用轻量模型+文档检索，让AI搞定印度会计复杂题
Retrieval-Augmented Reasoning for Chartered Accountancy
- 用140亿参数的4比特量化模型结合文档结构保留提取技术
- 在多层级会计考试数据集上达到GPT-4o 68.75%的准确率
- 适合资源受限环境下需高可靠性的财务智能应用
大型语言模型（LLMs）虽推动了金融领域AI应用，但在印度注册会计师（CA）这类需跨领域知识与多步计算的任务中仍不可靠。模型在处理涉及法律条文和复杂计算的任务时表现不佳，且大规模部署在资源有限场景下不现实。本文提出CA-ThinkFlow，一个参数高效的检索增强生成（RAG）框架，基于140亿参数、4比特量化推理模型14B-DeepSeek-R1与布局感知的Docling文档提取系统，保持原文档结构。该框架采用基础RAG方法自动将检索信息注入提示词，并依赖模型内置链式思维（CoT）功能生成上下文与答案。在多层级CA-Ben基准测试中，其表现达到大模型水平，取得68.75%的学术可靠性系数（SRC），相当于GPT-4o与Claude 3.5 Sonnet的水平。系统在参数效率与性能间取得平衡，但对税收等领域的复杂法规文本仍缺乏深层理解能力。
原文摘要 · Abstract (English)
The inception of Large Language Models (LLMs) has catalyzed AI adoption in the finance sector, yet their reliability in complex, jurisdiction-specific tasks like Indian Chartered Accountancy (CA) remains limited. The models display difficulty in executing numerical tasks which require multiple steps while also needing advanced knowledge about legal regulations and the method of scaling their operations is not feasible in settings which have limited access to resources. We present CA-ThinkFlow as a parameter-efficient Retrieval-Augmented Generation (RAG) framework which operates with a 14B, 4-bit-quantized reasoning model, 14B-DeepSeek-R1, and a layout-aware Docling extraction system which maintains document structure during extraction. CA-ThinkFlow uses a basic RAG method which automatically adds retrieved information into the prompt, while it depends on the model's built-in Chain-of-Thought (CoT) functions to create context and produce correct answers. The system we developed system operates at performance levels which match large proprietary models when we tested it on the multi-level CA-Ben benchmark, achieving Scholastic Reliability Coefficient (SRC) results which equal 68.75\% of GPT-4o and Claude 3.5 Sonnet. The framework shows high efficiency and strength in handling parameters, but essential reasoning abilities fail to process complex regulatory texts which exist in fields such as Taxation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。