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

• URL: http://arxiv.org/abs/2509.07150v2
• Date: Fri, 17 Oct 2025 04:59:57 GMT
• Title: PLaID++: A Preference Aligned Language Model for Targeted Inorganic Materials Design
• Abstract summary: We introduce PLaID++, an LLM post-trained for stable and property-guided crystal generation.<n>We find that performance hinges on our crystallographic representation and reward formulation.
• Score: 0.1408690282236036
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a promising approach to improve correctness in LLMs, however, in many scientific problems, the objective is not necessarily to produce the correct answer, but instead to produce a diverse array of candidates which satisfy a set of constraints. We study this challenge in the context of materials generation. To this end, we introduce PLaID++, an LLM post-trained for stable and property-guided crystal generation. We find that performance hinges on our crystallographic representation and reward formulation. First, we introduce a compact, symmetry-informed Wyckoff text representation which improves computational efficiency and encourages generalization from physical priors. Second, we demonstrate that temperature scaling acts as an entropy regularizer which counteracts mode collapse and encourages exploration. By encoding symmetry constraints directly into text and guiding model outputs towards desirable chemical space, PLaID++ generates structures that are thermodynamically stable, unique, and novel at a $\sim$50\% greater rate than prior methods and conditionally generates structures with desired space group properties. Our work demonstrates the potential of adapting post-training techniques from natural language processing to materials design, paving the way for targeted and efficient discovery of novel materials.

Related papers

• FormuEvo: LLM-Guided Evolution for Discovering Solver-Efficient Mixed-Integer Programming Formulations [66.32852384262038]
  Mixed-integer programming (MIP) lies at the core of operations research and industrial optimization.<n>We propose FormuEvo, an evolutionary framework for automated discovery of solver-efficient MIP formulations.<n>FormuEvo frames MIP formulation design as evolutionary optimization over the symbolic space of MIP formulations.
  arXiv  Detail & Related papers  (2026-08-24T15:01:28Z)
• Weave of Formal Thought [51.56484100374058]
  We introduce Weave of Formal Thought (WoFT), a paradigm uniting rigorous syntactic validation with learned structural representations.<n>We present a latent-variable fine-tuning method training the language model to interleave non-terminal grammar symbols directly into generation.<n>For Python, fine-tuning StarCoder2-3B with our RWS objective reduces per-token cross-entropy by 14.3% relative to a text-only SFT baseline.
  arXiv  Detail & Related papers  (2026-06-24T15:58:11Z)
• Towards Automated Discovery: A Review of Generative Models, Multimodal Learning and Closed-Loop Workflows in Inverse Materials Design [0.528869303898094]
  We review advances in generative crystal structure modeling, multimodal learning, and closed-loop design pipelines for crystalline solids.<n>We discuss how multimodal learning fuses diverse materials modalities, including crystal structures, thermodynamic, electronic information, microscopy, spectroscopy, processing context, and scientific text.<n>We highlight recurring failure modes, such as surrogate exploitation, diversity collapse, distribution shift, and the stability-synthesizability gap.
  arXiv  Detail & Related papers  (2026-06-01T17:20:55Z)
• STABLE: Simulation-Ready Tabletop Layout Generation via a Semantics-Physics Dual System [76.3920413336862]
  We present STABLE, a semantics-physics dual-system tailored for simulation-ready tabletop scene generation.<n>STABLE consists of two complementary modules: a Semantic Reasoner and a Physics Corrector.<n> Experiments demonstrate that STABLE successfully generates simulation-ready tabletop scenes that strictly conform to task instructions.
  arXiv  Detail & Related papers  (2026-05-15T16:18:42Z)
• CrystalReasoner: Reasoning and RL for Property-Conditioned Crystal Structure Generation [7.340047961454058]
  We propose CrystalReasoner (CrysReas), an end-to-end LLM framework that generates crystal structures from natural language instructions through reasoning and alignment.<n>CrysReas introduces physical priors as thinking tokens, which include crystallographic symmetry, local coordination environments and predicted physical properties before generating atomic coordinates.<n>For property-conditioned tasks, we design task-specific reward functions and train specialized models for discrete constraints and continuous properties.
  arXiv  Detail & Related papers  (2026-05-14T04:08:51Z)
• LLM-Based Scientific Equation Discovery via Physics-Informed Token-Regularized Policy Optimization [32.24464649397858]
  PiT-PO is a unified framework that evolves the Large Language Models into an adaptive generator via reinforcement learning.<n>Central to PiT-PO is a dual-constraint mechanism that rigorously enforces hierarchical physical validity while simultaneously applying fine-grained, token-level penalties to suppress redundant structures.<n> Empirically, PiT-PO achieves state-of-the-art performance on standard benchmarks and successfully discovers novel turbulence models for challenging fluid dynamics problems.
  arXiv  Detail & Related papers  (2026-02-11T07:02:23Z)
• Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning [59.11663802446183]
  Flow and diffusion generative models can be adapted to optimize task-specific objectives while preserving prior information.<n>We introduce Flow Density Control (FDC), a simple algorithm that reduces this complex problem to a specific sequence of simpler fine-tuning tasks.<n>We derive convergence guarantees for the proposed scheme under realistic assumptions by leveraging recent understanding of mirror flows.
  arXiv  Detail & Related papers  (2025-11-27T17:19:01Z)
• CLOUD: A Scalable and Physics-Informed Foundation Model for Crystal Representation Learning [0.0]
  We introduce CLOUD (Crystal Language mOdel for Unified and Differentiable materials modeling), a transformer-based framework trained on a novel Symmetry-Consistent SCOPE (SCOPE)<n>CLOUD is pre-trained on over six million crystal structures and achieves competitive performance in predicting a wide range of material properties.<n>As proof of concept of differentiable materials modeling, CLOUD is applied to predict the phonon internal energy and heat capacity.
  arXiv  Detail & Related papers  (2025-06-19T15:45:24Z)
• AI-Assisted Rapid Crystal Structure Generation Towards a Target Local Environment [5.169292784037981]
  We present a symmetry-informed AI generative approach called Local Environment Geometry-Oriented Crystal Generator (LEGO-xtal)<n>Our method generates initial structures using AI models trained on an augmented small dataset.<n>We demonstrate the effectiveness of LEGO-xtal by expanding from 25 known low-energy sp2 carbon allotropes to over 1,700, all within 0.5 eV/atom of the ground-state energy of graphite.
  arXiv  Detail & Related papers  (2025-06-09T20:47:36Z)
• Reparameterized LLM Training via Orthogonal Equivalence Transformation [54.80172809738605]
  We present POET, a novel training algorithm that uses Orthogonal Equivalence Transformation to optimize neurons.<n>POET can stably optimize the objective function with improved generalization.<n>We develop efficient approximations that make POET flexible and scalable for training large-scale neural networks.
  arXiv  Detail & Related papers  (2025-06-09T17:59:34Z)
• InvDesFlow-AL: Active Learning-based Workflow for Inverse Design of Functional Materials [10.518405572411286]
  We propose a novel inverse material design generative framework called InvDesFlow-AL, which is based on active learning strategies.<n>In terms of crystal structure prediction, the InvDesFlow-AL model achieves an RMSE of 0.0423 AA-AL representing an 32.96% improvement in performance compared to exsisting generative models.<n>InvDesFlow-AL has been successfully validated in the design of low-formation-energy and low-Ehull materials.
  arXiv  Detail & Related papers  (2025-05-14T07:29:06Z)
• Penrose Tiled Low-Rank Compression and Section-Wise Q&A Fine-Tuning: A General Framework for Domain-Specific Large Language Model Adaptation [7.161207910629032]
  Large language models (LLMs) hold great promise for specialized scientific domains such as materials science.<n>We propose a two-stage framework that combines structured model compression with a scientific fine-tuning regimen to address this challenge.
  arXiv  Detail & Related papers  (2025-03-28T01:33:05Z)
• Al-Khwarizmi: Discovering Physical Laws with Foundation Models [6.07593567400172]
  Inferring physical laws from data is a central challenge in science and engineering.<n>This work introduces Al-Khwarizmi, a novel agentic framework for physical law discovery from data.
  arXiv  Detail & Related papers  (2025-02-03T09:54:00Z)
• Establishing baselines for generative discovery of inorganic crystals [0.0]
  Generative artificial intelligence offers a promising avenue for materials discovery, yet its advantages over traditional methods remain unclear.<n>In this work, we introduce and benchmark two baseline approaches - random enumeration of charge-balanced prototypes and data-driven ion exchange of known compounds.<n>Our results show that established methods such as ion exchange are better at generating novel materials that are stable, although many of these closely resemble known compounds.
  arXiv  Detail & Related papers  (2025-01-04T00:14:59Z)
• Self-Improvement in Language Models: The Sharpening Mechanism [70.9248553790022]
  We offer a new perspective on the capabilities of self-improvement through a lens we refer to as sharpening.<n>Motivated by the observation that language models are often better at verifying response quality than they are at generating correct responses, we formalize self-improvement as using the model itself as a verifier during post-training.<n>We analyze two natural families of self-improvement algorithms based on SFT and RLHF.
  arXiv  Detail & Related papers  (2024-12-02T20:24:17Z)
• Efficient Symmetry-Aware Materials Generation via Hierarchical Generative Flow Networks [52.13486402193811]
  New solid-state materials require rapidly exploring the vast space of crystal structures and locating stable regions. Existing methods struggle to explore large material spaces and generate diverse samples with desired properties and requirements. We propose a novel generative model employing a hierarchical exploration strategy to efficiently exploit the symmetry of the materials space to generate crystal structures given desired properties.
  arXiv  Detail & Related papers  (2024-11-06T23:53:34Z)
• Unleashing the power of novel conditional generative approaches for new materials discovery [3.972733741872872]
  We propose two generative approaches to the problem of crystal structure design. One is conditional structure modification, using the energy difference between the most energetically favorable structure and all its less stable polymorphs. The other is conditional structure generation, using the energy difference between the most energetically favorable structure and all its less stable polymorphs.
  arXiv  Detail & Related papers  (2024-11-05T14:58:31Z)
• In-context Demonstration Matters: On Prompt Optimization for Pseudo-Supervision Refinement [71.60563181678323]
  Large language models (LLMs) have achieved great success across diverse tasks, and fine-tuning is sometimes needed to further enhance generation quality.<n>To handle these challenges, a direct solution is to generate high-confidence'' data from unsupervised downstream tasks.<n>We propose a novel approach, pseudo-supervised demonstrations aligned prompt optimization (PAPO) algorithm, which jointly refines both the prompt and the overall pseudo-supervision.
  arXiv  Detail & Related papers  (2024-10-04T03:39:28Z)
• DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization [49.85944390503957]
  DecompOpt is a structure-based molecular optimization method based on a controllable and diffusion model. We show that DecompOpt can efficiently generate molecules with improved properties than strong de novo baselines.
  arXiv  Detail & Related papers  (2024-03-07T02:53:40Z)
• Molecule Design by Latent Prompt Transformer [76.2112075557233]
  This work explores the challenging problem of molecule design by framing it as a conditional generative modeling task. We propose a novel generative model comprising three components: (1) a latent vector with a learnable prior distribution; (2) a molecule generation model based on a causal Transformer, which uses the latent vector as a prompt; and (3) a property prediction model that predicts a molecule's target properties and/or constraint values using the latent prompt.
  arXiv  Detail & Related papers  (2024-02-27T03:33:23Z)
• Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement [67.1393112206885]
  Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. We introduce Entropy-Regularized Token-level Policy Optimization (ETPO), an entropy-augmented RL method tailored for optimizing LLMs at the token level. We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks.
  arXiv  Detail & Related papers  (2024-02-09T07:45:26Z)
• Fine-Tuned Language Models Generate Stable Inorganic Materials as Text [53.81190146434045]
  Fine-tuning large language models on text-encoded atomistic data is simple to implement yet reliable.<n>We show that our strongest model can generate materials predicted to be metastable at about twice the rate of CDVAE.<n>Because of text prompting's inherent flexibility, our models can simultaneously be used for unconditional generation of stable material.
  arXiv  Detail & Related papers  (2024-02-06T20:35:28Z)
• Latent Conservative Objective Models for Data-Driven Crystal Structure Prediction [62.36797874900395]
  In computational chemistry, crystal structure prediction is an optimization problem. One approach to tackle this problem involves building simulators based on density functional theory (DFT) followed by running search in simulation. We show that our approach, dubbed LCOMs (latent conservative objective models), performs comparably to the best current approaches in terms of success rate of structure prediction.
  arXiv  Detail & Related papers  (2023-10-16T04:35:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.