Pith. sign in

REVIEW 7 cited by

Fino1: On the Transferability of Reasoning-Enhanced LLMs and Reinforcement Learning to Finance

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.08127 v3 pith:RXGFDHZJ submitted 2025-02-12 cs.CL

Lingfei Qian , Weipeng Zhou , Yan Wang , Xueqing Peng , Han Yi , Yilun Zhao , Jimin Huang , Qianqian Xie
show 1 more author
Jian-yun Nie
This is my paper · ORCID
classification cs.CL
keywords reasoningmodelsfinancialfinancefirstllmsbenchmarksbuilding
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

As the fundamental capability behind decision-making in finance, financial reasoning poses distinct challenges for LLMs. Although reinforcement learning (RL) have boosted generic reasoning, the progress in finance is hindered by the absence of empirical study of building effective financial chain-of-thought (CoT) corpus, a systematic comparison of different RL methods, and comprehensive benchmarks. To address these gaps, we introduce FinCoT, the first open high-fidelity CoT corpus for finance, distilled from seven QA datasets by a novel three-stage pipeline that incorporates domain supervision, iterative LLM refinement, and difficulty-aware filtering. Based on FinCoT, we develop Fin-o1, the first open financial reasoning models trained via supervised fine-tuning and GRPO-based RL. Our models outperform existing financial reasoning models and SOTA general models such as GPT-o1, DeepSeek-R1, and GPT-4.5. We also investigate the effectiveness of three different RL methods in improving domain-specific reasoning, offering the first such empirical study. We finally propose FinReason, the first financial reasoning benchmark covering multi-table analysis, long-context reasoning, and equation-based tasks, and evaluate 29 LLMs. Our extensive experiments reveal general reasoning models excel on standard benchmarks yet exhibit obvious performance degradation in financial contexts; even finance-tuned models like Dianjin-R1 and FinR1 degrade on lengthy documents. In contrast, our Fin-o1 models consistently outperform their backbones and larger GPT-o1 and DeepSeek-R1, confirming the effectiveness of our data building and model training strategy. Our study further shows that GRPO yields reliable gains whereas PPO and DPO do not, highlighting the need for targeted data and optimisation rather than scale alone.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Fin-RATE: A Real-world Financial Analytics and Tracking Evaluation Benchmark for LLMs on SEC Filings

    cs.CE 2026-02 conditional novelty 6.0 of 10

    A 7,500-question SEC-filing benchmark with a 13-type error taxonomy shows LLM accuracy falls by 14–19 points when reasoning moves from single documents to cross-company or multi-year tasks.

  2. VerIF: Verification Engineering for Reinforcement Learning in Instruction Following

    cs.CL 2025-06 conditional novelty 6.0 of 10

    A hybrid verifier that combines rule-based code checks and a reasoning-LLM judge enables reinforcement learning to improve LLM instruction following on several benchmarks.

  3. Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs

    cs.AI 2025-05 conditional novelty 6.0 of 10

    Post-training an LLM on economic reasoning problems improves accuracy on economic benchmarks and, without game-specific training, raises its Nash equilibrium frequency and win rates in strategic games.

  4. DataPrep-Bench: Benchmarking LLMs as Training Data Preparators

    cs.LG 2026-05 conditional novelty 5.0 of 10

    DataPrep-Bench jointly benchmarks data construction and data-quality evaluation for LLMs across six domains with downstream fine-tuning performance as ground truth.

  5. Agentar-Fin-R1: Enhancing Financial Intelligence through Domain Expertise, Training Efficiency, and Advanced Reasoning

    cs.CL 2025-07 conditional novelty 5.0 of 10

    Agentar-Fin-R1, an 8B and 32B financial LLM family, reports top scores on FinEval, FinanceIQ, and a new Finova benchmark while keeping general reasoning near its Qwen3 base.

  6. RoT: Enhancing Table Reasoning with Iterative Row-Wise Traversals

    cs.CL 2025-05 conditional novelty 5.0 of 10

    A training-free row-wise traversal prompt improves table question answering accuracy over long-CoT reasoning models on WikiTableQuestions and TableBench.

  7. Assessing the Capabilities and Limitations of FinGPT Model in Financial NLP Applications

    cs.CL 2025-07 reject novelty 3.0 of 10

    FinGPT matches GPT-4 on financial sentiment and headline classification, lags on QA and NER, and shows a bullish bias in stock movement prediction.

Pith tools