Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916740637655040 |
|---|---|
| author | Wu, Xuansheng Zhao, Haiyan Zhu, Yaochen Shi, Yucheng Yang, Fan Hu, Lijie Liu, Tianming Zhai, Xiaoming Yao, Wenlin Li, Jundong Du, Mengnan Liu, Ninghao |
| author_facet | Wu, Xuansheng Zhao, Haiyan Zhu, Yaochen Shi, Yucheng Yang, Fan Hu, Lijie Liu, Tianming Zhai, Xiaoming Yao, Wenlin Li, Jundong Du, Mengnan Liu, Ninghao |
| contents | Explainable AI (XAI) refers to techniques that provide human-understandable insights into the workings of AI models. Recently, the focus of XAI is being extended toward explaining Large Language Models (LLMs). This extension calls for a significant transformation in the XAI methodologies for two reasons. First, many existing XAI methods cannot be directly applied to LLMs due to their complexity and advanced capabilities. Second, as LLMs are increasingly deployed in diverse applications, the role of XAI shifts from merely opening the ``black box'' to actively enhancing the productivity and applicability of LLMs in real-world settings. Meanwhile, the conversation and generation abilities of LLMs can reciprocally enhance XAI. Therefore, in this paper, we introduce Usable XAI in the context of LLMs by analyzing (1) how XAI can explain and improve LLM-based AI systems and (2) how XAI techniques can be improved by using LLMs. We introduce 10 strategies, introducing the key techniques for each and discussing their associated challenges. We also provide case studies to demonstrate how to obtain and leverage explanations. The code used in this paper can be found at: https://github.com/JacksonWuxs/UsableXAI_LLM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_08946 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era Wu, Xuansheng Zhao, Haiyan Zhu, Yaochen Shi, Yucheng Yang, Fan Hu, Lijie Liu, Tianming Zhai, Xiaoming Yao, Wenlin Li, Jundong Du, Mengnan Liu, Ninghao Machine Learning Computation and Language Computers and Society Explainable AI (XAI) refers to techniques that provide human-understandable insights into the workings of AI models. Recently, the focus of XAI is being extended toward explaining Large Language Models (LLMs). This extension calls for a significant transformation in the XAI methodologies for two reasons. First, many existing XAI methods cannot be directly applied to LLMs due to their complexity and advanced capabilities. Second, as LLMs are increasingly deployed in diverse applications, the role of XAI shifts from merely opening the ``black box'' to actively enhancing the productivity and applicability of LLMs in real-world settings. Meanwhile, the conversation and generation abilities of LLMs can reciprocally enhance XAI. Therefore, in this paper, we introduce Usable XAI in the context of LLMs by analyzing (1) how XAI can explain and improve LLM-based AI systems and (2) how XAI techniques can be improved by using LLMs. We introduce 10 strategies, introducing the key techniques for each and discussing their associated challenges. We also provide case studies to demonstrate how to obtain and leverage explanations. The code used in this paper can be found at: https://github.com/JacksonWuxs/UsableXAI_LLM. |
| title | Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era |
| topic | Machine Learning Computation and Language Computers and Society |
| url | https://arxiv.org/abs/2403.08946 |