# Padamitra: Grounded Glossary Generation for Classical Sanskrit

arXiv: https://arxiv.org/abs/2608.25038 · HTML: https://mlsanity.com/paper/2608.25038/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 31 references that are in the map.
- First posted on arXiv 25 Aug 2026.

## Builds on (most cited first, 12 of 12)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation](https://mlsanity.com/paper/2004.09813/) (2020)
- [Word Translation Without Parallel Data](https://mlsanity.com/paper/1710.04087/) (2017)
- [Definition Modeling: Learning to define word embeddings in natural language](https://mlsanity.com/paper/1612.00394/) (2016)
- [Itihasa: A large-scale corpus for Sanskrit to English translation](https://mlsanity.com/paper/2106.03269/) (2021)
- [Chandomitra: Towards Generating Structured Sanskrit Poetry from Natural Language Inputs](https://mlsanity.com/paper/2506.00815/) (2025)
- [Anveshana: A New Benchmark Dataset for Cross-Lingual Information Retrieval On English Queries and Sanskrit Documents](https://mlsanity.com/paper/2505.19494/) (2025)
- [Still Not There: Can LLMs Outperform Smaller Task-Specific Seq2Seq Models on the Poetry-to-Prose Conversion Task?](https://mlsanity.com/paper/2511.08145/) (2025)
- [Mitrasamgraha: A Comprehensive Classical Sanskrit Machine Translation Dataset](https://mlsanity.com/paper/2601.07314/) (2026)
- [Pingala: Prosody-Aware Decoding for Sanskrit Poetry Generation](https://mlsanity.com/paper/2603.24413/) (2026)

## Abstract (arXiv)

We introduce grounded glossary generation, a structured task requiring models to recover semantically meaningful Sanskrit phrases and produce translation-grounded meanings from a sloka-translation pair, formalizing the traditional patha commentary practice as an evaluable NLP objective. We construct a benchmark of 31,316 sloka-translation-glossary triples from the Valmiki Ramayana and Srimad Bhagavatam, paired with two metrics: Jaccard for phrase recovery and Meaning Faithfulness for semantic consistency. Across zero-shot, few-shot, and instruction fine-tuned variants of Gemma-3n-E4B, Gemma-3-12B, Phi-4, and Qwen3.5-9B, instruction fine-tuning substantially outperforms prompting, while explicit segmentation yields gains. Error analysis identifies over-segmentation of sandhi and samasa compounds as the dominant failure mode, pointing to morphological modeling as the key bottleneck for faithful Sanskrit lexical decomposition.