{"author":{"name":"Kemal Kirtac","slug":"kemal-kirtac","article_count":1,"latest_published_at":"2026-05-01T13:43:35.535+00:00","profile_url":"https://vff.ai/authors/kemal-kirtac","api_url":"https://vff.ai/api/authors/kemal-kirtac"},"articles":[{"slug":"learning-to-aggregate-zero-shot-llm-agents-for-corporate-disclosure-classificati","title":"Aggregating Zero-Shot LLMs Beats Single Models for Financial Disclosure Analysis","url":"https://vff.ai/article/2026/05/01/learning-to-aggregate-zero-shot-llm-agents-for-corporate-disclosure-classificati","content_type":"research_summary","summary":"A new paper demonstrates that a lightweight supervised aggregator can effectively combine outputs from multiple zero-shot LLMs to improve corporate disclosure classification and stock return prediction. Researchers tested three fixed zero-shot classifiers reading financial disclosures from different perspectives, then trained a logistic meta-classifier to aggregate their outputs. Using 9,860 U.S. corporate disclosures from January 2025 to March 2026, the trained aggregator achieved 60.6% balanced accuracy compared to 56.6% for the best single classifier, with the largest gains appearing in mixed-signal cases where classifiers disagreed.","published_at":"2026-05-01T13:43:35.535+00:00","updated_at":"2026-05-07T02:19:52.375108+00:00","source":{"url":"https://arxiv.org/abs/2603.20965","name":"ArXiv (cs.AI)"},"featured_image":{"url":"https://towardsdatascience.com/wp-content/uploads/2026/04/zero-shot-free-text-classification-scaled-1.jpg","alt":null},"categories":[{"name":"Research","slug":"research"},{"name":"LLMs","slug":"llms"},{"name":"AI Agents","slug":"ai-agents"},{"name":"AI for Business","slug":"ai-for-business"}]}]}