Robust Knowledge Extraction from Large Language Models using Social Choice Theory
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914670941569024 |
|---|---|
| author | Potyka, Nico Zhu, Yuqicheng He, Yunjie Kharlamov, Evgeny Staab, Steffen |
| author_facet | Potyka, Nico Zhu, Yuqicheng He, Yunjie Kharlamov, Evgeny Staab, Steffen |
| contents | Large-language models (LLMs) can support a wide range of applications like conversational agents, creative writing or general query answering. However, they are ill-suited for query answering in high-stake domains like medicine because they are typically not robust - even the same query can result in different answers when prompted multiple times. In order to improve the robustness of LLM queries, we propose using ranking queries repeatedly and to aggregate the queries using methods from social choice theory. We study ranking queries in diagnostic settings like medical and fault diagnosis and discuss how the Partial Borda Choice function from the literature can be applied to merge multiple query results. We discuss some additional interesting properties in our setting and evaluate the robustness of our approach empirically. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_14877 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Robust Knowledge Extraction from Large Language Models using Social Choice Theory Potyka, Nico Zhu, Yuqicheng He, Yunjie Kharlamov, Evgeny Staab, Steffen Computation and Language Artificial Intelligence Large-language models (LLMs) can support a wide range of applications like conversational agents, creative writing or general query answering. However, they are ill-suited for query answering in high-stake domains like medicine because they are typically not robust - even the same query can result in different answers when prompted multiple times. In order to improve the robustness of LLM queries, we propose using ranking queries repeatedly and to aggregate the queries using methods from social choice theory. We study ranking queries in diagnostic settings like medical and fault diagnosis and discuss how the Partial Borda Choice function from the literature can be applied to merge multiple query results. We discuss some additional interesting properties in our setting and evaluate the robustness of our approach empirically. |
| title | Robust Knowledge Extraction from Large Language Models using Social Choice Theory |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2312.14877 |