# Worth Their Weights? Evaluating Generative Models for Discourse Parsing

arXiv: https://arxiv.org/abs/2610.17658 · HTML: https://mlsanity.com/paper/2610.17658/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 60 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Builds on (most cited first, 24 of 24)

- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [Pointer Networks](https://mlsanity.com/paper/1506.03134/) (2015)
- [Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference](https://mlsanity.com/paper/2412.13663/) (2024)
- [Larger-Scale Transformers for Multilingual Masked Language Modeling](https://mlsanity.com/paper/2105.00572/) (2021)
- [Pretraining with Contrastive Sentence Objectives Improves Discourse Performance of Language Models](https://mlsanity.com/paper/2005.10389/) (2020)
- [Seq vs Seq: An Open Suite of Paired Encoders and Decoders](https://mlsanity.com/paper/2507.11412/) (2025)
- [EuroBERT: Scaling Multilingual Encoders for European Languages](https://mlsanity.com/paper/2503.05500/) (2025)
- [DMRST: A Joint Framework for Document-Level Multilingual RST Discourse Segmentation and Parsing](https://mlsanity.com/paper/2110.04518/) (2021)
- [Better Document-level Sentiment Analysis from RST Discourse Parsing](https://mlsanity.com/paper/1509.01599/) (2015)
- [Cross-lingual RST Discourse Parsing](https://mlsanity.com/paper/1701.02946/) (2017)
- [Surprise! Uniform Information Density Isn't the Whole Story: Predicting Surprisal Contours in Long-form Discourse](https://mlsanity.com/paper/2410.16062/) (2024)
- [RST Parsing from Scratch](https://mlsanity.com/paper/2105.10861/) (2021)
- [GCDT: A Chinese RST Treebank for Multigenre and Multilingual Discourse Parsing](https://mlsanity.com/paper/2210.10449/) (2022)
- [eRST: A Signaled Graph Theory of Discourse Relations and Organization](https://mlsanity.com/paper/2403.13560/) (2024)
- [RST-LoRA: A Discourse-Aware Low-Rank Adaptation for Long Document Abstractive Summarization](https://mlsanity.com/paper/2405.00657/) (2024)
- [Persian Rhetorical Structure Theory](https://mlsanity.com/paper/2106.13833/) (2021)
- [Beyond Chunking: Discourse-Aware Hierarchical Retrieval for Long Document Question Answering](https://mlsanity.com/paper/2506.06313/) (2025)
- [Bilingual Rhetorical Structure Parsing with Large Parallel Annotations](https://mlsanity.com/paper/2409.14969/) (2024)
- [Findings of the Fourth Shared Task on Multilingual Coreference Resolution: Can LLMs Dethrone Traditional Approaches?](https://mlsanity.com/paper/2509.17796/) (2025)
- [A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing](https://mlsanity.com/paper/2210.08355/) (2022)
- [CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution](https://mlsanity.com/paper/2509.17858/) (2025)
- [Bridging Discourse Treebanks with a Unified Rhetorical Structure Parser](https://mlsanity.com/paper/2510.06427/) (2025)

## Abstract (arXiv)

Rhetorical Structure Theory (RST) parsing has historically been dominated by discriminative models based on pretrained encoder-only language models. The recent availability of high-quality generative language models has made it unclear whether RST parsing is better approached as a generative task. In this work, we investigate whether generative language models are better at parsing RST than traditional discriminative ones. We find that at matched parameter counts, discriminative parsers perform much better than generative ones, though much larger generative models sometimes outperform them. Generative models hold a particular advantage in elementary discourse unit (EDU) segmentation, and we report new state-of-the-art results on the RST-DT benchmark in end-to-end parsing as well as segmentation.