AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

PIXIU: A Comprehensive Benchmark, Instruction Dataset and Large Language Model for Finance

Qianqian Xie, Weiguang Han, Xiao Zhang, Yanzhao Lai, Min Peng, Alejandro Lopez-Lira, Jimin Huang

NeurIPS 2023 · Large language models › Instruction and fine-tuning · approach: Calibration and knowledge in LLM tuning · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
instruction-tune LLaMA-7B on financial NLP data (FinMA-7B) vs Vicuna-7BLLaMA-7B · FPBF1: 0.29 -> 0.94Improved
scale FinMA from 7B to 30B (ablation)FinMA · ConvFinQAEM accuracy: 0.25 -> 0.40Improved
scale FinMA from 7B to 30B (ablation)FinMA · FinQAEM accuracy: 0.06 -> 0.11Improved
scale FinMA from 7B to 30B (ablation)FinMA · FPBF1: 0.94 -> 0.88Hurt
scale FinMA from 7B to 30B (ablation)FinMA · BigData22Accuracy: 0.45 -> 0.47No clear effect
add prediction task data to NLP instruction data (FinMA-7B-full vs FinMA-7B) (ablation)FinMA-7B · ACL18Accuracy: 0.49 -> 0.51Improved
add prediction task data to NLP instruction data (FinMA-7B-full vs FinMA-7B) (ablation)FinMA-7B · CIKM18Accuracy: 0.43 -> 0.50Improved
add prediction task data to NLP instruction data (FinMA-7B-full vs FinMA-7B) (ablation)FinMA-7B · FPBF1: 0.94 -> 0.94No clear effect
fine-tune on prediction tasks only (FinMA-7B-trade) vs NLP-only FinMA-7B (ablation)FinMA-7B · FPBF1: 0.94 -> 0.03Hurt
fine-tune on prediction tasks only (FinMA-7B-trade) vs NLP-only FinMA-7B (ablation)FinMA-7B · BigData22Accuracy: 0.45 -> 0.45No clear effect
classification-only fine-tuning (FinMA vs Vicuna-7B)LLaMA-7B · EDTSumRouge-1: 0.22 -> 0.09Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy