Pith. sign in

REVIEW 8 cited by

DianJin-R1: Evaluating and Enhancing Financial Reasoning in Large Language Models

Not yet reviewed by Pith; the record is open.

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 2504.15716 v1 pith:AJCSE3NB submitted 2025-04-22 cs.AI

DianJin-R1: Evaluating and Enhancing Financial Reasoning in Large Language Models

classification cs.AI
keywords reasoningfinancialmodelsdianjin-r1compliancelearningstructuredb-instruct
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Effective reasoning remains a core challenge for large language models (LLMs) in the financial domain, where tasks often require domain-specific knowledge, precise numerical calculations, and strict adherence to compliance rules. We propose DianJin-R1, a reasoning-enhanced framework designed to address these challenges through reasoning-augmented supervision and reinforcement learning. Central to our approach is DianJin-R1-Data, a high-quality dataset constructed from CFLUE, FinQA, and a proprietary compliance corpus (Chinese Compliance Check, CCC), combining diverse financial reasoning scenarios with verified annotations. Our models, DianJin-R1-7B and DianJin-R1-32B, are fine-tuned from Qwen2.5-7B-Instruct and Qwen2.5-32B-Instruct using a structured format that generates both reasoning steps and final answers. To further refine reasoning quality, we apply Group Relative Policy Optimization (GRPO), a reinforcement learning method that incorporates dual reward signals: one encouraging structured outputs and another rewarding answer correctness. We evaluate our models on five benchmarks: three financial datasets (CFLUE, FinQA, and CCC) and two general reasoning benchmarks (MATH-500 and GPQA-Diamond). Experimental results show that DianJin-R1 models consistently outperform their non-reasoning counterparts, especially on complex financial tasks. Moreover, on the real-world CCC dataset, our single-call reasoning models match or even surpass the performance of multi-agent systems that require significantly more computational cost. These findings demonstrate the effectiveness of DianJin-R1 in enhancing financial reasoning through structured supervision and reward-aligned learning, offering a scalable and practical solution for real-world applications.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

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

  1. VertMark: A Unified Training-Free Robust Watermarking Framework for Vertical Domain Pre-trained Language Models

    cs.CR 2026-05 unverdicted novelty 7.0

    VertMark embeds robust, training-free watermarks into vertical domain language models by creating hidden semantic equivalence between low-frequency triggers and high-frequency domain terms via parameter swaps, support...

  2. CLExEval: A Human-in-the-Loop Framework for Qualitative Evaluation of LLM Clinical Reasoning

    cs.CL 2026-06 unverdicted novelty 6.0

    CLExEval introduces a human-annotated evaluation framework on 40 rare cases that identifies verbosity bias, hidden knowledge paradox, and 68.6% reasoning-to-output mismatch in LLMs while showing LLM-as-a-Judge overest...

  3. FinReasoning: A Hierarchical Benchmark for Reliable Financial Research Reporting

    cs.CL 2026-02 unverdicted novelty 6.0

    FinReasoning is a hierarchical benchmark that decomposes LLM financial research capabilities into semantic consistency, data alignment, and deep insight, revealing model-type differences in auditing versus insight generation.

  4. Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models

    cs.CL 2025-08 unverdicted novelty 6.0

    Fin-PRM is a domain-specialized process reward model that supplies binary step-level and trajectory-level supervision signals for financial reasoning in LLMs and outperforms general PRMs on CFLUE and FinQA benchmarks.

  5. LLM Evolution as an Industry-Scale Ecosystem: A Lifecycle Perspective on Continual Learning

    cs.LG 2026-06 unverdicted novelty 5.0

    The paper reformulates industrial continual learning for LLMs as a closed-loop ecosystem problem, identifies three core challenges, and organizes solutions around five lifecycle design principles.

  6. YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition

    cs.CL 2026-06 unverdicted novelty 5.0

    YouZhi-LLM applies a layer-adaptive GQA-to-MLA transition plus Ascend-specific distillation and fine-tuning to reduce KV-cache size, yielding up to 2.69× higher concurrency and modest gains on financial benchmarks ver...

  7. Reasoning through Verifiable Forecast Actions: Consistency-Grounded RL for Financial LLMs

    cs.LG 2026-05 unverdicted novelty 5.0

    StockR1 unifies LLM-based financial reasoning and time-series forecasting by emitting verifiable forecast actions that condition a decoder, optimized via consistency-grounded RL to improve accuracy on QA and prediction tasks.

  8. PubSwap: Public-Data Off-Policy Coordination for Federated RLVR

    cs.LG 2026-04 unverdicted novelty 5.0

    PubSwap uses a small public dataset for selective off-policy response swapping in federated RLVR to improve coordination and performance over standard baselines on math and medical reasoning tasks.