This work proposes LOBSTER, a novel active learning framework designed specifically for abstractive summarization that improves performance by prioritizing unlabeled instances semantically similar to the model's current high-loss training examples, enabling the model to explicitly correct its specific weaknesses.
Abstract
Fine-tuning abstractive summarization models requires high-quality annotated data. However, obtaining such corpora is expensive and time-consuming, as it requires human annotators to read and comprehend long documents to create accurate summaries. Active learning mitigates this issue by selecting only the most informative instances for annotation, allowing models to achieve competitive results with significantly fewer labels. However, the application of active learning to summarization remains under-explored, and existing studies often suffer from instability and significant computational bottlenecks. To overcome these challenges, we propose LOBSTER (LOss-BaSed acTivE leaRning), a novel active learning framework designed specifically for abstractive summarization. LOBSTER improves performance by prioritizing unlabeled instances semantically similar to the model's current high-loss training examples, enabling the model to explicitly correct its specific weaknesses. Our empirical evaluation across three benchmark datasets and two summarization backbone models demonstrates that LOBSTER consistently matches or outperforms current state-of-the-art approaches while achieving a query selection speedup of up to 665x.
The results show that BART achieves the best performance with an ROUGE-2 F1-score of 0.40664, while T5 demonstrates superior grammatical acceptability, achieving 93.36%, but BART achieves a very near performance to T5.
Emad Nabil· Islamic University Journal o...· 0 citations
AI-based text summarization plays a critical role in managing the rapidly increasing volume of textual information by enabling efficient information retrieval and concise knowledge representation. Conventional summarization approaches often rely on heuristic rules and surface-level features, limiting their ability to capture contextual relevance and semantic coherence in long documents. To overcome these limitations, this study develops a deep learning–based extractive text summarization framework using a hybrid Bidirectional Encoder Representations from Transformers (BERT) combined with Bidirectional Long Short-Term Memory (BiLSTM) architecture. The model leverages BERT’s bidirectional transformer encoder to generate rich contextual sentence embeddings and employs a BiLSTM network to model inter-sentence dependencies and document-level structure, enabling effective identification of summary-worthy sentences while preserving original semantic content. The framework is evaluated using the BBC News Summary dataset, which contains professionally written news articles and corresponding human reference summaries. Performance is assessed through sentence-level classification metrics and ROUGE-based evaluation. Experimental results demonstrate strong effectiveness, achieving an overall accuracy of 98.5%, with balanced precision (98.7%), recall (98.2%), and F1-score (98.45%), indicating reliable sentence importance classification. In addition, the model attains competitive ROUGE ((Recall-Oriented Understudy for Gisting Evaluation) scores (ROUGE-1 = 0.56, ROUGE-2 = 0.33, and ROUGE-L = 0.52), confirming substantial overlap with human summaries. These results highlight the robustness, generalization capability, and practical applicability of the suggested BERT–BiLSTM structure for automatic text summarization and knowledge representation.
Dr. RakeshKumar ER, S. Ramachandran, Ayushi Khandal et al.· 2026 7th International Confe...· 0 citations
Text summarization is deceptively difficult. While condensing information seems straightforward, real-world enterprise summarization of support tickets, legal documents, incident reports, and more, demands strict adherence to domain-specific guidelines, output formats, and organizational conventions. Crafting prompts that reliably satisfy these constraints is labor-intensive, requiring significant human expertise and continuous maintenance as requirements evolve. Existing automated prompt optimization methods reduce this burden through Large Language Model (LLM) critique-driven refinement, yet remain limited by static prompts that cannot adapt to the diversity of summary applications. We propose Multi-LLM Iterative Data-Adaptive Summarization (MIDAS), a multi-LLM framework that extends this paradigm with data-driven pattern learning and use-case-specific personalization, enabling automatic adaptation to different summarization requirements without manual prompt engineering. Applied to enterprise customer ticket summarization across five output formats, MIDAS achieves the strongest overall performance against state-of-the-art critique-driven optimization frameworks such as CriSPO and ZERA, improving ROUGE-1 by up to 11.0%, ROUGE-2 by up to 18.2%, and ROUGE-L by up to 8.0%, while consistently improving BERTScore F1 across all formats and output types. We additionally demonstrate cross-model and cross-domain generalization through multi-LLM configurations and finance-domain summarization benchmarks.
Karen Lee, D. Balaram, Seojun Shon et al.· 0 citations
Multimodal Large Language Models (MLLMs) have achieved strong performance on structured visual understanding tasks such as chart and document question answering. However, existing benchmarks typically evaluate these domains in isolation, leaving underexplored a key capability: whether models can use textual context to determine how chart evidence should be selected, interpreted, and aggregated. We introduce DocHop, a benchmark for integrated chart--context reasoning in document-style images. In DocHop, the document narrative specifies multi-step compositional constraints, while charts provide the corresponding data values. Questions are grounded on a semantic reference label defined in the narrative, requiring models to resolve target entities from context before aggregating evidence across multiple charts. To enable systematic evaluation, we construct DocHop via a stochastic logic-first generation pipeline with controllable reasoning depth and visual density, covering 2,074 examples across six task categories. Experiments on a wide range of proprietary and open-source MLLMs show a substantial gap to human performance: annotators achieve over 90% accuracy, while the best model reaches only 62.83%. Reasoning-enhanced models consistently show improved results, but performance degrades as reasoning complexity increases. Overall, DocHop provides a controlled testbed for challenging multi-hop document reasoning.
Zhuoran Yu, Le Thien Phuc Nguyen, Jaden Park et al.· 1 citation
This work proposes a distillation approach based on ranking supervision that consistently outperforms supervised fine-tuning as well as FKL and RKL baselines in Python code generation, multilingual generation, and data-science scenarios and offers guidance for future research in model compression.
Zhe Ding, Hui Ji, Su Pan et al.· Neural Networks· 0 citations
Text summarization requires models to condense content while preserving key qualities such as consistency and coherence. Large language models (LLMs) have shown strong performance on this task and can be further improved through reinforcement learning (RL). However, most existing methods apply reward signals directly to undifferentiated token sequences, overlooking the varying importance of individual tokens to word and sentence level quality in summarization. In this paper, we propose Token Importance-Aware Policy Optimization (TIAO), a novel reinforcement learning strategy that explicitly leverages token-importance awareness. Specifically, TIAO identifies core tokens based on token dependency and reweights a trajectory's advantage according to its overall dependencies. Experiments on the real world dataset show that our TIAO achieves highly competitive results, and that a 7B foundation model enhanced by TIAO performs comparably to GPT-4 and GPT-5-nano. Code is available at https://github.com/TechCloud-x/TIAO
Qi-Xiu Li, Chen-Long Bao, Xiang Zhu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
