{"slug": "findialoglens-event-extraction-over-multi-party-dialogue-for-missed-trade-in", "title": "FinDialogLens: Event Extraction over Multi-Party Dialogue for Missed-Trade Identification in Financial Chatrooms", "summary": "A hybrid LLM pipeline called FinDialogLens reached 92.1% accuracy on final price and 94.3% on trade outcome when extracting missed-trade events from multi-party financial chatrooms, according to an arXiv paper (arXiv:2610.02455v1). The system uses compact fine-tuned classifiers as inference-time scaffolds around GPT-4o, and a difficulty-aware router that cuts LLM calls by 85% on final price while saving over $300/day at a 70,000-RFQ/day scale. Fine-tuned open-source LLMs with as few as 3B parameters achieved comparable performance with modest in-domain data.", "body_md": "arXiv:2610.02455v1 Announce Type: new \nAbstract: Multi-party financial chatrooms are vital for sales-and-trading professionals, but their complexity makes manual recovery of missed trades infeasible: each Request for Quote (RFQ) is an event whose final price and trade outcome appear many messages after the RFQ-trigger message (the inquiry message), interleaved with concurrent RFQs from other participants. We cast this as event extraction (EE) over multi-party dialogue and present FinDialogLens, a hybrid LLM pipeline in which compact fine-tuned classifiers act as inference-time scaffolds: they detect RFQ-triggers and price/trade outcome metadata, an RFQ-Level Module segments per-event RFQ windows, and a Trade Engine fills argument roles. With GPT-4o, FinDialogLens reaches 92.1% and 94.3% accuracy on final price and trade outcome, respectively, outperforming full-chatroom CoT prompting methods; fine-tuned open-source LLMs with as few as 3B parameters achieve comparable performance with modest in-domain data. To make the LLM-based solution practical at scale, a difficulty-aware router balances cost and accuracy by allocating RFQs between a low-cost rule-based engine and the higher-performing LLM-powered Trade Engine, cutting LLM calls by 85% on final price while recovering half of the accuracy gap to FinDialogLens (GPT-4o), saving over $300/day at our 70,000-RFQ/day scale.", "url": "https://wpnews.pro/news/findialoglens-event-extraction-over-multi-party-dialogue-for-missed-trade-in", "canonical_source": "https://arxiv.org/abs/2610.02455", "published_at": "2026-10-05 04:00:00+00:00", "updated_at": "2026-10-05 04:14:46.938520+00:00", "lang": "en", "topics": ["large-language-models", "natural-language-processing", "ai-research", "ai-infrastructure"], "entities": ["FinDialogLens", "GPT-4o", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/findialoglens-event-extraction-over-multi-party-dialogue-for-missed-trade-in", "markdown": "https://wpnews.pro/news/findialoglens-event-extraction-over-multi-party-dialogue-for-missed-trade-in.md", "text": "https://wpnews.pro/news/findialoglens-event-extraction-over-multi-party-dialogue-for-missed-trade-in.txt", "jsonld": "https://wpnews.pro/news/findialoglens-event-extraction-over-multi-party-dialogue-for-missed-trade-in.jsonld"}}