Improving Classification Performance With Human Feedback: Label a few, we label the rest
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913199373156352 |
|---|---|
| author | Vidra, Natan Clifford, Thomas Jijo, Katherine Chung, Eden Zhang, Liang |
| author_facet | Vidra, Natan Clifford, Thomas Jijo, Katherine Chung, Eden Zhang, Liang |
| contents | In the realm of artificial intelligence, where a vast majority of data is unstructured, obtaining substantial amounts of labeled data to train supervised machine learning models poses a significant challenge. To address this, we delve into few-shot and active learning, where are goal is to improve AI models with human feedback on a few labeled examples. This paper focuses on understanding how a continuous feedback loop can refine models, thereby enhancing their accuracy, recall, and precision through incremental human input. By employing Large Language Models (LLMs) such as GPT-3.5, BERT, and SetFit, we aim to analyze the efficacy of using a limited number of labeled examples to substantially improve model accuracy. We benchmark this approach on the Financial Phrasebank, Banking, Craigslist, Trec, Amazon Reviews datasets to prove that with just a few labeled examples, we are able to surpass the accuracy of zero shot large language models to provide enhanced text classification performance. We demonstrate that rather than needing to manually label millions of rows of data, we just need to label a few and the model can effectively predict the rest. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_09555 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improving Classification Performance With Human Feedback: Label a few, we label the rest Vidra, Natan Clifford, Thomas Jijo, Katherine Chung, Eden Zhang, Liang Machine Learning Artificial Intelligence Computation and Language In the realm of artificial intelligence, where a vast majority of data is unstructured, obtaining substantial amounts of labeled data to train supervised machine learning models poses a significant challenge. To address this, we delve into few-shot and active learning, where are goal is to improve AI models with human feedback on a few labeled examples. This paper focuses on understanding how a continuous feedback loop can refine models, thereby enhancing their accuracy, recall, and precision through incremental human input. By employing Large Language Models (LLMs) such as GPT-3.5, BERT, and SetFit, we aim to analyze the efficacy of using a limited number of labeled examples to substantially improve model accuracy. We benchmark this approach on the Financial Phrasebank, Banking, Craigslist, Trec, Amazon Reviews datasets to prove that with just a few labeled examples, we are able to surpass the accuracy of zero shot large language models to provide enhanced text classification performance. We demonstrate that rather than needing to manually label millions of rows of data, we just need to label a few and the model can effectively predict the rest. |
| title | Improving Classification Performance With Human Feedback: Label a few, we label the rest |
| topic | Machine Learning Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2401.09555 |