generate long-form answers to complex financial questions.<n>We provide an automatic evaluation framework covering both answer quality and attribution quality.
  arXiv  Detail & Related papers  (2025-10-07T20:06:15Z)
• Finance Language Model Evaluation (FLaME) [5.904572835181286]
  Language Models (LMs) have demonstrated impressive capabilities with core Natural Language Processing (NLP) tasks.<n>We present the first holistic benchmarking suite for Financial Language Model Evaluation (FLaME)<n>We are the first research paper to comprehensively study LMs against'reasoning-reinforced' LMs.
  arXiv  Detail & Related papers  (2025-06-18T19:54:33Z)
• KFinEval-Pilot: A Comprehensive Benchmark Suite for Korean Financial Language Understanding [6.3604109210772934]
  KFinEval-Pilot is a benchmark suite specifically designed to evaluate large language models (LLMs) in the Korean financial domain.<n>It comprises over 1,000 curated questions across three critical areas: financial knowledge, legal reasoning, and financial toxicity.
  arXiv  Detail & Related papers  (2025-04-17T00:12:58Z)
• FinanceQA: A Benchmark for Evaluating Financial Analysis Capabilities of Large Language Models [0.0]
  FinanceQA is a testing suite that evaluates LLMs' performance on complex numerical financial analysis tasks that mirror real-world investment work.<n>Current LLMs fail to meet the strict accuracy requirements of financial institutions, with models failing approximately 60% of realistic tasks.<n>Results show that higher-quality training data is needed to support such tasks, which we experiment with using OpenAI's fine-tuning API.
  arXiv  Detail & Related papers  (2025-01-30T00:06:55Z)
• CFinBench: A Comprehensive Chinese Financial Benchmark for Large Language Models [61.324062412648075]
  CFinBench is an evaluation benchmark for assessing the financial knowledge of large language models (LLMs) under Chinese context. It comprises 99,100 questions spanning 43 second-level categories with 3 question types: single-choice, multiple-choice and judgment. The results show that GPT4 and some Chinese-oriented models lead the benchmark, with the highest average accuracy being 60.16%.
  arXiv  Detail & Related papers  (2024-07-02T14:34:36Z)
• FinBen: A Holistic Financial Benchmark for Large Language Models [75.09474986283394]
  FinBen is the first extensive open-source evaluation benchmark, including 36 datasets spanning 24 financial tasks. FinBen offers several key innovations: a broader range of tasks and datasets, the first evaluation of stock trading, novel agent and Retrieval-Augmented Generation (RAG) evaluation, and three novel open-source evaluation datasets for text summarization, question answering, and stock trading.
  arXiv  Detail & Related papers  (2024-02-20T02:16:16Z)
• BizBench: A Quantitative Reasoning Benchmark for Business and Finance [7.4673182865000225]
  BizBench is a benchmark for evaluating models' ability to reason about realistic financial problems. We include three financially-themed code-generation tasks from newly collected and augmented QA data. These tasks evaluate a model's financial background knowledge, ability to parse financial documents, and capacity to solve problems with code.
  arXiv  Detail & Related papers  (2023-11-11T16:16:11Z)
• PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance [63.51545277822702]
  PIXIU is a comprehensive framework including the first financial large language model (LLMs) based on fine-tuning LLaMA with instruction data. We propose FinMA by fine-tuning LLaMA with the constructed dataset to be able to follow instructions for various financial tasks. We conduct a detailed analysis of FinMA and several existing LLMs, uncovering their strengths and weaknesses in handling critical financial tasks.
  arXiv  Detail & Related papers  (2023-06-08T14:20:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.