Understanding the Relationship between Prompts and Response Uncertainty in Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915168684867584 |
|---|---|
| author | Zhang, Ze Yu Verma, Arun Doshi-Velez, Finale Low, Bryan Kian Hsiang |
| author_facet | Zhang, Ze Yu Verma, Arun Doshi-Velez, Finale Low, Bryan Kian Hsiang |
| contents | Large language models (LLMs) are widely used in decision-making, but their reliability, especially in critical tasks like healthcare, is not well-established. Therefore, understanding how LLMs reason and make decisions is crucial for their safe deployment. This paper investigates how the uncertainty of responses generated by LLMs relates to the information provided in the input prompt. Leveraging the insight that LLMs learn to infer latent concepts during pretraining, we propose a prompt-response concept model that explains how LLMs generate responses and helps understand the relationship between prompts and response uncertainty. We show that the uncertainty decreases as the prompt's informativeness increases, similar to epistemic uncertainty. Our detailed experimental results on real-world datasets validate our proposed model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_14845 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Understanding the Relationship between Prompts and Response Uncertainty in Large Language Models Zhang, Ze Yu Verma, Arun Doshi-Velez, Finale Low, Bryan Kian Hsiang Machine Learning Computation and Language Large language models (LLMs) are widely used in decision-making, but their reliability, especially in critical tasks like healthcare, is not well-established. Therefore, understanding how LLMs reason and make decisions is crucial for their safe deployment. This paper investigates how the uncertainty of responses generated by LLMs relates to the information provided in the input prompt. Leveraging the insight that LLMs learn to infer latent concepts during pretraining, we propose a prompt-response concept model that explains how LLMs generate responses and helps understand the relationship between prompts and response uncertainty. We show that the uncertainty decreases as the prompt's informativeness increases, similar to epistemic uncertainty. Our detailed experimental results on real-world datasets validate our proposed model. |
| title | Understanding the Relationship between Prompts and Response Uncertainty in Large Language Models |
| topic | Machine Learning Computation and Language |
| url | https://arxiv.org/abs/2407.14845 |