A Survey on the Honesty of Large Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913521251385344 |
|---|---|
| author | Li, Siheng Yang, Cheng Wu, Taiqiang Shi, Chufan Zhang, Yuji Zhu, Xinyu Cheng, Zesen Cai, Deng Yu, Mo Liu, Lemao Zhou, Jie Yang, Yujiu Wong, Ngai Wu, Xixin Lam, Wai |
| author_facet | Li, Siheng Yang, Cheng Wu, Taiqiang Shi, Chufan Zhang, Yuji Zhu, Xinyu Cheng, Zesen Cai, Deng Yu, Mo Liu, Lemao Zhou, Jie Yang, Yujiu Wong, Ngai Wu, Xixin Lam, Wai |
| contents | Honesty is a fundamental principle for aligning large language models (LLMs) with human values, requiring these models to recognize what they know and don't know and be able to faithfully express their knowledge. Despite promising, current LLMs still exhibit significant dishonest behaviors, such as confidently presenting wrong answers or failing to express what they know. In addition, research on the honesty of LLMs also faces challenges, including varying definitions of honesty, difficulties in distinguishing between known and unknown knowledge, and a lack of comprehensive understanding of related research. To address these issues, we provide a survey on the honesty of LLMs, covering its clarification, evaluation approaches, and strategies for improvement. Moreover, we offer insights for future research, aiming to inspire further exploration in this important area. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_18786 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Survey on the Honesty of Large Language Models Li, Siheng Yang, Cheng Wu, Taiqiang Shi, Chufan Zhang, Yuji Zhu, Xinyu Cheng, Zesen Cai, Deng Yu, Mo Liu, Lemao Zhou, Jie Yang, Yujiu Wong, Ngai Wu, Xixin Lam, Wai Computation and Language Artificial Intelligence Honesty is a fundamental principle for aligning large language models (LLMs) with human values, requiring these models to recognize what they know and don't know and be able to faithfully express their knowledge. Despite promising, current LLMs still exhibit significant dishonest behaviors, such as confidently presenting wrong answers or failing to express what they know. In addition, research on the honesty of LLMs also faces challenges, including varying definitions of honesty, difficulties in distinguishing between known and unknown knowledge, and a lack of comprehensive understanding of related research. To address these issues, we provide a survey on the honesty of LLMs, covering its clarification, evaluation approaches, and strategies for improvement. Moreover, we offer insights for future research, aiming to inspire further exploration in this important area. |
| title | A Survey on the Honesty of Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2409.18786 |