Skip to content

From Documents to Reasoning: A Validated Synthetic Data Pipeline and Semantic-Aware Fine-Tuning for Financial Numerical Reasoning

Aug 2026 · 0 citations · 21 references
Computer Science

TL;DR

This work proposes a comprehensive pipeline for improving financial QA systems through high-quality synthetic data generation and fine-tuning of smaller language models (SLMs) using Quantized Low-Rank Adaptation (QLoRA).

Abstract

Financial question answering (QA) has emerged as a key benchmark for evaluating the performance of Large Language Models (LLMs) on domain-specific tasks involving complex data formats such as tables, charts, and rich textual narratives. While recent advancements have enabled models to reason across modalities and perform multi-step arithmetic operations, limitations remain in performance consistency, and evaluation reliability. In particular, standard evaluation metrics like Exact Match (EM) often fail to account for minor variations such as differences in units or formats, misleading performance assessments. In this work, we propose a comprehensive pipeline for improving financial QA systems through high-quality synthetic data generation and fine-tuning of smaller language models (SLMs) using Quantized Low-Rank Adaptation (QLoRA). Our pipeline includes aggressive data validation for synthetic question answer generation to ensure the relevance and correctness of synthetic question-answer pairs. We introduce a novel evaluation metric that matches answers computed from arithmetic expressions rather than ground-truth answers; providing a more accurate reflection of model reasoning capability. Furthermore, we propose a modified loss function that aligns predicted and reference expressions using semantic similarity, our novel evaluation metric and standard cross-entropy, resulting in improved performance. Experimental results on benchmark datasets, ConvFinQA demonstrate significant gains in QA accuracy after fine-tuning using synthetic dataset and proposed loss function.

View source

Similar papers

Augmenting Datasets for Fine-Tuning Large Language Models Using Semantic Variations

This study explores a semantic variation methodology to augment training data by generating question-answer pairs with explicit control over semantic similarity, and shows that semantically controlled augmentation improves domain-specific knowledge acquisition while preserving consistency.

Alexander Chen, Caroline Tang, Jennifer Sleeman · 0 citations
Conference Jul 2026

Lightweight reasoning models for NER

Lite-CoNER is proposed, a lightweight NER framework that achieves an effective balance between recognition accuracy and inference efficiency and provides a transparent view of the decision-making process, proving that lightweight models can effectively inherit complex logic through structured distillation.

Yang Wang, Lushuang Gao · 0 citations
Preprint Jul 2026

Gold-Guided Programmatic Distillation for Financial Reasoning over Hybrid Tables and Text

Financial question answering over hybrid tabular and textual data may require multi-source reasoning and precise numerical computation. While large language models (LLMs) can generate intermediate reasoning steps, natural-language rationales remain prone to arithmetic errors, making them an unreliable supervision source for distillation. Building on programmatic distillation, we develop an approach that transfers reliable numerical reasoning from a large teacher model to a compact student using execution-verified Python programs instead of free-form textual rationales. It leverages gold derivations to guide teacher-side program synthesis and retains only programs that execute correctly and produce the gold answer, ensuring high-quality supervision. We further introduce an iterative recovery stage that revisits teacher-failed examples, enabling the student to recover and incorporate newly verified programs into training. Experiments on TAT-QA show that our framework is highly effective for hybrid financial reasoning. Our best 7B student achieves 87.00 EM / 87.18 F1 on the test set, substantially outperforming the 72B teacher (78.46 EM) as well as traditional and strong LLM-based baselines, including TAGOP and TAT-LLM. These results demonstrate that execution-verified programmatic distillation provides an effective and extensible framework for training smaller models to perform reliable numerical reasoning.

Yunfang Dong, Erica Zhao, Elana Chen · 0 citations
Book Open access Aug 2026

AutoDavis: Automatic and Dynamic Evaluation Protocol of Large Vision-Language Models on Visual Question-Answering

AutoDavis is introduced, a first-of-its-kind automatic and dynamic evaluation protocol that enables on-demand benchmarking of LVLMs across specific capability dimensions and shows effectiveness and reliability, offering a new paradigm for dynamic benchmarking of multimodal intelligence.

Han Bao, Yue Huang, Yanbo Wang et al. · 0 citations
Open access Jul 2026

GradeSQL: Outcome reward models for intelligent Text-to-SQL generation from LLMs

As Large Language Models (LLMs) become foundational to next-generation Intelligent Information Systems, the bridge between natural language interfaces and structured database systems remains a critical bottleneck. While Text-to-SQL generation enables cooperative support for complex query formulation, ensuring the reliability of these generated queries at inference time is a central challenge. Conventional methods rely on coarse execution-based signals, which may limit their ability to capture the nuanced semantic alignment required for high-stakes database environments. In this work, we propose the use of Outcome Reward Models (ORMs) as a fine-grained, probabilistic feedback mechanism for test-time verification in Text-to-SQL tasks. We introduce GradeSQL, a framework for training task-specific ORMs that assign scalar utility scores to candidate SQL queries based on their semantic correctness and alignment with database schema. Our approach is evaluated on the BIRD and Spider benchmarks across multiple open-source LLM families. Experimental results demonstrate that ORM-based verification consistently outperforms traditional execution-based heuristics.

M. Tritto, G. Farano, Dario Di Palma et al. · 2 citations
Book Open access Jun 2025

TReB: A Comprehensive Benchmark for Evaluating Table Reasoning Capabilities of Large Language Models

The majority of data in businesses and industries is stored in tables, databases, and data warehouses. Reasoning with table-structured data poses significant challenges for large language models (LLMs) due to its hidden semantics, inherent complexity, and structured nature. One of these challenges is lacking an effective evaluation benchmark fairly reflecting the performances of LLMs on broad table reasoning abilities. In this paper, we fill in this gap by presenting a comprehensive table reasoning benchmark, TReB. Firstly, we propose a taxonomy to systematically measure both shallow table understanding abilities and deep table reasoning abilities, covering a total of 26 sub-tasks. We then construct a high quality dataset through a dedicated data processing and synthesis procedure. Based on these well-constructed samples, we design an evaluation framework to robustly measure table reasoning capabilities with three distinct inference modes. Experimental results with our data and framework reveal that existing LLMs still have significant room for improvement in addressing the complex and real world table related tasks. Both the dataset and evaluation framework are publicly available, with the dataset hosted on huggingface.co/datasets/JT-LM/JIUTIAN-TReB, and the framework on github.com/JT-LM/jiutian-treb.

Ce Li, Xiaofan Liu, Zhiyan Song et al. · 3 citations

Related blog posts