# [테디노트 2탄] 라이브 소식 & 자료 모음

### **[Teddy's Note 2탄] 라이브 소식 & 자료 모음 **

****

안녕하세요. 

12/4일 오늘 저녁 9시에 **테디노트의 테디님과 함께 라이브 방송 2탄을 **하게 되었습니다.

오늘 방송에서는,

- **프롬프트 정성/정량 평가**

- **프롬프트 최적화 **

- **sLM 프롬프트 엔지니어링  (with Upstage's Solar-Pro) **

세 가지 메인 주제와 함께,   

FastCampus 의 오프라인 프롬프트 엔지니어링 수업을 수강했던 분들의 허락을 구한, 

**우수 프롬프트 제작 사례**를 소개 합니다. 

연말의 하루를 "프롬프트"로 꽉 채울 수 있기를 기대하면서, 

함께해주세요.  ❣️ 

여기서요: [https://www.youtube.com/watch?v=iuhXs4iHLdk](https://www.youtube.com/watch?v=iuhXs4iHLdk) 

 

---

오늘 라이브에서 사용 할 논문(및 자료 출처)를 모았습니다.

**References **

- **A Survey on Evaluation of Large Language Models**

Chang, Y., Wang, X., Wang, J., Wu, Y., Yang, L., Zhu, K., ... & Xie, X. (2024). A survey on evaluation of large language models. ACM Transactions on Intelligent Systems and Technology, 15(3), 1-45.

[A Survey on Evaluation of Large Language Models](https://arxiv.org/abs/2307.03109)

[https://arxiv.org/pdf/2307.03109](https://arxiv.org/pdf/2307.03109)

- **Automated Prompt Engineering for Semantic Vulnerabilities in Large Language Models**

[https://www.authorea.com/users/813729/articles/1214990-automated-prompt-engineering-for-semantic-vulnerabilities-in-large-language-models](https://www.authorea.com/users/813729/articles/1214990-automated-prompt-engineering-for-semantic-vulnerabilities-in-large-language-models) 

[https://www.authorea.com/users/813729/articles/1214990-automated-prompt-engineering-for-semantic-vulnerabilities-in-large-language-models](https://www.authorea.com/users/813729/articles/1214990-automated-prompt-engineering-for-semantic-vulnerabilities-in-large-language-models)

- Chiang, W. L., Zheng, L., Sheng, Y., Angelopoulos, A. N., Li, T., Li, D., ... & Stoica, I. (2024). Chatbot arena: An open platform for evaluating llms by human preference. arXiv preprint arXiv:2403.04132. 

[Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://arxiv.org/abs/2403.04132)

[Automate document processing with Amazon Bedrock Prompt Flows (preview) | Amazon Web Services](https://aws.amazon.com/blogs/machine-learning/automate-document-processing-with-amazon-bedrock-prompt-flows-preview/)

- Razeghi, Y., Logan IV, R. L., Gardner, M., & Singh, S. (2022). Impact of pretraining term frequencies on few-shot reasoning. arXiv preprint arXiv:2202.07206. 

[Impact of Pretraining Term Frequencies on Few-Shot Reasoning](https://arxiv.org/abs/2202.07206)

- Wahle, J. P., Ruas, T., Xu, Y., & Gipp, B. (2024). Paraphrase Types Elicit Prompt Engineering Capabilities. arXiv preprint arXiv:2406.19898.

[Paraphrase Types Elicit Prompt Engineering Capabilities](https://arxiv.org/abs/2406.19898)

- Zheng, M., Pei, J., Logeswaran, L., Lee, M., & Jurgens, D. (2024, November). When” A Helpful Assistant” Is Not Really Helpful: Personas in System Prompts Do Not Improve Performances of Large Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2024 (pp. 15126-15154).

[When "A Helpful Assistant" Is Not Really Helpful: Personas...](https://arxiv.org/abs/2311.10054)

- Jin, M., Yu, Q., Shu, D., Zhao, H., Hua, W., Meng, Y., ... & Du, M. (2024). The impact of reasoning step length on large language models. arXiv preprint arXiv:2401.04925.

[The Impact of Reasoning Step Length on Large Language Models](https://arxiv.org/abs/2401.04925)

---

못다한, **수강생의 베스트 프롬프트 자료**입니다. 

프롬프트는, 슬래시페이지에서도 보실 수 있습니다. 

프롬프트엔지니어링_오프라인_실습_우수과제 (1).pdf

For the site tree, see the [root Markdown](https://slashpage.com/sujin-prompt-engineer.md).