Multiple paper suggestions

[trigaten]

Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback
Active Prompting with Chain-of-Thought for Large Language Models
More than you've asked for: A Comprehensive Analysis of Novel Prompt Injection Threats to Application-Integrated Large Language Models
Guiding Large Language Models via Directional Stimulus Prompting
When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment

[trigaten]

https://arxiv.org/pdf/2302.12813.pdf
Augment with search, also rl

https://arxiv.org/pdf/2302.12246.pdf
CoT bad for complex reasoning
Selecting exemplars, seems complex

https://arxiv.org/pdf/2302.11520.pdf
Generate partial, helping stimulus prompt, not LP

https://arxiv.org/pdf/2210.01478.pdf
Moral decision making, maybe add reference in reliability section

https://arxiv.org/pdf/2302.12173.pdf
Very cool, about different types of injections, direct, indirect, etc.

https://arxiv.org/pdf/2303.11315.pdf
Good fit for learn prompting
Deal w knowledge conflict and prediction with abstention
Through prompting