Mis-prompt: Benchmarking Large Language Models for Proactive Error Handling
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918041082658816 |
|---|---|
| author | Zeng, Jiayi Feng, Yizhe He, Mengliang Lei, Wenhui Zhang, Wei Liu, Zeming Shi, Xiaoming Zhou, Aimin |
| author_facet | Zeng, Jiayi Feng, Yizhe He, Mengliang Lei, Wenhui Zhang, Wei Liu, Zeming Shi, Xiaoming Zhou, Aimin |
| contents | Large language models (LLMs) have demonstrated significant advancements in error handling. Current error-handling works are performed in a passive manner, with explicit error-handling instructions. However, in real-world scenarios, explicit error-handling instructions are usually unavailable. In this paper, our work identifies this challenge as how to conduct proactive error handling without explicit error handling instructions. To promote further research, this work introduces a new benchmark, termed Mis-prompt, consisting of four evaluation tasks, an error category taxonomy, and a new evaluation dataset. Furthermore, this work analyzes current LLMs' performance on the benchmark, and the experimental results reveal that current LLMs show poor performance on proactive error handling, and SFT on error handling instances improves LLMs' proactive error handling capabilities. The dataset will be publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_00064 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Mis-prompt: Benchmarking Large Language Models for Proactive Error Handling Zeng, Jiayi Feng, Yizhe He, Mengliang Lei, Wenhui Zhang, Wei Liu, Zeming Shi, Xiaoming Zhou, Aimin Computation and Language Artificial Intelligence Large language models (LLMs) have demonstrated significant advancements in error handling. Current error-handling works are performed in a passive manner, with explicit error-handling instructions. However, in real-world scenarios, explicit error-handling instructions are usually unavailable. In this paper, our work identifies this challenge as how to conduct proactive error handling without explicit error handling instructions. To promote further research, this work introduces a new benchmark, termed Mis-prompt, consisting of four evaluation tasks, an error category taxonomy, and a new evaluation dataset. Furthermore, this work analyzes current LLMs' performance on the benchmark, and the experimental results reveal that current LLMs show poor performance on proactive error handling, and SFT on error handling instances improves LLMs' proactive error handling capabilities. The dataset will be publicly available. |
| title | Mis-prompt: Benchmarking Large Language Models for Proactive Error Handling |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2506.00064 |