# LLM aided semi-supervision for Extractive Dialog Summarization

arXiv: https://arxiv.org/abs/2311.11462 · HTML: https://mlsanity.com/paper/2311.11462/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 36 references that are in the map.
- First posted on arXiv 19 Nov 2023.

## Builds on (most cited first, 26 of 26)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond](https://mlsanity.com/paper/1602.06023/) (2016)
- [Sequence-Level Knowledge Distillation](https://mlsanity.com/paper/1606.07947/) (2016)
- [Text Summarization with Pretrained Encoders](https://mlsanity.com/paper/1908.08345/) (2019)
- [Meta Pseudo Labels](https://mlsanity.com/paper/2003.10580/) (2020)
- [Is GPT-3 a Good Data Annotator?](https://mlsanity.com/paper/2212.10450/) (2022)
- [Want To Reduce Labeling Cost? GPT-3 Can Help](https://mlsanity.com/paper/2108.13487/) (2021)
- [Neural Text Summarization: A Critical Evaluation](https://mlsanity.com/paper/1908.08960/) (2019)
- [Revisiting Self-Training for Neural Sequence Generation](https://mlsanity.com/paper/1909.13788/) (2019)
- [Fine-tune BERT for Extractive Summarization](https://mlsanity.com/paper/1903.10318/) (2019)
- [Pre-trained Summarization Distillation](https://mlsanity.com/paper/2010.13002/) (2020)
- [Unsupervised Abstractive Meeting Summarization with Multi-Sentence Compression and Budgeted Submodular Maximization](https://mlsanity.com/paper/1805.05271/) (2018)
- [Abstractive Dialogue Summarization with Sentence-Gated Modeling Optimized by Dialogue Acts](https://mlsanity.com/paper/1809.05715/) (2018)
- [TWEETSUMM -- A Dialog Summarization Dataset for Customer Service](https://mlsanity.com/paper/2111.11894/) (2021)
- [Noisy Self-Knowledge Distillation for Text Summarization](https://mlsanity.com/paper/2009.07032/) (2020)
- [Revisiting Self-Training for Few-Shot Learning of Language Model](https://mlsanity.com/paper/2110.01256/) (2021)
- [Unsupervised Summarization for Chat Logs with Topic-Oriented Ranking and Context-Aware Auto-Encoders](https://mlsanity.com/paper/2012.07300/) (2020)
- [Unsupervised Abstractive Dialogue Summarization for Tete-a-Tetes](https://mlsanity.com/paper/2009.06851/) (2020)
- [Ask Me What You Need: Product Retrieval using Knowledge from GPT-3](https://mlsanity.com/paper/2207.02516/) (2022)
- [Heuristic-based Inter-training to Improve Few-shot Multi-perspective Dialog Summarization](https://mlsanity.com/paper/2203.15590/) (2022)

## Built on by (most cited first, 4 of 4)

- [A Guide To Effectively Leveraging LLMs for Low-Resource Text Summarization: Data Augmentation and Semi-supervised Approaches](https://mlsanity.com/paper/2407.07341/) (2024)
- [Semi-Supervised Dialogue Abstractive Summarization via High-Quality Pseudolabel Selection](https://mlsanity.com/paper/2403.04073/) (2024)
- [Pre-Trained AI Model Assisted Online Decision-Making under Missing Covariates: A Theoretical Perspective](https://mlsanity.com/paper/2507.07852/) (2025)
- [Paired by the Teacher: Turning Unpaired Data into High-Fidelity Pairs for Low-Resource Text Generation](https://mlsanity.com/paper/2509.25144/) (2025)

## Abstract (arXiv)

Generating high-quality summaries for chat dialogs often requires large labeled datasets. We propose a method to efficiently use unlabeled data for extractive summarization of customer-agent dialogs. In our method, we frame summarization as a question-answering problem and use state-of-the-art large language models (LLMs) to generate pseudo-labels for a dialog. We then use these pseudo-labels to fine-tune a chat summarization model, effectively transferring knowledge from the large LLM into a smaller specialized model. We demonstrate our method on the tweetsumm dataset, and show that using 10% of the original labelled data set we can achieve 65.9/57.0/61.0 ROUGE-1/-2/-L, whereas the current state-of-the-art trained on the entire training data set obtains 65.16/55.81/64.37 ROUGE-1/-2/-L. In other words, in the worst case (i.e., ROUGE-L) we still effectively retain 94.7% of the performance while using only 10% of the data.