Pith. sign in

REVIEW 4 cited by

FinTral: A Family of GPT-4 Level Multimodal Financial Large Language Models

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 2402.10986 v3 pith:SXTFJDHD submitted 2024-02-16 cs.CL cs.AI

Gagan Bhatia , El Moatez Billah Nagoudi , Hasan Cavusoglu , Muhammad Abdul-Mageed This is my paper
classification cs.CLcs.AI
keywords fintralfinanciallargetasksanalysisdatasetsgithubgpt-4
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We introduce FinTral, a suite of state-of-the-art multimodal large language models (LLMs) built upon the Mistral-7b model and tailored for financial analysis. FinTral integrates textual, numerical, tabular, and image data. We enhance FinTral with domain-specific pretraining, instruction fine-tuning, and RLAIF training by exploiting a large collection of textual and visual datasets we curate for this work. We also introduce an extensive benchmark featuring nine tasks and 25 datasets for evaluation, including hallucinations in the financial domain. Our FinTral model trained with direct preference optimization employing advanced Tools and Retrieval methods, dubbed FinTral-DPO-T&R, demonstrates an exceptional zero-shot performance. It outperforms ChatGPT-3.5 in all tasks and surpasses GPT-4 in five out of nine tasks, marking a significant advancement in AI-driven financial technology. We also demonstrate that FinTral has the potential to excel in real-time analysis and decision-making in diverse financial contexts. The GitHub repository for FinTral is available at \url{https://github.com/UBC-NLP/fintral}.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

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

  1. CFBenchmark-MM: Chinese Financial Assistant Benchmark for Multimodal Large Language Model

    cs.CL 2025-06 conditional novelty 6.0 of 10

    A 9,356-pair Chinese multimodal financial benchmark reveals that state-of-the-art multimodal LLMs, including GPT-4V, still score below 53% on objective and 39% on subjective financial chart tasks.

  2. Reasoning or Overthinking: Evaluating Large Language Models on Financial Sentiment Analysis

    cs.CL 2025-06 conditional novelty 5.0 of 10

    On financial sentiment classification, zero-shot LLMs match human labels better without chain-of-thought reasoning than with it.

  3. Continual Learning for Generative AI: From LLMs to MLLMs and Beyond

    cs.LG 2025-06 conditional novelty 4.0 of 10

    A survey that categorizes continual learning methods for generative models into architecture-based, regularization-based, and replay-based paradigms across four model families.

  4. FinBERT2: A Specialized Bidirectional Encoder for Bridging the Gap in Finance-Specific Deployment of Large Language Models

    cs.IR 2025-05 conditional novelty 4.0 of 10

    A 32B-token Chinese financial corpus and FinBERT2 model outperform prior FinBERTs, general BERTs, and several large LLMs on five classification and retrieval benchmarks.

Pith tools