Applying What I Learned in AI Lectures to LLM Related Topics

• AI (COMSW4701)

• Search when generating something with LLM

• Make Every Move Count: LLM-based High-Quality RTL Code Generation Using MCTS

  • Like (blu3mo)

• Derivative of chain-of-thoughts

  • Various Derivatives of CoT

• It’s all about how to define rewards~~ (blu3mo)

  • Thinking about tasks that seem easy to define

• I might want to try this with a fictional paper title + abstract

  • Think about that chain
  • Wait, this is definitely going to be interesting (blu3mo)(blu3mo)(blu3mo)
  • Citations could be the reward or something

• Ideas to do later

  • It seems possible to create several types of researchers
    • Like technical type vs vision type, bottom-up vs top-down, etc.
    • It seems like updating the type=prompt itself genetically could be possible (blu3mo)(blu3mo)
  • “Conferences” could also be simulated

• It might be interesting in the context of SciSci as well

  • You could say, with this kind of system, this kind of paper was created

• Different from MCTS

  • Take 3
  • Instead of traversing the tree, just take the top 3 normally
  • Just taking them would make the leaf nodes grow too much, so exclude leaf nodes without 3
  • Want to lighten the weighting as you go down to descendants.
    • When there are two parents and there is a stretched lineage, it’s delicate for the score of the parent who hasn’t contributed much to increase
    • Like with α=0.7, multiply α^depth by the value to be added to count and sum

• => Simulation of Research Activities with LLM x Tree Search

• This could be interesting if integrated with human feedback

  • I remember discussing an idea with (ritar) about using gaze information
  • If it catches attention