Are the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon Statements

• URL: http://arxiv.org/abs/2607.28661v1
• Date: Wed, 22 Jul 2026 06:53:07 GMT
• Title: Are the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon Statements
• Abstract summary: FinIndices is a large-scale benchmark evaluating data-processing fidelity over uncropped financial statements.<n>Our evaluation reveals two severe LLM vulnerabilities. First, a "Knowledge Bottleneck": despite memorizing formulas during pre-training, models demonstrate fragile pattern matching.<n>Second, a " Structural Bottleneck": the intense cognitive load of generating multi-metric, multi-period tables actively drains reasoning capacity.
• Score: 33.97676862545625
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Do Large Language Models (LLMs) possess genuine structural reasoning, or merely rely on surface-level pattern matching? The financial domain, demanding numerical precision and multi-step logic over long contexts, is an ideal testbed. Existing benchmarks fail to capture real-world industrial complexity, predominantly relying on multiple-choice questions or single-hop QA over cropped tables while ignoring intricate cross-statement dynamics and temporal de-cumulation. To bridge this gap, we introduce FinIndices, a large-scale benchmark evaluating data-processing fidelity over uncropped financial statements (up to 32K tokens). Utilizing an automated synthesis pipeline with adversarial traps, FinIndices encompasses Single-Index computation and Table-Index tabulation to test complex domain, temporal, and caliber reasoning. Our evaluation reveals two severe LLM vulnerabilities. First, a "Knowledge Bottleneck": despite memorizing formulas during pre-training, models demonstrate fragile pattern matching. Removing explicit formula hints causes performance to collapse (e.g., Gemini-3.1-Pro drops from 70.70% to 38.22% on table tasks), exposing fatal flaws in temporal de-cumulation and stock-flow caliber mismatch. Second, a "Structural Bottleneck": the intense cognitive load of generating multi-metric, multi-period tables actively drains reasoning capacity. Under structural pressure, LLMs that flawlessly execute isolated derivations regress to shallow heuristics, such as fetching incorrect adjacent columns or substituting deep accounting adjustments with lazy literal arithmetic. Finally, Supervised Fine-Tuning (SFT) yields substantial zero-hint gains (+8.54% Single, +3.82% Table), validating that structured logic can be partially restored via data-centric alignment.

Related papers

• Imbuing Large Language Models with Bidirectional Logic for Robust Chain Repair [44.80087038178069]
  We introduce Teleological Reasoning Infilling (TRI), a training framework that endows decoder-only transformers with a native emphgoal-conditioned bridging capability.<n>At inference, TRI operates as a surgical repair module within a dual-system loop.<n>Experiments on three benchmarks demonstrate that TRI achieves state-of-the-art performance across all tasks, while reducing per-problem token expenditure by 31.2%.
  arXiv  Detail & Related papers  (2026-06-03T15:58:48Z)
• A2RBench: An Automatic Paradigm for Formally Verifiable Abstract Reasoning Benchmark Generation [59.98516959731531]
  Abstract reasoning ability reflects intelligence and capacity of LLMs to extract and apply abstract rules.<n>Existing benchmarks either rely on expensive manual annotation, limiting their scale, or risk measuring memorization rather than genuine reasoning.<n>We introduce an automated pipeline named A2RBench, encompassing generation, expansion, evaluation, and analysis.
  arXiv  Detail & Related papers  (2026-05-17T06:14:20Z)
• TopBench: A Benchmark for Implicit Prediction and Reasoning over Tabular Question Answering [80.93487993878836]
  A common class of real-world queries is implicitly predictive, requiring the inference of unobserved answers from historical patterns rather than mere retrieval.<n>These queries introduce two challenges: recognizing latent intent and reliable predictive reasoning over massive tables.<n>We introduce TopBench, a benchmark consisting of 779 samples across four sub-tasks, ranging from single-point prediction to decision making, treatment effect analysis, and complex reasoning.
  arXiv  Detail & Related papers  (2026-04-30T16:22:51Z)
• How LLMs Fail and Generalize in RTL Coding for Hardware Design? [56.361436215029045]
  We introduce a new error taxonomy grounded in problem solvability, inspired by cognitive theory.<n>Our taxonomy categorizes failures into syntactic, semantic, solvable functional, and unsolvable functional types.
  arXiv  Detail & Related papers  (2026-04-26T14:34:49Z)
• Dynamic analysis enhances issue resolution [53.50448142467294]
  DAIRA (Dynamic Analysis-enhanced Issue Resolution Agent) is an automated repair framework that embeds dynamic analysis into the agent's reasoning cycle.<n> Driven by a Test Tracing-Driven methodology, DAIRA utilizes lightweight monitors to extract critical runtime data.<n>When powered by Gemini 3 Flash Preview, DAIRA establishes a new state-of-the-art (SOTA) performance, achieving a 79.4% resolution rate on the SWE-bench Verified dataset.
  arXiv  Detail & Related papers  (2026-03-23T14:48:54Z)
• TableMind++: An Uncertainty-Aware Programmatic Agent for Tool-Augmented Table Reasoning [44.20336483508951]
  Table reasoning requires models to jointly perform semantic understanding and precise numerical operations.<n>To address these limitations, we previously proposed TableMind as a tuning-based autonomous programmatic agent.<n>We extend this foundation to TableMind++ by introducing a novel uncertainty-aware inference framework.
  arXiv  Detail & Related papers  (2026-03-08T08:31:33Z)
• CMT-Bench: Cricket Multi-Table Generation Benchmark for Probing Robustness in Large Language Models [11.167804698594866]
  We present CMT-Bench, a diagnostic benchmark built from live cricket commentary.<n>We find large drops without extractive summaries, monotonic degradation with input length, and consistent accuracy drop under entity-form changes.
  arXiv  Detail & Related papers  (2025-10-20T23:51:28Z)
• seqBench: A Tunable Benchmark to Quantify Sequential Reasoning Limits of LLMs [1.0519693622157462]
  We introduce seqBench, a benchmark for probing sequential reasoning limits in Large Language Models (LLMs)<n>We find that even top-performing models systematically fail on seqBench's structured reasoning tasks despite minimal search complexity.
  arXiv  Detail & Related papers  (2025-09-21T01:32:13Z)
• LLM-Symbolic Integration for Robust Temporal Tabular Reasoning [69.27153114778748]
  We introduce TempTabQA-C, a synthetic dataset designed for systematic and controlled evaluations.<n>This structured approach allows Large Language Models (LLMs) to generate and executesql queries, enhancing generalization and mitigating biases.
  arXiv  Detail & Related papers  (2025-06-06T05:14:04Z)
• Fractured Chain-of-Thought Reasoning [61.647243580650446]
  We introduce Fractured Sampling, a unified inference-time strategy that interpolates between full CoT and solution-only sampling.<n>We show that Fractured Sampling consistently achieves superior accuracy-cost trade-offs, yielding steep log-linear scaling gains in Pass@k versus token budget.
  arXiv  Detail & Related papers  (2025-05-19T11:30:41Z)
• DCR: Divide-and-Conquer Reasoning for Multi-choice Question Answering with LLMs [9.561022942046279]
  We propose Divide and Conquer Reasoning (DCR) to enhance the reasoning capability of large language models (LLMs) We first categorize questions into two subsets based on confidence score ($mathcalCS$), which is estimated by statistical frequency of generated answers. In particular, we first categorize questions into two subsets based on confidence score ($mathcalCS$), which is estimated by statistical frequency of generated answers.
  arXiv  Detail & Related papers  (2024-01-10T14:38:46Z)

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.