# FinBalance: A Multi-Document Accounting Reconciliation Benchmark

arXiv: https://arxiv.org/abs/2606.15949 · HTML: https://mlsanity.com/paper/2606.15949/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 20 references that are in the map.
- First posted on arXiv 14 Jun 2026.

## Builds on (most cited first, 18 of 18)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [FinQA: A Dataset of Numerical Reasoning over Financial Data](https://mlsanity.com/paper/2109.00122/) (2021)
- [TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance](https://mlsanity.com/paper/2105.07624/) (2021)
- [FinanceBench: A New Benchmark for Financial Question Answering](https://mlsanity.com/paper/2311.11944/) (2023)
- [ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering](https://mlsanity.com/paper/2210.03849/) (2022)
- [MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data](https://mlsanity.com/paper/2206.01347/) (2022)
- [DocFinQA: A Long-Context Financial Reasoning Dataset](https://mlsanity.com/paper/2401.06915/) (2024)
- [FinanceMath: Knowledge-Intensive Math Reasoning in Finance Domains](https://mlsanity.com/paper/2311.09797/) (2023)
- [FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark for Evaluating LLMs](https://mlsanity.com/paper/2510.08886/) (2025)
- [FinDABench: Benchmarking Financial Data Analysis Ability of Large Language Models](https://mlsanity.com/paper/2401.02982/) (2024)
- [FinMaster: A Holistic Benchmark for Mastering Full-Pipeline Financial Workflows with LLMs](https://mlsanity.com/paper/2505.13533/) (2025)
- [FinRule-Bench: A Benchmark for Joint Reasoning over Financial Tables and Principles](https://mlsanity.com/paper/2603.11339/) (2026)

## Built on by (most cited first, 3 of 3)

- [FinalityBench: An Effect-Level Benchmark for Agent Decisions Under Delayed and Conflicting Financial Finality](https://mlsanity.com/paper/2609.04706/) (2026)
- [FinRCA-Bench: Benchmarking Evidence Retrieval and Reasoning for Financial AI Systems](https://mlsanity.com/paper/2608.18534/) (2026)
- [Crypto Accounting Bench: Evaluating Frontier and Open-Weight Models on Crypto-Asset Accounting Tasks](https://mlsanity.com/paper/2609.14811/) (2026)

## Abstract (arXiv)

Existing financial-NLP benchmarks mostly evaluate prepared artifacts such as filings, tables, or extracted values. Real accounting begins earlier: source documents must be reconciled into cited journal entries, aggregated into a balance sheet, and checked for contradictions. We introduce FinBalance, a multi-document accounting reconciliation benchmark built from source-document bundles across eight industries, three period types, and five difficulty levels. Human-authored business scenarios, accounting policies, tax/FX treatments, document schemas, distractors, and inconsistency templates are composed by a deterministic generator whose ledger produces journal entries,balance sheets, and 23 inconsistency-code labels. On a 710-record evaluation split, six contemporary LLMs reach at most 46% exact final-balance-sheet accuracy. Four models show a 26-41 pp gap between BS_exact, the model's reported balance sheet, and BS_recon, the balance sheet obtained by replaying its entries through our ledger. Models often recover numerically plausible entries but fail to bind them to supporting documents and aggregate them consistently. Citation-pressure prompting barely changes document-linking errors, while ledger-feedback ablations substantially improve reported balance sheets and expose inconsistency-detection trade-offs. Expert finance reviewers validate the benchmark design and labels.