2000 character limit reached
Utilizing GPT to Enhance Text Summarization: A Strategy to Minimize Hallucinations (2405.04039v1)
Published 7 May 2024 in cs.CL, cs.AI, and cs.LG
Abstract: In this research, we uses the DistilBERT model to generate extractive summary and the T5 model to generate abstractive summaries. Also, we generate hybrid summaries by combining both DistilBERT and T5 models. Central to our research is the implementation of GPT-based refining process to minimize the common problem of hallucinations that happens in AI-generated summaries. We evaluate unrefined summaries and, after refining, we also assess refined summaries using a range of traditional and novel metrics, demonstrating marked improvements in the accuracy and reliability of the summaries. Results highlight significant improvements in reducing hallucinatory content, thereby increasing the factual integrity of the summaries.
- A survey of advanced methods for efficient text summarization. In 2023 IEEE 13th Annual Computing and Communication Workshop and Conference (CCWC), pages 0962–0968. IEEE, 2023.
- Performance study on extractive text summarization using bert models. Information, 13(2):67, 2022.
- Text summarization using transformer model. In 2022 Ninth International Conference on Social Networks Analysis, Management and Security (SNAMS), pages 1–5. IEEE, 2022.
- Faithful to the original: Fact aware neural abstractive summarization. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 32, 2018.
- Automatic text summarization: A comprehensive survey. Expert systems with applications, 165:113679, 2021.
- Gpt (generative pre-trained transformer)–a comprehensive review on enabling technologies, potential applications, emerging challenges, and future directions. IEEE Access, 2024.
- Text summarization techniques: a brief survey. arXiv preprint arXiv:1707.02268, 2017.
- Text summarization with pretrained encoders. arXiv preprint arXiv:1908.08345, 2019.
- Evaluating the tradeoff between abstractiveness and factuality in abstractive summarization. In Findings of the Association for Computational Linguistics: EACL 2023, pages 2044–2060, 2023.
- Ranking sentences for extractive summarization with reinforcement learning. arXiv preprint arXiv:1802.08636, 2018.
- Extractive text summarization by feature-based sentence extraction using rule-based concept. In 2017 2nd IEEE international conference on recent trends in electronics, Information & Communication Technology (RTEICT), pages 1364–1368. IEEE, 2017.
- Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084, 2019.
- A hierarchical network for abstractive meeting summarization with cross-domain pretraining. arXiv preprint arXiv:2004.02016, 2020.
- Survey of hallucination in natural language generation. ACM Computing Surveys, 55(12):1–38, 2023.
- Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108, 2019.
- Exploring the limits of transfer learning with a unified text-to-text transformer. The Journal of Machine Learning Research, 21(1):5485–5551, 2020.
- Deep learning-based extractive text summarization with word-level attention mechanism. Multimedia Tools and Applications, 81(15):20829–20852, 2022.
- Hoon Heo. Factsumm: Factual consistency scorer for abstractive summarization. https://github.com/Huffon/factsumm, 2021.
- Asking and answering questions to evaluate the factual consistency of summaries. ArXiv, abs/2004.04228, 2020. URL https://api.semanticscholar.org/CorpusID:215548661.
- SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization. Transactions of the Association for Computational Linguistics, 10:163–177, 02 2022. ISSN 2307-387X. doi:10.1162/tacl_a_00453. URL https://doi.org/10.1162/tacl_a_00453.
- Chin-Yew Lin. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out, pages 74–81, Barcelona, Spain, July 2004. Association for Computational Linguistics. URL https://aclanthology.org/W04-1013.
- Andy Field. Discovering statistics using IBM SPSS statistics. sage, 2013.
- EEL Lehmann and JP Romano. Testing statistical hypotheses: Springer science+ business media. 2005.
- Hassan Shakil (5 papers)
- Zeydy Ortiz (3 papers)
- Grant C. Forbes (6 papers)