Beyond Static Evaluation: A Dynamic Approach to Assessing AI Assistants' API Invocation Capabilities
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_ | 1866911815667023872 |
|---|---|
| author | Mu, Honglin Xu, Yang Feng, Yunlong Han, Xiaofeng Li, Yitong Hou, Yutai Che, Wanxiang |
| author_facet | Mu, Honglin Xu, Yang Feng, Yunlong Han, Xiaofeng Li, Yitong Hou, Yutai Che, Wanxiang |
| contents | With the rise of Large Language Models (LLMs), AI assistants' ability to utilize tools, especially through API calls, has advanced notably. This progress has necessitated more accurate evaluation methods. Many existing studies adopt static evaluation, where they assess AI assistants' API call based on pre-defined dialogue histories. However, such evaluation method can be misleading, as an AI assistant might fail in generating API calls from preceding human interaction in real cases. Instead of the resource-intensive method of direct human-machine interactions, we propose Automated Dynamic Evaluation (AutoDE) to assess an assistant's API call capability without human involvement. In our framework, we endeavor to closely mirror genuine human conversation patterns in human-machine interactions, using a LLM-based user agent, equipped with a user script to ensure human alignment. Experimental results highlight that AutoDE uncovers errors overlooked by static evaluations, aligning more closely with human assessment. Testing four AI assistants using our crafted benchmark, our method further mirrored human evaluation compared to conventional static evaluations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_11128 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Beyond Static Evaluation: A Dynamic Approach to Assessing AI Assistants' API Invocation Capabilities Mu, Honglin Xu, Yang Feng, Yunlong Han, Xiaofeng Li, Yitong Hou, Yutai Che, Wanxiang Computation and Language With the rise of Large Language Models (LLMs), AI assistants' ability to utilize tools, especially through API calls, has advanced notably. This progress has necessitated more accurate evaluation methods. Many existing studies adopt static evaluation, where they assess AI assistants' API call based on pre-defined dialogue histories. However, such evaluation method can be misleading, as an AI assistant might fail in generating API calls from preceding human interaction in real cases. Instead of the resource-intensive method of direct human-machine interactions, we propose Automated Dynamic Evaluation (AutoDE) to assess an assistant's API call capability without human involvement. In our framework, we endeavor to closely mirror genuine human conversation patterns in human-machine interactions, using a LLM-based user agent, equipped with a user script to ensure human alignment. Experimental results highlight that AutoDE uncovers errors overlooked by static evaluations, aligning more closely with human assessment. Testing four AI assistants using our crafted benchmark, our method further mirrored human evaluation compared to conventional static evaluations. |
| title | Beyond Static Evaluation: A Dynamic Approach to Assessing AI Assistants' API Invocation Capabilities |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2403.11128 |