Extractive summarization via chatgpt for faithful summary generation

H Zhang, X Liu, J Zhang - arXiv preprint arXiv:2304.04193, 2023 - arxiv.org
Extractive summarization is a crucial task in natural language processing that aims to
condense long documents into shorter versions by directly extracting sentences. The recent …

Summit: Iterative text summarization via chatgpt

H Zhang, X Liu, J Zhang - arXiv preprint arXiv:2305.14835, 2023 - arxiv.org
Text summarization systems have made significant progress in recent years, but typically
generate summaries in one single step. However, the one-shot summarization setting is …

Diffusum: Generation enhanced extractive summarization with diffusion

H Zhang, X Liu, J Zhang - arXiv preprint arXiv:2305.01735, 2023 - arxiv.org
Extractive summarization aims to form a summary by directly extracting sentences from the
source document. Existing works mostly formulate it as a sequence labeling problem by …

On improving summarization factual consistency from natural language feedback

Y Liu, B Deb, M Teruel, A Halfaker, D Radev… - arXiv preprint arXiv …, 2022 - arxiv.org
Despite the recent progress in language generation models, their outputs may not always
meet user expectations. In this work, we study whether informational feedback in natural …

Hegel: Hypergraph transformer for long document summarization

H Zhang, X Liu, J Zhang - arXiv preprint arXiv:2210.04126, 2022 - arxiv.org
Extractive summarization for long documents is challenging due to the extended structured
input context. The long-distance sentence dependency hinders cross-sentence relations …

Faithfulness-aware decoding strategies for abstractive summarization

D Wan, M Liu, K McKeown, M Dreyer… - arXiv preprint arXiv …, 2023 - arxiv.org
Despite significant progress in understanding and improving faithfulness in abstractive
summarization, the question of how decoding strategies affect faithfulness is less studied …

Single-Document Abstractive Text Summarization: A Systematic Literature Review

A Rao, S Aithal, S Singh - ACM Computing Surveys, 2024 - dl.acm.org
Abstractive text summarization is a task in natural language processing that automatically
generates the summary from the source document in a human-written form with minimal loss …

Unveiling the Magic: Investigating Attention Distillation in Retrieval-augmented Generation

Z Li, H Zhang, J Zhang - arXiv preprint arXiv:2402.11794, 2024 - arxiv.org
Retrieval-augmented generation framework can address the limitations of large language
models by enabling real-time knowledge updates for more accurate answers. An efficient …

Aligning factual consistency for clinical studies summarization through reinforcement learning

X Tang, A Cohan, M Gerstein - Proceedings of the 5th Clinical …, 2023 - aclanthology.org
In the rapidly evolving landscape of medical research, accurate and concise summarization
of clinical studies is crucial to support evidence-based practice. This paper presents a novel …

Promoting Topic Coherence and Inter-Document Consorts in Multi-Document Summarization via Simplicial Complex and Sheaf Graph

Y Atri, A Iyer, T Chakraborty… - Proceedings of the 2023 …, 2023 - aclanthology.org
Multi-document Summarization (MDS) characterizes compressing information from multiple
source documents to its succinct summary. An ideal summary should encompass all topics …