PROMPT ENGINEERING

→ View original post on X — @thatroblennon

Link to copyable prompts available at bottom

By

@thatroblennon

–

14 January 2023 17h39

If you look at the bottom you will find a link with all the prompts to copy paste

→ View original post on X — @langchain

LangChain Adds Custom Prompt Support for LLMBash API QAEval

By

@langchain

–

14 January 2023 17h15

Custom prompts for LLMBash, API, and QAEval chains – @nickscamara_ Francisco Ingham Continuing the trend from yesterday, more chains now have the ability to pass in custom prompts! LLMBash: https://
langchain.readthedocs.io/en/latest/modu
les/chains/examples/llm_bash.html#customize-prompt
… QAEval: https://
langchain.readthedocs.io/en/latest/use_
cases/evaluation/question_answering.html#customize-prompt
…

Fine-tuning diverse high-quality data for better AI generalization

By

–

14 January 2023 16h15

5. Finetune Finetune with diverse, high-quality, and task-specific to help the model generalize better and avoid hallucination.

External Filters Add Constraints to Improve AI Text Generation

By

–

14 January 2023 16h15

4. External Filters Add specific constraints or thresholds on generated text to filter out the unrealistic or non-sensical generated output.

Limit predicted tokens to reduce AI hallucination risks

By

–

14 January 2023 16h15

3. Limit the number of predicted tokens When generating text, limit the number of tokens the model is allowed to generate. The longer the text generation process, the higher the risk of hallucination.

Provide More Context to Reduce AI Model Hallucination

By

–

14 January 2023 16h15

1. Provide more context When providing input to the model, try to include as much context as possible. This will help the model understand the task better and reduce the likelihood of hallucination.

Five Practical Tips to Reduce LLM Hallucination

By

–

14 January 2023 16h15

Large language models like GPT-3 have a tendency to "hallucinate" or generate text that is not based on the input data and is not accurate. Here are five practical tips to reduce hallucination in LLMs. (A thread)