Introduction

In this post, we explore the use of Large Language Models (LLMs) in a feedback loop to enhance the quality of results through iterative cycles. The goal is to improve the initial intuitive results provided by LLMs by engaging in a cycle of feedback and optimization, extending beyond the internal feedback mechanisms of LLMs.

Concept

  • LLMs can improve results through self-feedback, a widely utilized feature. However, relying solely on a single user request for complete results is challenging. By re-requesting and exchanging feedback on initial results, we aim to enhance the quality of responses. This process involves not only internal feedback within the LLM but also feedback in a larger cycle that includes algorithms, continuously improving results.

  • Self-feedback outside LLM API In This Work:
    Flowchart
  • Self-feedback inside LLM API examples:
    llm_self_feedback_examples
  • Significance of Using LLMs:
    • Acts as a bridge between vague user needs and specific algorithmic criteria.
    • Understands cycle results and reflects them in subsequent cycles to improve responses.

Premises

  • Two Main Components:
    • LLM:
      • Used for intuitive selection.
      • Bridges the gap between the user’s relatively vague intentions and the optimizer’s specific criteria.
    • Heuristic Optimizer (GA):
      • Used for relatively specific optimization.
  • Use Cycles:
    • By repeating cycle execution, we aim to create a structure that approaches the intended results independently.

Details

  1. Parameter Conversion:
    • Convert intuitive selections into clear parameter inputs for algorithm input using LLM and structured output.

    • Adjust the number of additional subdivisions based on zone grid and grid size.

         number_additional_subdivision_x: int
   number_additional_subdivision_y: int

    • Prioritize placement close to boundaries for each use based on prompts.

         place_rest_close_to_boundary: bool
   place_office_close_to_boundary: bool
   place_lobby_close_to_boundary: bool
   place_coworking_close_to_boundary: bool

    • Ask about the desired percentage of mixture for different uses in adjacent patches.

         percentage_of_mixture: number

    • Inquire about the percentage each use should occupy.

         office: number
   coworking: number
   lobby: number
   rest: number
  2. Optimization Based on LLM Responses:
    • Use LLM responses as optimization criteria, transforming user thoughts into specific criteria.
  3. Incorporate Optimization Results into Next Cycle:
    • Insert optimization results as references when asking LLMs in the next cycle, reinforcing the significance of multiple [LLM answer - optimize results with the answer] cycles.
  4. Cycle Structure:
    • One Cycle:
      • First [LLM answer - optimize results with the answer]:
        • Ask LLM about subdivision criteria based on the prompt before optimizing zone usage.
      • Second [LLM answer - optimize results with the answer]:
        • Request intuitive answers from LLM regarding zone configuration based on the prompt.
    • After the Second Cycle:
      • After the second cycle, directly request improvement in responses by providing the actual optimization results along with the previous LLM responses.

Test Results

Case 1

  • Prompt:

    In a large space, the office spaces are gathered in the center for a common goal. I want to place the other spaces close to the boundary.

  • GIFs:

    0_1_zone_subdivision.gif 0_2_zone_placement.if 1_1_zone_subdivision.if 1_2_zone_placement.if 2_1_zone_subdivision.if 2_2_zone_placement.if 3_1_zone_subdivision.if 3_2_zone_placement.if 4_1_zone_subdivision.if 4_2_zone_placement.if

Case 2

  • Prompt:

      The goal is to have teams of about 5 people, working in silos.
  Therefore, we want mixed spaces where no single use is concentrated.

  • GIFs:

    0_1_zone_subdivision 1.if 0_2_zone_placement 1.if 1_1_zone_subdivision 1.if 1_2_zone_placement 1.if 2_1_zone_subdivision 1.if 2_2_zone_placement 1.if 3_1_zone_subdivision 1.if 3_2_zone_placement 1.if 4_1_zone_subdivision 1.if 4_2_zone_placement 1.if

Case 3

  • Prompt:

      Prioritize placing the office close to the boundary to easily receive sunlight, and place other spaces inside.

  • GIFs:

    0_1_zone_subdivision 2.if 0_2_zone_placement 2.if 1_1_zone_subdivision 2.if 1_2_zone_placement 2.if 2_1_zone_subdivision 2.if 2_2_zone_placement 2.if 3_1_zone_subdivision 2.if 3_2_zone_placement 2.if 4_1_zone_subdivision 2.if 4_2_zone_placement 2.if

Conclusion

This work aims to improve final results by expanding the scope of Self Feedback beyond LLMs to include LLM requests, optimization, and post-processing. As cycles repeat, results approach the intended outcomes, reducing the potential incompleteness of initial values relied upon by LLMs.