{"paper_id":"2510.01526","title":"One More Question is Enough, Expert Question Decomposition (EQD) Model for Domain Quantitative Reasoning","authors":["Mengyu Wang","Sotirios Sabanis","Miguel de Carvalho","Shay B. Cohen","Tiejun Ma"],"paper_date":"2025-10-01","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2510.01526v1","page_url":"https://thequant.space/flowcharts/one-more-question-is-enough-expert-question-decomposition-/","scores":{"empirical_rigor":3,"math_complexity":1.5,"quadrant":"Philosophers"},"proposes":{"status":"available","statement":"The paper proposes Expert Question Decomposition (EQD), a two‑step fine‑tuning framework that generates concise supporting sub‑questions to improve domain‑specific quantitative QA.","quote":"In this work, we propose Expert Question Decomposition (EQD), an approach designed to balance the use of domain knowledge with computational efficiency.","summary":"Domain-specific quantitative reasoning remains a major challenge for large language models (LLMs), especially in fields requiring expert knowledge and complex question answering (QA). In this work, we propose Expert Question Decomposition (EQD), an approach designed to balance the use of domain…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"A single concise supporting question is sufficient to improve QA performance more than detailed step‑by‑step guidance.","type":"other","stated":"implied","quote":"a single supporting question often provides greater benefit than detailed guidance steps."}]},"datasets":{"status":"available","items":[{"name":"ConvFinQA","provider":null,"kind":"benchmark","access":"public","period":null,"universe":null,"quote":"In our experiments, we use just two datasets, ConvFinQA and FinQA, among the many datasets used for financial LLM fine-tuning"},{"name":"FinQA","provider":null,"kind":"benchmark","access":"public","period":null,"universe":null,"quote":"In our experiments, we use just two datasets, ConvFinQA and FinQA, among the many datasets used for financial LLM fine-tuning"}],"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":"EQD consistently improves QA performance across four financial datasets by 0.6% to 10.5% for multiple LLMs, outperforming advanced domain‑adapted models and prompting techniques.","kind":"performance","quote":"Across four financial QA benchmarks, it achieves performance gains of 0.6% to 10.5% across multiple LLMs, out-performing advanced domain-adapted models and prompting techniques."},{"finding":"A single critical supporting question yields greater benefit than extensive step‑by‑step CoT prompting in domain‑specific QA.","kind":"other","quote":"a single supporting question often provides greater benefit than detailed guidance steps."},{"finding":"EQD requires only a few thousand training examples and a single A100 GPU, with inference time comparable to zero‑shot prompting.","kind":"performance","quote":"It requires only a few thousand training examples and a single A100 GPU for fine-tuning, with inference time comparable to zero-shot prompting."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":28,"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":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":"2026-11-14T17:25:40Z"},"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/"}