The proposed NumCache, which compresses SEC filings into KV caches initialized from numerically dense regions and trained directly on financial QAs, is evaluated, which highlights cache-based retrieval with number-preserving representations as an effective approach for long-context financial QA.
Eftychia Makri, Peiwen Li, Yidong Jiang et al.· Proceedings of the 32nd ACM...· 0 citations
Large Language Models (LLMs) are increasingly deployed in financial applications, particularly for interpreting U.S. Securities and Exchange Commission (SEC) filings. However, financial QA over these filings is challenging, as they are extremely long, numerically dense, and often require cross-document reasoning. Exist...
Eftychia Makri, Peiwen Li, Yidong Jiang et al.· Proceedings of the 32nd ACM...· 0 citations
The allocator, ModalShare, sets each modality's keep-ratio from a Shapley contribution score that the server computes over coalitions of activations it has already received, and shows that existing compressors underperform in multimodal settings, with ModalShare recovering what gains are left behind.
Iason Ofeidis, Leandros Tassiulas· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
