# Hybrid Neural-LLM Pipeline for Morphological Glossing in Endangered Language Documentation: A Case Study of Jungar Tuvan

arXiv: https://arxiv.org/abs/2603.00923 · HTML: https://mlsanity.com/paper/2603.00923/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 46 references that are in the map.
- First posted on arXiv 1 Mar 2026.

## Builds on (most cited first, 19 of 19)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [Neural Architectures for Named Entity Recognition](https://mlsanity.com/paper/1603.01360/) (2016)
- [Bidirectional LSTM-CRF Models for Sequence Tagging](https://mlsanity.com/paper/1508.01991/) (2015)
- [NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark](https://mlsanity.com/paper/2310.18018/) (2023)
- [End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF](https://mlsanity.com/paper/1603.01354/) (2016)
- [Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models](https://mlsanity.com/paper/2106.13353/) (2021)
- [Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering](https://mlsanity.com/paper/2210.02627/) (2022)
- [Language Models are Few-shot Multilingual Learners](https://mlsanity.com/paper/2109.07684/) (2021)
- [Exploring LLM Prompting Strategies for Joint Essay Scoring and Feedback Generation](https://mlsanity.com/paper/2404.15845/) (2024)
- [Cross-lingual, Character-Level Neural Morphological Tagging](https://mlsanity.com/paper/1708.09157/) (2017)
- [Can we teach language models to gloss endangered languages?](https://mlsanity.com/paper/2406.18895/) (2024)
- [Neural Machine Translation Quality and Post-Editing Performance](https://mlsanity.com/paper/2109.05016/) (2021)
- [GlossLM: A Massively Multilingual Corpus and Pretrained Model for Interlinear Glossed Text](https://mlsanity.com/paper/2403.06399/) (2024)
- [Cross-Lingual Morphological Tagging for Low-Resource Languages](https://mlsanity.com/paper/1606.04279/) (2016)
- [Neural Factor Graph Models for Cross-lingual Morphological Tagging](https://mlsanity.com/paper/1805.04570/) (2018)
- [Wav2Gloss: Generating Interlinear Glossed Text from Speech](https://mlsanity.com/paper/2403.13169/) (2024)
- [LingGym: How Far Are LLMs from Thinking Like Field Linguists?](https://mlsanity.com/paper/2511.00343/) (2025)
- [Interdisciplinary Research in Conversation: A Case Study in Computational Morphology for Language Documentation](https://mlsanity.com/paper/2509.10644/) (2025)

## Abstract (arXiv)

Interlinear glossed text (IGT) creation remains a major bottleneck in linguistic documentation and fieldwork, particularly for low-resource morphologically rich languages. We present a hybrid automatic glossing pipeline that combines neural sequence labeling with large language model (LLM) post-correction, evaluated on Jungar Tuvan, a low-resource Turkic language. Through systematic ablation studies, we show that retrieval-augmented prompting provides substantial gains over random example selection. We further find that morpheme dictionaries paradoxically hurt performance compared to providing no dictionary at all in most cases, and that performance scales approximately logarithmically with the number of few-shot examples. Most significantly, our two-stage pipeline combining a BiLSTM-CRF model with LLM post-correction yields substantial gains for most models, achieving meaningful reductions in annotation workload. Drawing on these findings, we establish concrete design principles for integrating structured prediction models with LLM reasoning in morphologically complex fieldwork contexts. These principles demonstrate that hybrid architectures offer a promising direction for computationally light solutions to automatic linguistic annotation in endangered language documentation.