KB국민은행에서 제공하는 경제/금융 도메인에 특화된 한국어 ALBERT 모델

A symbolic benchmark for verifiable chain-of-thought financial reasoning. Includes executable templates, 58 topics across 12 domains, and ChainEval metrics.

Research on all kind of NLP in market forecasting, expert estimation, etc.

Resource-efficient LLM distillation: Improving sustainability and reducing computational costs of Large Language Models in financial analytics through knowledge distillation.

Living Literature Review on Memestock identification using NLP

🎯 Fine-tuning LLMs using LlamaFactory for financial intent understanding | Evaluating open-source models on OpenFinData benchmark | Full implementation with multiple models (Qwen2.5/ChatGLM3/Baichuan2/Llama3)

A structured evaluation pipeline for LLM-generated outputs in financial supervision contexts. Combines PRA-aligned prompts, thread-type detection, and metric-level meta-review to assess relevance, justification, and actionability across 50+ regulatory and conversational metrics.

Comparative study of FinBERT, Local LLM, and RAG-enhanced approaches for financial sentiment classification on FinancialPhraseBank

Fine-tuning small LLMs (Phi-3.5, LLaMA-3.2) with QLoRA for summarizing earnings call transcripts. Evaluated with ROUGE and BERTScore. Part of NLP for Finance coursework.

Fine-tuning BERT for financial sentiment analysis across multiple datasets. Achieves 86% accuracy on professional news, exploring domain adaptation challenges.

Regime-based evaluation framework for financial NLP stability. Implements chronological cross-validation, semantic drift quantification via Jensen-Shannon divergence, and multi-faceted robustness profiling. Replicates Sun et al.'s (2025) methodology with modular, auditable Python codebase.