{"paper_id":"2507.22936","title":"Evaluating Large Language Models (LLMs) in Financial NLP: A Comparative Study on Financial Report Analysis","authors":["Md Talha Mohsin"],"paper_date":"2025-07-24","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2507.22936v1","page_url":"https://thequant.space/flowcharts/evaluating-large-language-models-llms-in-financial-nlp-a/","scores":{"empirical_rigor":6,"math_complexity":2.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a controlled evaluation of five transformer‑based LLMs on question answering over 10‑K Business sections, using human evaluation, automated similarity metrics, and behavioral diagnostics.","quote":"This paper presents a controlled evaluation of five transformer-based LLMs applied to question answering over the Business sections of U.S. 10‑K filings.","summary":"Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide variety of Financial Natural Language Processing (FinNLP) tasks. However, systematic comparisons among widely used LLMs remain underexplored. Given the rapid advancement and growing influence of LLMs in financial…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The Business sections of 10‑K filings are representative of complex financial disclosures for evaluating LLM behavior.","type":"data","stated":"implied","quote":"Focusing on large, information‑rich disclosures from major technology firms allows for a controlled and demanding evaluation setting"},{"assumption":"Chain‑of‑Thought prompting can make LLMs behave like financial analysts, enabling simulation of real‑life analytical workflows.","type":"model","stated":"implied","quote":"We introduce a Chain‑of‑Thought (CoT) prompting approach that tells models to behave like financial analysts in order to simulate real‑life analytical workflows."}]},"datasets":{"status":"available","items":[{"name":"Business section of 10‑K filings","provider":"U.S. Securities and Exchange Commission (SEC)","kind":"text-news","access":"public","period":"last three years","universe":"\"Magnificent 7\" tech companies","quote":"ChatGPT‑4, Perplexity, Claude 4 Opus, Gemini, and DeepSeek—look at the Business section (Item 1) of 10‑K filings from the ”Magnificent 7” tech companies over the last three years."}],"known":[{"id":"edgar","name":"SEC EDGAR","provider":"U.S. Securities and Exchange Commission","kind":"text-news","access":"public","quote":"Text was obtained from the SEC’s EDGAR system, converted from HTML, and manually preprocessed to remove boilerplate language and ensure consistent formatting across companies and models.","mentions":1,"used_in":1}],"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":"No single LLM consistently dominates across all evaluation perspectives; performance differences are relative tendencies under the tested conditions.","kind":"other","quote":"Importantly, no single model consistently dominates across all evaluation perspectives."},{"finding":"GPT achieved the highest average human scores on relevance, completeness, clarity, and factual accuracy among the models evaluated.","kind":"performance","quote":"GPT is rated by the highest number of annotators on the scale of relevance, completeness, and clarity. It also scores well on the accuracy of the facts."},{"finding":"Inter‑rater reliability was low across all qualitative dimensions, indicating substantial disagreement among expert annotators.","kind":"statistical","quote":"Agreement levels are generally low across all qualitative dimensions, with α values clustered near zero and occasional negative estimates."}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":15,"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":"2026-11-14T17:31:14Z"},"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/"}