{"paper_id":"2412.10906","title":"SusGen-GPT: A Data-Centric LLM for Financial NLP and Sustainability Report Generation","authors":["Qilong Wu","Xiaoneng Xiang","Hejia Huang","Xuan Wang","Yeo Wei Jie","Ranjan Satapathy","Ricardo Shirota Filho","Bharadwaj Veeravalli"],"paper_date":"2024-12-14","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2412.10906v1","page_url":"https://thequant.space/flowcharts/susgen-gpt-a-data-centric-llm-for-financial-nlp-and-sustain/","scores":{"empirical_rigor":8.5,"math_complexity":3,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper introduces the SusGen-30K dataset, the TCFD-Bench benchmark, and a suite of fine‑tuned LLMs called SusGen‑GPT for financial and ESG NLP tasks.","quote":"In total, our contributions include the following: 1. SusGen-30K, a large-scale high quality dataset in both financial & ESG domain. 2. We propose and release a well-curated benchmark, tailored towards ESG report generation, TCFD-Bench. 3. A suite of fine-tuned LLMs, SusGen-GPT, shown to achieve comparable state-of-the","summary":"The rapid growth of the financial sector and the rising focus on Environmental, Social, and Governance (ESG) considerations highlight the need for advanced NLP tools. However, open-source LLMs proficient in both finance and ESG domains remain scarce. To address this gap, we introduce SusGen-30K, a…","strategy":null},"assumptions":{"status":"none_found","items":[]},"datasets":{"status":"available","items":[{"name":"SusGen-30K","provider":"Hugging Face and TCFDHub","kind":"text-news","access":"public","period":null,"universe":null,"quote":"The dataset is originally sourced from two primary sources: open-source datasets available on Hugging Face2 and annual reports sourced from TCFDHub3 Database."},{"name":"TCFD-Bench","provider":null,"kind":"benchmark","access":"public","period":null,"universe":null,"quote":"We propose a new benchmark, TCFD-Bench, specifically designed to assess models’ ability to generate concise and accurate ESG reports from annual reports."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"none"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"SusGen‑GPT achieves state‑of‑the‑art performance across six adapted and two off‑the‑shelf tasks, trailing GPT‑4 by only 2% while using only 7‑8B parameters versus GPT‑4’s 1,700B.","kind":"performance","quote":"... trailing GPT‑4 by only 2% despite using 7-8B parameters compared to GPT‑4's 1,700B."},{"finding":"Increasing the dataset size consistently improves performance across all eight financial NLP tasks.","kind":"statistical","quote":"Overall, the results show a clear trend: increasing the dataset size consistently improves performance across all tasks."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":16,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":true,"code_url":"https://github.com/JerryWu-code/SusGen","note":null},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T17:49:50Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}