{"paper_id":"2407.01953","title":"CatMemo at the FinLLM Challenge Task: Fine-Tuning Large Language Models using Data Fusion in Financial Applications","authors":["Yupeng Cao","Zhiyuan Yao","Zhi Chen","Zhiyang Deng"],"paper_date":"2024-07-02","paper_type":"methodological","paper_url":"https://arxiv.org/pdf/2407.01953v1","page_url":"https://thequant.space/flowcharts/catmemo-at-the-finllm-challenge-task-fine-tuning-large-lang/","scores":{"empirical_rigor":6,"math_complexity":1.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper fine‑tunes Llama3‑8B and Mistral‑7B with PEFT and LoRA, using data fusion of task‑1 and task‑2 datasets to address classification, summarization, and stock‑trading tasks.","quote":"We adopted Llama3-8B and Mistral-7B as base models, fine-tuning them through Parameter Efficient Fine-Tuning (PEFT) and Low-Rank Adaptation (LoRA) approaches. To enhance model performance, we combine datasets from task 1 and task 2 for data fusion.","summary":"The integration of Large Language Models (LLMs) into financial analysis has garnered significant attention in the NLP community. This paper presents our solution to IJCAI-2024 FinLLM challenge, investigating the capabilities of LLMs within three critical areas of financial tasks: financial…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The task‑3 dataset is excluded because its narrow company‑specific content would not benefit the model.","type":"data","stated":"implied","quote":"We excluded the dataset for task 3, which focuses on texts related to three specific stocks, due to its narrow company-specific content."},{"assumption":"Models are fine‑tuned for only one epoch due to limited computational resources.","type":"execution","stated":"implied","quote":"The models were trained and inferenced on two NVIDIA RTX-A6000 GPUs (each has 48GB DRAM) with one epoch."}]},"datasets":{"status":"available","items":[{"name":"Task 1 dataset","provider":null,"kind":"text-news","access":"unknown","period":null,"universe":null,"quote":"We combine datasets from task 1 and task 2 for data fusion."},{"name":"Task 2 dataset","provider":null,"kind":"text-news","access":"unknown","period":null,"universe":null,"quote":"We combine datasets from task 1 and task 2 for data fusion."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"no","evidence_card":"no","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Fine‑tuned Mistral‑7B on the fused dataset achieved a 0.5634 F1 score on the classification task (Task 1).","kind":"performance","quote":"where it achieves a 0.5634 F1 score."},{"finding":"On the summarization task (Task 2), the fused model improved Rouge‑1 to 0.4920, Rouge‑2 to 0.3015, and BertScore to 0.6946.","kind":"performance","quote":"Task 1 + Task 2 0.4920 0.3015 0.6946"},{"finding":"Mistral‑7B demonstrated superior predictive capabilities over Llama3‑8B, leading to its exclusive use in subsequent experiments.","kind":"performance","quote":"Mistral-7B demonstrated superior predictive capabilities and produced well-formatted outputs that could be easily parsed to yield final predictions."},{"finding":"On the stock‑trading task (Task 3), the integrated Sharpe Ratio was -0.6199, indicating poor performance.","kind":"negative","quote":"In Task 3, the integrated Sharp Ratio (SR) was -0.6199."},{"finding":"In the test set, the fine‑tuned model achieved ACC 0.711, F1 0.4199, and MCC 0.6818 on Task 1.","kind":"performance","quote":"In Task 1, the model achieved an ACC of 0.711, an F1 score of 0.4199, and a Matthews correlation coefficient (MCC) of 0.6818."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":24,"citations":{"cited_by_in_corpus":2,"by_independent_authors":2,"how_cited":{"used_as_baseline":0,"uses_method_or_data":1,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":0},"independent_papers":[{"paper":{"paper_id":"2507.18560","title":"HARLF: Hierarchical Reinforcement Learning and Lightweight LLM-Driven Sentiment Integration for Financial Portfolio Optimization","paper_date":"2025-07-24","authors":["Benjamin Coriat","Eric Benhamou"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/harlf-hierarchical-reinforcement-learning-and-lightweight-l/"},"how":"uses_method_or_data","quote":null}],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"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":"2026-11-14T18:06:56Z"},"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/"}