Decoupling Generation and Selection for Budget-Constrained Faithful Summarization

• URL: http://arxiv.org/abs/2608.03655v1
• Date: Tue, 04 Aug 2026 13:36:25 GMT
• Title: Decoupling Generation and Selection for Budget-Constrained Faithful Summarization
• Abstract summary: We propose a modular generation-and-selection framework for sentence-budget-constrained summarization.<n>A pretrained generator produces multiple candidate summaries, which are decomposed into sentence-level candidates.<n>A selector then constructs the final summary by balancing relevance, factuality, and redundancy under an explicit budget.
• Score: 5.708600866689601
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Abstractive summarization models remain vulnerable to factual inconsistency, redundancy, and weak length control. We propose a modular generation-and-selection framework for sentence-budget-constrained summarization. A pretrained generator produces multiple candidate summaries, which are decomposed into sentence-level candidates. A combinatorial selector then constructs the final summary by balancing relevance, factuality, and redundancy under an explicit budget. The framework supports MMR, ILP, and a DPP-inspired log-determinant objective without retraining the generator. Experiments on CNN/DailyMail, Multi-News, FaithBench, and TofuEval show consistent improvements in factuality and source-grounding metrics, especially for multi-document summarization, at the cost of lower reference-overlap scores. Human evaluation further indicates higher perceived consistency, relevance, clarity, and conciseness, with a small reduction in coherence. These results show that decoupling generation from selection provides a model-agnostic mechanism for improving factual grounding. Code is available at https://anonymous.4open.science/r/bcfs-D05E/.

Related papers

• A Hybrid Hierarchical 1D-CNN-BiLSTM Framework for Extractive Summarization of Biomedical and Clinical Text [0.39146761527401436]
  Large language models have made abstractive summarization remarkably fluent, but generated summaries can hallucinate facts.<n>We address this by removing generation from the pipeline and framing summarization as extractive sentence selection.<n>Our architecture outperforms isolated CNN and LSTM baselines, while ablations show that wider convolutional receptive fields improve sentence scoring.
  arXiv  Detail & Related papers  (2026-09-11T19:49:33Z)
• Hacking Generative Perplexity: Why Unconditional Text Evaluation Needs Distributional Metrics [49.443264461057645]
  Diffusion and continuous flow-based language models have emerged as the leading non-autoregressive alternatives to language modeling.<n>Progress in both paradigms is overwhelmingly tracked by generative perplexity (gen-PPL): the per-token negative log-likelihood of samples under a frozen autoregressive (AR) scorer.<n>We argue that this metric is unsound. By construction, gen-PPL measures only predictability under the scoring AR, not grammaticality or semantic coherence.
  arXiv  Detail & Related papers  (2026-06-07T02:35:56Z)
• Enhancing Factuality through Consensus and Consistency in Summarization Using Minimum Bayes Risk Decoding [64.98167175790817]
  We propose ConSUM that reranks candidate summaries by considering two factors: consistency to the source document and consensus among the other candidates.<n>Our system is competitive with existing methods, with human evaluations confirming that its generated summaries are preferred over those from other systems.
  arXiv  Detail & Related papers  (2026-05-28T04:14:43Z)
• Budget-Aware Routing for Long Clinical Text [8.474809035213118]
  Key challenge for large language models is token cost per query and overall deployment cost.<n>We study budgeted context selection, where a subset of document units is chosen under a strict token budget.<n>We propose textbfRCD, a monotone submodular objective that balances relevance, coverage, and diversity.
  arXiv  Detail & Related papers  (2026-05-01T01:34:53Z)
• Contextual Counterfactual Credit Assignment for Multi-Agent Reinforcement Learning in LLM Collaboration [22.269718913202595]
  We introduce Contextual Counterfactual Credit Assignment (textbftextttC3)<n>Instead of distributing rewards across an entire episode, textbftextttC3 isolates the causal impact of individual messages.<n>textbftextttC3 improves terminal performance over established baselines.
  arXiv  Detail & Related papers  (2026-03-06T20:25:11Z)
• Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching [66.39914384073145]
  We propose a self-consistency framework that turns cheap diffusion-sampled reasoning into a reusable pool of step-level candidates.<n>We find that step-level recombination is most beneficial on harder problems.<n>Our training-free framework improves average accuracy by up to 2 across six math and coding tasks.
  arXiv  Detail & Related papers  (2026-02-26T11:08:39Z)
• SimGR: Escaping the Pitfalls of Generative Decoding in LLM-based Recommendation [68.00727783181289]
  A core objective in recommender systems is to accurately model the distribution of user preferences over items to enable personalized recommendations.<n>We observe that existing methods inevitably introduce systematic bias when estimating item-level preference distributions.<n>We propose textbfSimply textbfGenerative textbfRecommendation (textbfSimGR), a framework that directly models item-level preference distributions in a shared latent space.
  arXiv  Detail & Related papers  (2026-02-08T07:26:52Z)
• AMRFact: Enhancing Summarization Factuality Evaluation with AMR-Driven Negative Samples Generation [57.8363998797433]
  We propose AMRFact, a framework that generates perturbed summaries using Abstract Meaning Representations (AMRs) Our approach parses factually consistent summaries into AMR graphs and injects controlled factual inconsistencies to create negative examples, allowing for coherent factually inconsistent summaries to be generated with high error-type coverage.
  arXiv  Detail & Related papers  (2023-11-16T02:56:29Z)
• Multi-Fact Correction in Abstractive Text Summarization [98.27031108197944]
  Span-Fact is a suite of two factual correction models that leverages knowledge learned from question answering models to make corrections in system-generated summaries via span selection. Our models employ single or multi-masking strategies to either iteratively or auto-regressively replace entities in order to ensure semantic consistency w.r.t. the source text. Experiments show that our models significantly boost the factual consistency of system-generated summaries without sacrificing summary quality in terms of both automatic metrics and human evaluation.
  arXiv  Detail & Related papers  (2020-10-06T02:51:02Z)
• Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward [42.925345819778656]
  We present ASGARD, a novel framework for Abstractive Summarization with Graph-Augmentation and semantic-driven RewarD. We propose the use of dual encoders---a sequential document encoder and a graph-structured encoder---to maintain the global context and local characteristics of entities. Results show that our models produce significantly higher ROUGE scores than a variant without knowledge graph as input on both New York Times and CNN/Daily Mail datasets.
  arXiv  Detail & Related papers  (2020-05-03T18:23:06Z)
• Exploring Explainable Selection to Control Abstractive Summarization [51.74889133688111]
  We develop a novel framework that focuses on explainability. A novel pair-wise matrix captures the sentence interactions, centrality, and attribute scores. A sentence-deployed attention mechanism in the abstractor ensures the final summary emphasizes the desired content.
  arXiv  Detail & Related papers  (2020-04-24T14:39:34Z)

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.