When Active Learning Falls Short: An Empirical Study on Chemical Reaction Extraction

• URL: http://arxiv.org/abs/2604.19335v1
• Date: Tue, 21 Apr 2026 11:10:03 GMT
• Title: When Active Learning Falls Short: An Empirical Study on Chemical Reaction Extraction
• Abstract summary: We conduct a systematic study of active learning for chemical reaction extraction.<n>We integrate six uncertainty- and diversity-based strategies with pretrained transformer-CRF architectures.<n>Our analysis shows that strong pretraining, structured CRF decoding, and label sparsity limit the stability of conventional active learning strategies.
• Score: 0.7734726150561088
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The rapid growth of chemical literature has generated vast amounts of unstructured data, where reaction information is particularly valuable for applications such as reaction predictions and drug design. However, the prohibitive cost of expert annotation has led to a scarcity of training data, severely hindering the performance of automatic reaction extraction. In this work, we conduct a systematic study of active learning for chemical reaction extraction. We integrate six uncertainty- and diversity-based strategies with pretrained transformer-CRF architectures, and evaluate them on product extraction and role labeling task. While several methods approach full-data performance with fewer labeled instances, learning curves are often non-monotonic and task-dependent. Our analysis shows that strong pretraining, structured CRF decoding, and label sparsity limit the stability of conventional active learning strategies. These findings provide practical insights for the effective use of active learning in chemical information extraction.

Related papers

• 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)
• Modular Multi-Task Learning for Chemical Reaction Prediction [1.443416244644791]
  Low-Rank Adaptation (LoRA) is a parameter-efficient alternative to full fine-tuning for organic reaction prediction.<n>LoRA achieves accuracy comparable to full fine-tuning while effectively mitigating catastrophic forgetting and better preserving multi-task performance.
  arXiv  Detail & Related papers  (2026-02-11T01:17:06Z)
• AgentCAT: An LLM Agent for Extracting and Analyzing Catalytic Reaction Data from Chemical Engineering Literature [55.66036140125613]
  This paper presents a large language model (LLM) agent named AgentCAT, which extracts and analyzes catalytic reaction data from chemical engineering papers.<n>AgentCAT serves as an alternative to overcome the long-standing data bottleneck in chemical engineering field.
  arXiv  Detail & Related papers  (2026-02-10T04:30:11Z)
• Chemical knowledge-informed framework for privacy-aware retrosynthesis learning [72.39098405805318]
  Current machine learning-based retrosynthesis gathers reaction data from multiple sources into one single edge to train prediction models.<n>This paradigm poses considerable privacy risks as it necessitates broad data availability across organizational boundaries.<n>In the present study, we introduce the chemical knowledge-informed framework (CKIF), a privacy-preserving approach for learning retrosynthesis models.
  arXiv  Detail & Related papers  (2025-02-26T13:13:24Z)
• A Self-feedback Knowledge Elicitation Approach for Chemical Reaction Predictions [24.80165173525286]
  We introduce a data-curated self-feedback knowledge elicitation approach. We employ adaptive prompt learning to infuse the prior knowledge into the large language model. This research offers a novel paradigm for knowledge elicitation in scientific research.
  arXiv  Detail & Related papers  (2024-04-15T09:26:33Z)
• Revealing the Relationship Between Publication Bias and Chemical Reactivity with Contrastive Learning [13.299207805882755]
  Training on 20,798 aryl halides in the CAS Content Collection$textTM$, spanning thousands of publications from 2010-2015, we demonstrate that the learned embeddings exhibit a correlation with physical organic reactivity descriptors.<n>This work not only presents a chemistry-specific machine learning training strategy to learn from data literature in a new way, but also represents a unique approach to uncover trends in chemical reactivity reflected by trends in substrate selection in publications.
  arXiv  Detail & Related papers  (2024-02-19T02:21:20Z)
• ReactIE: Enhancing Chemical Reaction Extraction with Weak Supervision [27.850325653751078]
  structured chemical reaction information plays a vital role for chemists engaged in laboratory work and advanced endeavors such as computer-aided drug design. Despite the importance of extracting structured reactions from scientific literature, data annotation for this purpose is cost-prohibitive due to the significant labor required from domain experts. We propose ReactIE, which combines two weakly supervised approaches for pre-training. Our method utilizes frequent patterns within the text as linguistic cues to identify specific characteristics of chemical reactions.
  arXiv  Detail & Related papers  (2023-07-04T02:52:30Z)
• Self-Verification Improves Few-Shot Clinical Information Extraction [73.6905567014859]
  Large language models (LLMs) have shown the potential to accelerate clinical curation via few-shot in-context learning. They still struggle with issues regarding accuracy and interpretability, especially in mission-critical domains such as health. Here, we explore a general mitigation framework using self-verification, which leverages the LLM to provide provenance for its own extraction and check its own outputs.
  arXiv  Detail & Related papers  (2023-05-30T22:05:11Z)
• MetaRF: Differentiable Random Forest for Reaction Yield Prediction with a Few Trails [58.47364143304643]
  In this paper, we focus on the reaction yield prediction problem. We first put forth MetaRF, an attention-based differentiable random forest model specially designed for the few-shot yield prediction. To improve the few-shot learning performance, we further introduce a dimension-reduction based sampling method.
  arXiv  Detail & Related papers  (2022-08-22T06:40:13Z)
• Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation [4.846235640334886]
  Traditional object detectors are ill-equipped for incremental learning. Fine-tuning directly on a well-trained detection model with only new data will lead to catastrophic forgetting. We propose a response-based incremental distillation method, dubbed Elastic Response Distillation (ERD)
  arXiv  Detail & Related papers  (2022-04-05T11:57:43Z)
• Deep Learning for Virtual Screening: Five Reasons to Use ROC Cost Functions [80.12620331438052]
  deep learning has become an important tool for rapid screening of billions of molecules in silico for potential hits containing desired chemical features. Despite its importance, substantial challenges persist in training these models, such as severe class imbalance, high decision thresholds, and lack of ground truth labels in some datasets. We argue in favor of directly optimizing the receiver operating characteristic (ROC) in such cases, due to its robustness to class imbalance.
  arXiv  Detail & Related papers  (2020-06-25T08:46:37Z)

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.