- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This work presents FLOORA. It is a small domain‑specific language‑model family for multi‑family residential architectural floor‑layout generation. The authors design a compact, parsable domain‑specific language to represent building massing and floor‑plan geometry, which is far more token‑efficient than standard IFC BIM formats. The authors release datasets, model weights and inference code, and suggest this domain‑specialized recipe may transfer to other engineering structured‑generation tasks.
Critical strengths
-
Most prior architectural generative work uses either pure rule‑based optimization or only human‑preference reward. However, this paper carefully normalizes reward‑model outputs to prevent learned reward from overwhelming hard constraint rewards, achieving both architectural subjective quality and formal geometric validity.
-
The authors find that reward‑model benefits depend on model capacity, which is an important empirical observation for domain‑specific RLHF.
-
Compared with verbose industry IFC standards, the DSL achieves ~15× text compression and 54% shorter average token sequences.
Critical weaknesses
-
While labeling protocols and filtering steps are thoroughly described, the raw human feedback dataset (SFT edited layouts and pairwise preference data) is not released.
-
The paper hypothesizes the recipe generalizes to other engineering domains, but there is no preliminary empirical cross‑domain evidence to back this claim.
-
Readers cannot assess how transferable this full pipeline would be for other structured engineering generation problems.
Questions for authors
-
For the reward‑model normalization hyper‑parameter α=3 selected in GRPO: in practical deployment across different model sizes, do you observe that the optimal α value shifts with model capacity? Could you give practical guidance for picking α when adapting this hybrid‑reward setup to new domain tasks?
-
Regarding the unreleased human feedback dataset: are there licensing or privacy constraints preventing release? Would it be feasible to release anonymized?