Program-of-Thought Prompting Outperforms Chain-of-Thought by 15% (2022)

https://arxiv.org/abs/2211.12588

#HackerNews #ProgramOfThought #Prompting #ChainOfThought #AIResearch #MachineLearning #2022Study

Addendum 11

Making Large Language Models Better Reasoners w. Alignment
https://arxiv.org/abs/2309.02144

* reasoning: cognitive process; evidence-based conclusions
* fine-tuning LLM w. chain of thought (COT) reasoning sig. enhances reasoning
* h/e freq. assign higher scores to subpar COT
* Alignment Fine-Tuning; 3 steps: fine-tuning; multiple COT responses, cat. correct/incorrect; calibrating scores w. a constraint alignment loss

#LLM #LargeLanguageModels #ChainOfThought #ProgramOfThought #reasoning

Addendum 10

When Do Program-of-Thoughts Work for Reasoning?
https://arxiv.org/abs/2308.15452
https://github.com/zjunlp/EasyInstruct

* reasoning capabilities of large language models pivotal in embodied AI
* program-of-thought prompting for LLM uses programming language to tackle complex reasoning
* e.g. mathematical reasoning; code data filtering
* specific impact of code data on improvement of reasoning capabilities underexplored

#LLM #LargeLanguageModels #ChainOfThought #ProgramOfThought #reasoning #EasyInstruct