AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

PLaID++: A Preference Aligned Language Model for Targeted Inorganic Materials Design

Andy Xu, Rohan Desai, Larry Wang, Ethan T. Ritz, Gabriel Hope

ICML 2026 · Large language models › Language, safety and interpretability · approach: Data and evaluation methodology · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use Wyckoff text instead of 3D coordinates (ablation)PLaID++ SFT · MP-20 unconditionalS.U.N. (%): 2.81 -> 3.58Improved
use Wyckoff text instead of 3D coordinates (ablation)PLaID++ DPO · MP-20 unconditionalS.U.N. (%): 1.69 -> 6.25Improved
run more DPO iterations on 3D coordinate representation (ablation)PLaID++ 3D Coord · MP-20 unconditionalS.U.N. (%): 2.93 -> 2.23 -> 1.69Hurt
run more DPO iterations on 3D coordinate representation (ablation)PLaID++ 3D Coord · MP-20 unconditionalstability (%): 10.35 -> 13.47 -> 15.94Improved
use DPO instead of iterative SFT (ablation)PLaID++ Wyckoff · MP-20 unconditionalstability (%): 9.85 -> 15.59Improved
add DPO to Wyckoff SFT model (ablation)PLaID++ Wyckoff · MP-20 unconditionalS.U.N. (%): 3.58 -> 6.25Improved
add dynamic temperature adjustment and joint training (ablation)PLaID++ Stability + Novelty · MP-20 unconditionalstability (%): 16.72 -> 22.27Improved
add dynamic temperature adjustment and joint training (ablation)PLaID++ Stability + Novelty · MP-20 unconditionalS.U.N. (%): 6.22 -> 7.74Improved
train DPO jointly on bulk modulus, stability, novelty and space group instead of bulk modulus only (ablation)PLaID++ · Bulk modulus >325 GPacount high BM & S.U.N.: 28 -> 40Improved
add DPO on space-group pairs plus unconditional data (ablation)PLaID++ Wyckoff · Space group conditioned generationS.S.U.N.: 22% -> 47%Improved
apply DPO on low-data space groups (Amm2, P6_3/mmc)PLaID++ · Space group conditioned generationS.S.U.N.No clear effect
apply one DPO iteration for band gap preferencePLaID++ · Band gap >3 eVS.U.N. count: 0 -> 3Improved

Later papers that compared with this method

1 later accepted paper reports PLAID as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy