Training Chemical Plausibility-Aware Large Language Models for Single-Step Retrosynthesis

• URL: http://arxiv.org/abs/2608.18940v1
• Date: Wed, 19 Aug 2026 14:08:05 GMT
• Title: Training Chemical Plausibility-Aware Large Language Models for Single-Step Retrosynthesis
• Abstract summary: We introduce Top-K prompting as a robust training and inference paradigm to better capture diverse, plausible reaction predictions.<n>We compile CREED-CCV-2+USPTO-XL, an ultra-large-scale dataset of 45.6 million verified reactions to train the C3LM.
• Score: 3.841858001721215
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Single-step retrosynthesis is a central component of computer-aided synthesis planning, yet its intrinsically one-to-many nature is poorly captured by single-answer evaluation and benchmarking protocols. To address this, we introduce Top-K prompting as a robust training and inference paradigm to better capture diverse, plausible reaction predictions. We compile CREED-CCV-2+USPTO-XL, an ultra-large-scale dataset of ~45.6 million verified reactions to train the C3LM (Chemistry Constraint-Consistent Language Model). By integrating fine-tuning with ChemCensor-based and novelty-oriented rewards, our model achieves state-of-the-art performance on the OOD URSA-expert-2026 benchmark. Further analysis of reaction uniqueness shows that LLMs and conventional models explore complementary reaction spaces, motivating ensemble-based retrosynthesis systems. Overall, our results establish Top-K, plausibility-aware training as a practical new direction for robust future LLM-based synthesis planning.

Related papers

• URSA: Chemistry-Aware Benchmark for Utilitarian Retrosynthesis Assessment [3.6442441313881706]
  This study introduces the URSA (Utilitarian RetroSynthesis Assessment) evaluation framework.<n>It provides the opportunity to benchmark the synthetic routes not only from a formal perspective, but also from a chemical plausibility perspective.<n>The study covers a comprehensive evaluation of both conventional end-to-end retrosynthesis solutions and LLMs for the synthesis planning task.
  arXiv  Detail & Related papers  (2026-07-06T05:32:09Z)
• Molecular Identifier Visual Prompt and Verifiable Reinforcement Learning for Chemical Reaction Diagram Parsing [52.825281124618535]
  Reaction diagram parsing (RxnDP) is critical for extracting chemical synthesis information from literature.<n>Recent Vision-Language Models (VLMs) have emerged as a promising paradigm to automate this complex visual reasoning task.<n>This work enhances VLM-based RxnDP from two complementary perspectives: prompting representation and learning paradigms.
  arXiv  Detail & Related papers  (2026-03-16T09:17:05Z)
• RetroReasoner: A Reasoning LLM for Strategic Retrosynthesis Prediction [10.722337545605626]
  Retrosynthesis is a core task in organic synthesis that aims to predict reactants for a given product molecule.<n>We propose RetroReasoner, a retrosynthetic reasoning model that leverages chemists' strategic thinking.<n> Experimental results show that RetroReasoner not only outperforms prior baselines but also generates a broader range of feasible reactant proposals.
  arXiv  Detail & Related papers  (2026-03-13T05:20:56Z)
• When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs [3.973137925060284]
  We propose a new benchmarking framework for single-step retrosynthesis.<n>By emphasizing plausibility over exact match, this approach better aligns with human synthesis planning practices.<n>We also introduce CREED, a novel dataset comprising millions of ChemCensor-validated reaction records for LLM training.
  arXiv  Detail & Related papers  (2026-02-03T14:03:32Z)
• A Scientific Reasoning Model for Organic Synthesis Procedure Generation [12.609346156252393]
  We present QFANG, a scientific reasoning language model capable of generating precise, structured experimental procedures.<n>We introduce a Chemistry-Guided Reasoning (CGR) framework that produces chain-of-thought data grounded in chemical knowledge at scale.<n>We apply Reinforcement Learning from Verifiable Rewards (RLVR) to further enhance procedural accuracy.
  arXiv  Detail & Related papers  (2025-12-15T18:55:39Z)
• Round-trip Reinforcement Learning: Self-Consistent Training for Better Chemical LLMs [51.29260537017623]
  Large Language Models (LLMs) are emerging as versatile foundation models for computational chemistry.<n>These models often lack round-trip consistency.<n>We introduce Round-Trip Reinforcement Learning (RTRL), a novel framework that trains a model to improve its consistency.
  arXiv  Detail & Related papers  (2025-10-01T23:58:58Z)
• ChemActor: Enhancing Automated Extraction of Chemical Synthesis Actions with LLM-Generated Data [53.78763789036172]
  We present ChemActor, a fully fine-tuned large language model (LLM) as a chemical executor to convert between unstructured experimental procedures and structured action sequences.<n>This framework integrates a data selection module that selects data based on distribution divergence, with a general-purpose LLM, to generate machine-executable actions from a single molecule input.<n>Experiments on reaction-to-description (R2D) and description-to-action (D2A) tasks demonstrate that ChemActor achieves state-of-the-art performance, outperforming the baseline model by 10%.
  arXiv  Detail & Related papers  (2025-06-30T05:11:19Z)
• Enhancing Chemical Reaction and Retrosynthesis Prediction with Large Language Model and Dual-task Learning [8.402406301818905]
  Large language models (LLMs) have shown potential in many domains.<n>ChemDual is a novel framework for accurate chemical synthesis.<n>ChemDual achieves state-of-the-art performance in both predictions of reaction and retrosynthesis.
  arXiv  Detail & Related papers  (2025-05-05T13:31:36Z)
• BatGPT-Chem: A Foundation Large Model For Retrosynthesis Prediction [65.93303145891628]
  BatGPT-Chem is a large language model with 15 billion parameters, tailored for enhanced retrosynthesis prediction. Our model captures a broad spectrum of chemical knowledge, enabling precise prediction of reaction conditions. This development empowers chemists to adeptly address novel compounds, potentially expediting the innovation cycle in drug manufacturing and materials science.
  arXiv  Detail & Related papers  (2024-08-19T05:17:40Z)
• Retrosynthesis prediction enhanced by in-silico reaction data augmentation [66.5643280109899]
  We present RetroWISE, a framework that employs a base model inferred from real paired data to perform in-silico reaction generation and augmentation. On three benchmark datasets, RetroWISE achieves the best overall performance against state-of-the-art models.
  arXiv  Detail & Related papers  (2024-01-31T07:40:37Z)
• RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning [107.64562550844146]
  Retrosynthesis is an emerging research area of deep learning. We propose a new approach that reformulating retrosynthesis into a selection problem of reactants from a candidate set of commercially available molecules. For learning the score functions, we also propose a novel contrastive training scheme with hard negative mining.
  arXiv  Detail & Related papers  (2021-05-03T12:47:57Z)

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.