2 papers
cs.CL2025
Adaptation of Embedding Models to Financial Filings via LLM Distillation
Eliot Brenner, Dominic Seyler, Manjunath Hegde +3
Despite advances in generative large language models (LLMs), practical application of specialized conversational AI agents remains constrained by computation costs, latency require…
cs.CL2025
Healing Powers of BERT: How Task-Specific Fine-Tuning Recovers Corrupted Language Models
Shijie Han, Zhenyu Zhang, Andrei Arsene Simion
Language models like BERT excel at sentence classification tasks due to extensive pre-training on general data, but their robustness to parameter corruption is unexplored. To under…