Papers
Topics
Authors
Recent
Search
2000 character limit reached

No Language is an Island: Unifying Chinese and English in Financial Large Language Models, Instruction Data, and Benchmarks

Published 10 Mar 2024 in cs.CE and cs.CL | (2403.06249v3)

Abstract: While the progression of LLMs has notably propelled financial analysis, their application has largely been confined to singular language realms, leaving untapped the potential of bilingual Chinese-English capacity. To bridge this chasm, we introduce ICE-PIXIU, seamlessly amalgamating the ICE-INTENT model and ICE-FLARE benchmark for bilingual financial analysis. ICE-PIXIU uniquely integrates a spectrum of Chinese tasks, alongside translated and original English datasets, enriching the breadth and depth of bilingual financial modeling. It provides unrestricted access to diverse model variants, a substantial compilation of diverse cross-lingual and multi-modal instruction data, and an evaluation benchmark with expert annotations, comprising 10 NLP tasks, 20 bilingual specific tasks, totaling 95k datasets. Our thorough evaluation emphasizes the advantages of incorporating these bilingual datasets, especially in translation tasks and utilizing original English data, enhancing both linguistic flexibility and analytical acuity in financial contexts. Notably, ICE-INTENT distinguishes itself by showcasing significant enhancements over conventional LLMs and existing financial LLMs in bilingual milieus, underscoring the profound impact of robust bilingual data on the accuracy and efficacy of financial NLP.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (55)
  1. Gpt-4 technical report. arXiv preprint arXiv:2303.08774.
  2. Domain adaption of named entity recognition to support credit risk assessment. In Proceedings of the Australasian Language Technology Association Workshop 2015, pages 84–90.
  3. Dogu Araci. 2019. Finbert: Financial sentiment analysis with pre-trained language models. arXiv preprint arXiv:1908.10063.
  4. Qwen technical report. arXiv preprint arXiv:2309.16609.
  5. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.
  6. The bq corpus: A large-scale domain-specific chinese corpus for sentence semantic equivalence identification. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4946–4951.
  7. Disc-finllm: A chinese financial large language model based on multiple experts fine-tuning. arXiv preprint arXiv:2310.15205.
  8. Finqa: A dataset of numerical reasoning over financial data. arXiv preprint arXiv:2109.00122.
  9. Convfinqa: Exploring the chain of numerical reasoning in conversational finance question answering. arXiv preprint arXiv:2210.03849.
  10. Electra: Pre-training text encoders as discriminators rather than generators. arXiv preprint arXiv:2003.10555.
  11. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
  12. Glm: General language model pretraining with autoregressive blank infilling. arXiv preprint arXiv:2103.10360.
  13. Hans Hofmann. 1994. Statlog (German Credit Data). UCI Machine Learning Repository. DOI: https://doi.org/10.24432/C5NC77.
  14. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685.
  15. Entity enhanced bert pre-training for chinese ner. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6384–6396.
  16. Cfbenchmark: Chinese financial assistant benchmark for large language model. arXiv preprint arXiv:2311.05812.
  17. Cfgpt: Chinese financial assistant with large language model. arXiv preprint arXiv:2309.10654.
  18. Are chatgpt and gpt-4 general-purpose solvers for financial text analytics? an examination on several typical tasks. arXiv preprint arXiv:2305.05862.
  19. Bbt-fin: Comprehensive construction of chinese financial domain pre-trained language model, corpus and benchmark. arXiv preprint arXiv:2302.09432.
  20. Www’18 open challenge: financial opinion mining and question answering. In Companion proceedings of the the web conference 2018, pages 1941–1942.
  21. Good debt or bad debt: Detecting semantic orientations in economic texts. Journal of the Association for Information Science and Technology, 65(4):782–796.
  22. Crosslingual generalization through multitask finetuning. arXiv preprint arXiv:2211.01786.
  23. Ectsum: A new benchmark dataset for bullet point summarization of long earnings call transcripts. arXiv preprint arXiv:2210.12467.
  24. Typhoon: Thai large language models. arXiv preprint arXiv:2312.13951.
  25. Ross Quinlan. Statlog (Australian Credit Approval). UCI Machine Learning Repository. DOI: https://doi.org/10.24432/C59012.
  26. Trillion dollar words: A new financial dataset, task & market analysis. arXiv preprint arXiv:2305.07972.
  27. When flue meets flang: Benchmarks and large pre-trained language model for financial domain. arXiv preprint arXiv:2211.00083.
  28. Ankur Sinha and Tanmay Khandait. 2021. Impact of news on the commodity market: Dataset and results. In Advances in Information and Communication: Proceedings of the 2021 Future of Information and Communication Conference (FICC), pages 589–601. Springer.
  29. Big data: Deep learning for financial sentiment analysis. Journal of Big Data, 5(1):1–25.
  30. Accurate stock movement prediction with self-supervised learning from sparse noisy tweets. In 2022 IEEE International Conference on Big Data (Big Data), pages 1691–1700. IEEE.
  31. InternLM Team. 2023. Internlm: A multilingual language model with progressively enhanced capabilities.
  32. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971.
  33. Wg Wang. 2023. Awesome-llms-in-china. https://github.com/wgwang/awesome-LLMs-In-China.
  34. Self-instruct: Aligning language model with self generated instructions. arXiv preprint arXiv:2212.10560.
  35. Pangu-Ï€: Enhancing language model architectures via nonlinearity compensation. arXiv preprint arXiv:2312.17276.
  36. Hybrid deep sequential modeling for social text-driven stock prediction. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management(CIKM), pages 1627–1630.
  37. Bloomberggpt: A large language model for finance. arXiv preprint arXiv:2303.17564.
  38. The finben: An holistic financial benchmark for large language models. arXiv preprint arXiv:2402.12659.
  39. The wall street neophyte: A zero-shot analysis of chatgpt over multimodal stock movement prediction challenges. arXiv preprint arXiv:2304.05351.
  40. Pixiu: A comprehensive benchmark, instruction dataset and large language model for finance. In 37th International Conference on Neural Information Processing Systems.
  41. Clue: A chinese language understanding evaluation benchmark. arXiv preprint arXiv:2004.05986.
  42. Yumo Xu and Shay B Cohen. 2018. Stock movement prediction from tweets and historical prices. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1970–1979.
  43. Baichuan 2: Open large-scale language models. arXiv preprint arXiv:2309.10305.
  44. Fingpt: Open-source financial large language models. arXiv preprint arXiv:2306.06031.
  45. Investlm: A large language model for investment using financial domain instruction tuning. arXiv preprint arXiv:2309.13064.
  46. Finbert: A pretrained language model for financial communications. arXiv preprint arXiv:2006.08097.
  47. YangMu Yu. 2023. Cornucopia-llama-fin-chinese. https://github.com/jerry1993-tech/Cornucopia-LLaMA-Fin-Chinese.
  48. Instruct-fingpt: Financial sentiment analysis by instruction tuning of general-purpose large language models. arXiv preprint arXiv:2306.12659.
  49. Fineval: A chinese financial domain knowledge evaluation benchmark for large language models. arXiv preprint arXiv:2308.09975.
  50. Cgce: A chinese generative chat evaluation benchmark for general and financial domains. arXiv preprint arXiv:2305.14471.
  51. Yang Qing Xu Dongliang Zhang, Xuanyu. 2023. Xuanyuan 2.0: A large chinese financial chat model with hundreds of billions parameters. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, pages 4435–4439.
  52. Mengzi: Towards lightweight yet ingenious pre-trained models for chinese. arXiv preprint arXiv:2110.06696.
  53. Global table extractor (gte): A framework for joint table identification and cell structure recognition using visual context. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 697–706.
  54. Trade the event: Corporate events detection for news-based event-driven trading. arXiv preprint arXiv:2105.12825.
  55. Astock: A new dataset and automated stock trading based on stock-specific news analyzing model. arXiv preprint arXiv:2206.06606.
Citations (2)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up

Tweets

Sign up for free to view the 1 tweet with 0 likes about this paper.

Sign Up for Free