Large Language Models Acing Chartered Accountancy

• URL: http://arxiv.org/abs/2506.21031v1
• Date: Thu, 26 Jun 2025 06:10:37 GMT
• Title: Large Language Models Acing Chartered Accountancy
• Authors: Jatin Gupta, Akhil Sharma, Saransh Singhania, Mohammad Adnan, Sakshi Deo, Ali Imam Abidi, Keshav Gupta,
• Abstract summary: This paper introduces CA-Ben, a Chartered Accountancy benchmark specifically designed to evaluate the financial, legal, and quantitative reasoning capabilities of LLMs.<n>Six prominent LLMs i.e. GPT 4o, LLAMA 3.3 70B, LLAMA 3.1 405B, MISTRAL Large, Claude 3.5 Sonnet, and Microsoft Phi 4 were evaluated using standardized protocols.<n>Results indicate variations in performance, with Claude 3.5 Sonnet and GPT-4o outperforming others, especially in conceptual and legal reasoning.
• Score: 0.4711628883579317
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Advanced intelligent systems, particularly Large Language Models (LLMs), are significantly reshaping financial practices through advancements in Natural Language Processing (NLP). However, the extent to which these models effectively capture and apply domain-specific financial knowledge remains uncertain. Addressing a critical gap in the expansive Indian financial context, this paper introduces CA-Ben, a Chartered Accountancy benchmark specifically designed to evaluate the financial, legal, and quantitative reasoning capabilities of LLMs. CA-Ben comprises structured question-answer datasets derived from the rigorous examinations conducted by the Institute of Chartered Accountants of India (ICAI), spanning foundational, intermediate, and advanced CA curriculum stages. Six prominent LLMs i.e. GPT 4o, LLAMA 3.3 70B, LLAMA 3.1 405B, MISTRAL Large, Claude 3.5 Sonnet, and Microsoft Phi 4 were evaluated using standardized protocols. Results indicate variations in performance, with Claude 3.5 Sonnet and GPT-4o outperforming others, especially in conceptual and legal reasoning. Notable challenges emerged in numerical computations and legal interpretations. The findings emphasize the strengths and limitations of current LLMs, suggesting future improvements through hybrid reasoning and retrieval-augmented generation methods, particularly for quantitative analysis and accurate legal interpretation.

Related papers

• Advanced Financial Reasoning at Scale: A Comprehensive Evaluation of Large Language Models on CFA Level III [0.0]
  This paper presents a benchmark evaluating 23 state-of-the-art Large Language Models (LLMs) on the Chartered Financial Analyst (CFA) Level III exam.<n>We assess both multiple-choice questions (MCQs) and essay-style responses using multiple prompting strategies including Chain-of-Thought and Self-Discover.<n>Our evaluation reveals that leading models demonstrate strong capabilities, with composite scores such as 79.1% (o4-mini) and 77.3% (Gemini 2.5 Flash) on CFA Level III.
  arXiv  Detail & Related papers  (2025-06-29T19:54:57Z)
• Can Large Language Models Predict the Outcome of Judicial Decisions? [0.0]
  Large Language Models (LLMs) have shown exceptional capabilities in Natural Language Processing (NLP)<n>We benchmark state-of-the-art open-source LLMs, including LLaMA-3.2-3B and LLaMA-3.1-8B, under varying configurations.<n>Our results demonstrate that fine-tuned smaller models achieve comparable performance to larger models in task-specific contexts.
  arXiv  Detail & Related papers  (2025-01-15T11:32:35Z)
• GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation [108.2008975785364]
  Graph Inspired Veracity Extrapolation (GIVE) is a novel reasoning method that merges parametric and non-parametric memories to improve accurate reasoning with minimal external input.<n>GIVE guides the LLM agent to select the most pertinent expert data (observe), engage in query-specific divergent thinking (reflect), and then synthesize this information to produce the final output (speak)
  arXiv  Detail & Related papers  (2024-10-11T03:05:06Z)
• LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models [17.90483181611453]
  Large language models (LLMs) have made significant progress in natural language processing tasks and demonstrate considerable potential in the legal domain. Applying existing LLMs to legal systems without careful evaluation of their potential and limitations could pose significant risks in legal practice. We introduce a standardized comprehensive Chinese legal benchmark LexEval.
  arXiv  Detail & Related papers  (2024-09-30T13:44:00Z)
• 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)
• Large Language Model in Financial Regulatory Interpretation [0.276240219662896]
  This study explores the innovative use of Large Language Models (LLMs) as analytical tools for interpreting complex financial regulations. The primary objective is to design effective prompts that guide LLMs in distilling verbose and intricate regulatory texts. This novel approach aims to streamline the implementation of regulatory mandates within the financial reporting and risk management systems of global banking institutions.
  arXiv  Detail & Related papers  (2024-05-10T20:45:40Z)
• FoundaBench: Evaluating Chinese Fundamental Knowledge Capabilities of Large Language Models [64.11333762954283]
  This paper introduces FoundaBench, a pioneering benchmark designed to rigorously evaluate the fundamental knowledge capabilities of Chinese LLMs. We present an extensive evaluation of 12 state-of-the-art LLMs using FoundaBench, employing both traditional assessment methods and our CircularEval protocol to mitigate potential biases in model responses. Our results highlight the superior performance of models pre-trained on Chinese corpora, and reveal a significant disparity between models' reasoning and memory recall capabilities.
  arXiv  Detail & Related papers  (2024-04-29T01:49:07Z)
• Analyzing and Adapting Large Language Models for Few-Shot Multilingual NLU: Are We There Yet? [82.02076369811402]
  Supervised fine-tuning (SFT), supervised instruction tuning (SIT) and in-context learning (ICL) are three alternative, de facto standard approaches to few-shot learning. We present an extensive and systematic comparison of the three approaches, testing them on 6 high- and low-resource languages, three different NLU tasks, and a myriad of language and domain setups. Our observations show that supervised instruction tuning has the best trade-off between performance and resource requirements.
  arXiv  Detail & Related papers  (2024-03-04T10:48:13Z)
• 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)
• LLaMA Beyond English: An Empirical Study on Language Capability Transfer [49.298360366468934]
  We focus on how to effectively transfer the capabilities of language generation and following instructions to a non-English language. We analyze the impact of key factors such as vocabulary extension, further pretraining, and instruction tuning on transfer. We employ four widely used standardized testing benchmarks: C-Eval, MMLU, AGI-Eval, and GAOKAO-Bench.
  arXiv  Detail & Related papers  (2024-01-02T06:29:02Z)
• FinEval: A Chinese Financial Domain Knowledge Evaluation Benchmark for Large Language Models [31.961563103990432]
  This paper presents FinEval, a benchmark designed to evaluate LLMs' financial domain knowledge and practical abilities.<n>The dataset contains 8,351 questions categorized into four different key areas: Financial Academic Knowledge, Financial Industry Knowledge, Financial Security Knowledge, and Financial Agent.<n>Our results show that Claude 3.5-Sonnet achieves the highest weighted average score of 72.9 across all financial domain categories under zero-shot setting.
  arXiv  Detail & Related papers  (2023-08-19T10:38:00Z)
• CMMLU: Measuring massive multitask language understanding in Chinese [133.70911295934746]
  This paper introduces a comprehensive Chinese benchmark that covers various subjects, including natural science, social sciences, engineering, and humanities. CMMLU fills the gap in evaluating the knowledge and reasoning capabilities of large language models within the Chinese context.
  arXiv  Detail & Related papers  (2023-06-15T15:49:51Z)

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.