Sentiment Classification on Finance
89.41F1 ScoreBERT-FT
Evaluation results
| Method | Links | |
|---|---|---|
| BERT-FTBackbone=BERT-base, Evaluation Protocol=Fine-tuning2024.06 | 89.41 | |
| Random + Feedback-ICLBackbone=Llama-2 13B Chat, Evaluation Protocol=In-context learning, Number of in-context examples=4, Retrieval Strategy=Random2024.06 | 78.64 | |
| K-Means + Feedback-ICLBackbone=Llama-2 13B Chat, Evaluation Protocol=In-context learning, Number of in-context examples=4, Retrieval Strategy=K-Means2024.06 | 78.44 | |
| K-MeansBackbone=Llama-2 13B Chat, Evaluation Protocol=In-context learning, Number of in-context examples=4, Retrieval Strategy=K-Means2024.06 | 76.14 | |
| RandomBackbone=Llama-2 13B Chat, Evaluation Protocol=In-context learning, Number of in-context examples=4, Retrieval Strategy=Random2024.06 | 75.34 | |
| BM25 + Feedback-ICLBackbone=Llama-2 13B Chat, Evaluation Protocol=In-context learning, Number of in-context examples=4, Retrieval Strategy=BM252024.06 | 66.94 | |
| MMR + Feedback-ICLBackbone=Llama-2 13B Chat, Evaluation Protocol=In-context learning, Number of in-context examples=4, Retrieval Strategy=MMR2024.06 | 59.85 | |
| SBERT + Feedback-ICLBackbone=Llama-2 13B Chat, Evaluation Protocol=In-context learning, Number of in-context examples=4, Retrieval Strategy=SBERT2024.06 | 58.21 | |
| BM25Backbone=Llama-2 13B Chat, Evaluation Protocol=In-context learning, Number of in-context examples=4, Retrieval Strategy=BM252024.06 | 56.13 | |
| MMRBackbone=Llama-2 13B Chat, Evaluation Protocol=In-context learning, Number of in-context examples=4, Retrieval Strategy=MMR2024.06 | 54.51 | |
| SBERTBackbone=Llama-2 13B Chat, Evaluation Protocol=In-context learning, Number of in-context examples=4, Retrieval Strategy=SBERT2024.06 | 47.12 |