Reliable Decision Making via Calibration Oriented Retrieval Augmented Generation
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_ | 1866911211436638208 |
|---|---|
| author | Jang, Chaeyun Cho, Deukhwan Lee, Seanie Lee, Hyungi Lee, Juho |
| author_facet | Jang, Chaeyun Cho, Deukhwan Lee, Seanie Lee, Hyungi Lee, Juho |
| contents | Recently, Large Language Models (LLMs) have been increasingly used to support various decision-making tasks, assisting humans in making informed decisions. However, when LLMs confidently provide incorrect information, it can lead humans to make suboptimal decisions. To prevent LLMs from generating incorrect information on topics they are unsure of and to improve the accuracy of generated content, prior works have proposed Retrieval Augmented Generation (RAG), where external documents are referenced to generate responses. However, previous RAG methods focus only on retrieving documents most relevant to the input query, without specifically aiming to ensure that the human user's decisions are well-calibrated. To address this limitation, we propose a novel retrieval method called Calibrated Retrieval-Augmented Generation (CalibRAG), which ensures that decisions informed by RAG are well-calibrated. Then we empirically validate that CalibRAG improves calibration performance as well as accuracy, compared to other baselines across various datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_08891 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Reliable Decision Making via Calibration Oriented Retrieval Augmented Generation Jang, Chaeyun Cho, Deukhwan Lee, Seanie Lee, Hyungi Lee, Juho Information Retrieval Artificial Intelligence Recently, Large Language Models (LLMs) have been increasingly used to support various decision-making tasks, assisting humans in making informed decisions. However, when LLMs confidently provide incorrect information, it can lead humans to make suboptimal decisions. To prevent LLMs from generating incorrect information on topics they are unsure of and to improve the accuracy of generated content, prior works have proposed Retrieval Augmented Generation (RAG), where external documents are referenced to generate responses. However, previous RAG methods focus only on retrieving documents most relevant to the input query, without specifically aiming to ensure that the human user's decisions are well-calibrated. To address this limitation, we propose a novel retrieval method called Calibrated Retrieval-Augmented Generation (CalibRAG), which ensures that decisions informed by RAG are well-calibrated. Then we empirically validate that CalibRAG improves calibration performance as well as accuracy, compared to other baselines across various datasets. |
| title | Reliable Decision Making via Calibration Oriented Retrieval Augmented Generation |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2411.08891 |