{"paper_id":"2308.08031","title":"Company Similarity using Large Language Models","authors":["Dimitrios Vamvourellis","Máté Toth","Snigdha Bhagat","Dhruv Desai","Dhagash Mehta","Stefano Pasquali"],"paper_date":"2023-08-15","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2308.08031v1","page_url":"https://thequant.space/flowcharts/company-similarity-using-large-language-models/","scores":{"empirical_rigor":8,"math_complexity":6.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes generating company embeddings from SEC 10-K business descriptions using state‑of‑the‑art language models and benchmarking them on classification and financial similarity tasks.","quote":"In this paper, we generate company embeddings using the raw business descriptions reported in SEC 10K filings using SOTA language models.","summary":"Identifying companies with similar profiles is a core task in finance with a wide range of applications in portfolio construction, asset pricing and risk attribution. When a rigorous definition of similarity is lacking, financial analysts usually resort to ’traditional’ industry classifications…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Similarity between companies is measured by the correlation of their daily returns, assuming similar companies have similar return movements over long horizons.","type":"market","stated":"explicit","quote":"we measure similarity between two companies based on the correlation of their daily returns, assuming that similar companies typically experience similar movements in their stock returns over long horizons."},{"assumption":"Only the first 512 tokens of Item 1 are used for finetuning the BERT model.","type":"data","stated":"explicit","quote":"we finetune it on the task of predicting GICS industry, using only the first 512 tokens of Item 1."},{"assumption":"A stratified train‑test split ensures a representative sample from all GICS categories.","type":"statistical","stated":"explicit","quote":"we opt for a stratified split, ensuring a representative sample from all categories in both train and test splits."}]},"datasets":{"status":"available","items":[{"name":"SEC 10‑K Item 1 business description","provider":"U.S. Securities and Exchange Commission","kind":"text-news","access":"public","period":null,"universe":null,"quote":"we used the textual content from Item 1 of the SEC 10K reports as input features."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"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":"Company embeddings can reproduce GICS sector classifications with approximately 90% accuracy, with finetuned SBERT achieving the best performance.","kind":"predictive-accuracy","quote":"Finetuned Sentence-BERT (SBERT-FT) models preform best, achieving approximately 90% accuracy in predicting GICS sectors from 10-K business descriptions."},{"finding":"Finetuned models outperform pre‑trained models on sector/industry classification but underperform on similarity and return‑attribution tasks.","kind":"performance","quote":"finetuned models underperform compared to the pre‑trained models on the similarity and return attribution tasks, while they outperformed pre‑trained models on sector/industry classification tasks."},{"finding":"Using embeddings, the closest peer of each company shows a 10% higher return correlation than the sector average and 6% higher than the industry average.","kind":"performance","quote":"using the embeddings we can identify the closest peer of each company in the embedding space which has 10% greater returns correlation compared to the sector average and 6% greater returns correlation compared to the industry average."},{"finding":"Larger LLMs (≈200‑500B parameters) marginally outperform SBERT on return attribution but are comparable or slightly worse on similarity tasks.","kind":"performance","quote":"PaLM and GPT marginally outperform SBERT on the return attribution task while they are on par on slightly worse than SBERT on the similarity task."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":20,"citations":{"cited_by_in_corpus":11,"by_independent_authors":9,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":5,"unclassified":6},"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":"2026-11-14T18:23:22Z"},"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/"}