{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/fingpt-instruction-tuning-benchmark-for-open","title":"FinGPT: Instruction Tuning Benchmark for Open-Source Large Language Models in Financial Datasets","arxiv_id":"2310.04793","date":"2023-10-07","proceeding":null,"authors":["Neng Wang","Hongyang Yang","Christina Dan Wang"],"abstract":"In the swiftly expanding domain of Natural Language Processing (NLP), the potential of GPT-based models for the financial sector is increasingly evident. However, the integration of these models with financial datasets presents challenges, notably in determining their adeptness and relevance. This paper introduces a distinctive approach anchored in the Instruction Tuning paradigm for open-source large language models, specifically adapted for financial contexts. Through this methodology, we capitalize on the interoperability of open-source models, ensuring a seamless and transparent integration. We begin by explaining the Instruction Tuning paradigm, highlighting its effectiveness for immediate integration. The paper presents a benchmarking scheme designed for end-to-end training and testing, employing a cost-effective progression. Firstly, we assess basic competencies and fundamental tasks, such as Named Entity Recognition (NER) and sentiment analysis to enhance specialization. Next, we delve into a comprehensive model, executing multi-task operations by amalgamating all instructional tunings to examine versatility. Finally, we explore the zero-shot capabilities by earmarking unseen tasks and incorporating novel datasets to understand adaptability in uncharted terrains. Such a paradigm fortifies the principles of openness and reproducibility, laying a robust foundation for future investigations in open-source financial large language models (FinLLMs).","url_abs":"https://arxiv.org/abs/2310.04793v2","url_pdf":"https://arxiv.org/pdf/2310.04793v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"fingpt-instruction-tuning-benchmark-for-open","repo_url":"https://github.com/ai4finance-foundation/fingpt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"cg","task_name":"NER"},{"task_slug":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.04793","atlas_url":"https://app.syntology.ai/?focus=2310.04793","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04793"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/AI4Finance-Foundation/FinGPT","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ai4finance-foundation/fingpt","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":11},"by_repo_kind":{"official":{"samples":11,"ran":11,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"a96e07dcf3f1f8de","entry":"LinearLayer_LoRA","repo":"ai4finance-foundation/fingpt","repo_kind":"official","path":"fingpt/FinGPT_RAG/instruct-FinGPT/training/utils/module/lora.py","file_url":"https://github.com/ai4finance-foundation/fingpt/blob/HEAD/fingpt/FinGPT_RAG/instruct-FinGPT/training/utils/module/lora.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a96e07dcf3f1f8de"}},{"code_sha256_prefix":"cab0ca5f5d5011c9","entry":"bin_mapping","repo":"AI4Finance-Foundation/FinGPT","repo_kind":"official","path":"fingpt/FinGPT_Forecaster/data.py","file_url":"https://github.com/AI4Finance-Foundation/FinGPT/blob/HEAD/fingpt/FinGPT_Forecaster/data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cab0ca5f5d5011c9"}},{"code_sha256_prefix":"7e84fc5e535cbee5","entry":"check_package","repo":"AI4Finance-Foundation/FinGPT","repo_kind":"official","path":"cloud_test_fingpt.py","file_url":"https://github.com/AI4Finance-Foundation/FinGPT/blob/HEAD/cloud_test_fingpt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7e84fc5e535cbee5"}},{"code_sha256_prefix":"b238cd3633a995b0","entry":"dataset_csv_path","repo":"AI4Finance-Foundation/FinGPT","repo_kind":"official","path":"fingpt/FinGPT_Forecaster/market_sentiment.py","file_url":"https://github.com/AI4Finance-Foundation/FinGPT/blob/HEAD/fingpt/FinGPT_Forecaster/market_sentiment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b238cd3633a995b0"}},{"code_sha256_prefix":"2b49d3d2bda3735e","entry":"enabled","repo":"AI4Finance-Foundation/FinGPT","repo_kind":"official","path":"fingpt/FinGPT_Forecaster/market_sentiment.py","file_url":"https://github.com/AI4Finance-Foundation/FinGPT/blob/HEAD/fingpt/FinGPT_Forecaster/market_sentiment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2b49d3d2bda3735e"}},{"code_sha256_prefix":"761e6e67888a33d2","entry":"get_api_key","repo":"AI4Finance-Foundation/FinGPT","repo_kind":"official","path":"fingpt/FinGPT_Forecaster/market_sentiment.py","file_url":"https://github.com/AI4Finance-Foundation/FinGPT/blob/HEAD/fingpt/FinGPT_Forecaster/market_sentiment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"761e6e67888a33d2"}},{"code_sha256_prefix":"130ab5832e26fbdd","entry":"get_prompt","repo":"AI4Finance-Foundation/FinGPT","repo_kind":"official","path":"fingpt/FinGPT_Benchmark/utils.py","file_url":"https://github.com/AI4Finance-Foundation/FinGPT/blob/HEAD/fingpt/FinGPT_Benchmark/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"130ab5832e26fbdd"}},{"code_sha256_prefix":"f0af8e0445d8fede","entry":"n_weeks_before","repo":"AI4Finance-Foundation/FinGPT","repo_kind":"official","path":"fingpt/FinGPT_Forecaster/data_infererence_fetch.py","file_url":"https://github.com/AI4Finance-Foundation/FinGPT/blob/HEAD/fingpt/FinGPT_Forecaster/data_infererence_fetch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f0af8e0445d8fede"}},{"code_sha256_prefix":"6f6d5a0985347117","entry":"resolve_symbol","repo":"AI4Finance-Foundation/FinGPT","repo_kind":"official","path":"fingpt/FinGPT_Forecaster/market_symbols.py","file_url":"https://github.com/AI4Finance-Foundation/FinGPT/blob/HEAD/fingpt/FinGPT_Forecaster/market_symbols.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6f6d5a0985347117"}},{"code_sha256_prefix":"698fcf3cf5957913","entry":"test_mapping","repo":"AI4Finance-Foundation/FinGPT","repo_kind":"official","path":"fingpt/FinGPT_Benchmark/utils.py","file_url":"https://github.com/AI4Finance-Foundation/FinGPT/blob/HEAD/fingpt/FinGPT_Benchmark/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"698fcf3cf5957913"}},{"code_sha256_prefix":"a8301984bfcfdc76","entry":"tokenize","repo":"AI4Finance-Foundation/FinGPT","repo_kind":"official","path":"fingpt/FinGPT_Benchmark/utils.py","file_url":"https://github.com/AI4Finance-Foundation/FinGPT/blob/HEAD/fingpt/FinGPT_Benchmark/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a8301984bfcfdc76"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}