# Towards Multi-Level Transcript Segmentation: LoRA Fine-Tuning for Table-of-Contents Generation

arXiv: https://arxiv.org/abs/2601.02128 · HTML: https://mlsanity.com/paper/2601.02128/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 40 references that are in the map.
- First posted on arXiv 5 Jan 2026.

## Builds on (most cited first, 21 of 21)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation](https://mlsanity.com/paper/2004.09813/) (2020)
- [Text Segmentation as a Supervised Learning Task](https://mlsanity.com/paper/1803.09337/) (2018)
- [Text Segmentation by Cross Segment Attention](https://mlsanity.com/paper/2004.14535/) (2020)
- [Unsupervised Topic Segmentation of Meetings with BERT Embeddings](https://mlsanity.com/paper/2106.12978/) (2021)
- [Uncovering the Potential of ChatGPT for Discourse Analysis in Dialogue: An Empirical Study](https://mlsanity.com/paper/2305.08391/) (2023)
- [From Text Segmentation to Smart Chaptering: A Novel Benchmark for Structuring Video Transcriptions](https://mlsanity.com/paper/2402.17633/) (2024)
- [Improving Long Document Topic Segmentation Models With Enhanced Coherence Modeling](https://mlsanity.com/paper/2310.11772/) (2023)
- [Hierarchical Summarization for Longform Spoken Dialog](https://mlsanity.com/paper/2108.09597/) (2021)
- [SmartBook: AI-Assisted Situation Report Generation for Intelligence Analysts](https://mlsanity.com/paper/2303.14337/) (2023)
- [PODTILE: Facilitating Podcast Episode Browsing with Auto-generated Chapters](https://mlsanity.com/paper/2410.16148/) (2024)
- [Cem Mil Podcasts: A Spoken Portuguese Document Corpus For Multi-modal, Multi-lingual and Multi-Dialect Information Access Research](https://mlsanity.com/paper/2209.11871/) (2022)
- [Prompting Large Language Models with Audio for General-Purpose Speech Summarization](https://mlsanity.com/paper/2406.05968/) (2024)
- [Topic Segmentation in the Wild: Towards Segmentation of Semi-structured & Unstructured Chats](https://mlsanity.com/paper/2211.14954/) (2022)
- [Improving automated segmentation of radio shows with audio embeddings](https://mlsanity.com/paper/2002.05194/) (2020)
- [Unsupervised Dialogue Topic Segmentation in Hyperdimensional Space](https://mlsanity.com/paper/2308.10464/) (2023)
- [An End-to-End Speech Summarization Using Large Language Model](https://mlsanity.com/paper/2407.02005/) (2024)

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

- [Beyond Transcripts: A Renewed Perspective on Audio Chaptering](https://mlsanity.com/paper/2602.08979/) (2026)
- [Reading Between the Waves: Robust Topic Segmentation Using Inter-Sentence Audio Features](https://mlsanity.com/paper/2602.06647/) (2026)
- [Reusing Latent Speech Representations for Query-Conditioned Topic Localization in Transcripts](https://mlsanity.com/paper/2609.21844/) (2026)
- [Zero-Shot Cue-Grounded Topic Segmentation of Spoken Documents](https://mlsanity.com/paper/2609.34425/) (2026)

## Abstract (arXiv)

Segmenting speech transcripts into thematic sections benefits both downstream processing and users who depend on written text for accessibility. We introduce a novel approach to hierarchical topic segmentation in transcripts, generating multi-level tables of contents that capture both topic and subtopic boundaries. We compare zero-shot prompting and LoRA fine-tuning on large language models, while also exploring the integration of high-level speech pause features. Evaluations on English meeting recordings and multilingual lecture transcripts (Portuguese, German) show significant improvements over established topic segmentation baselines. Additionally, we adapt a common evaluation measure for multi-level segmentation, taking into account all hierarchical levels within one metric.