DeepRAG: Building a Custom Hindi Embedding Model for Retrieval Augmented Generation from Scratch

• URL: http://arxiv.org/abs/2503.08213v1
• Date: Tue, 11 Mar 2025 09:27:56 GMT
• Title: DeepRAG: Building a Custom Hindi Embedding Model for Retrieval Augmented Generation from Scratch
• Authors: Nandakishor M,
• Abstract summary: DeepRAG is a specialized embedding model we built specifically for Hindi language in RAG systems.<n>We saw a 23% improvement in retrieval precision compared to the multilingual models everyone's been using.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, I present our work on DeepRAG, a specialized embedding model we built specifically for Hindi language in RAG systems. While LLMs have gotten really good at generating text, their performance in retrieval tasks still depends heavily on having quality embeddings - something that's been lacking for Hindi despite being one of the world's most spoken languages. We tackled this by creating embeddings from the ground up rather than just fine-tuning existing models. Our process involved collecting diverse Hindi texts (over 2.7M samples), training a custom SentencePiece tokenizer that actually understands Hindi morphology, designing transformer architecture with Hindi-specific attention mechanisms, and optimizing with contrastive learning. Results were honestly better than I expected - we saw a 23% improvement in retrieval precision compared to the multilingual models everyone's been using. The paper details our methodology, which I think could help others working with low-resource languages where the one-size-fits-all multilingual models fall short. We've also integrated our embeddings with LangChain to build complete Hindi RAG systems, which might be useful for practitioners. While there's still tons more to explore, I believe this work addresses a critical gap for Hindi NLP and demonstrates why language-specific approaches matter.

Related papers

• Improving Multilingual Capabilities with Cultural and Local Knowledge in Large Language Models While Enhancing Native Performance [0.0]
  We present our latest Hindi-English bi-lingual LLM textbfMantra-14B with 3% average improvement in benchmark scores over both languages. We instruction tuned models such as Qwen-2.5-14B-Instruct and Phi-4 to improve performance over both English and Hindi. Our results indicate that modest fine-tuning with culturally and locally informed data can bridge performance gaps without incurring significant computational overhead.
  arXiv  Detail & Related papers  (2025-04-13T23:10:13Z)
• mFollowIR: a Multilingual Benchmark for Instruction Following in Retrieval [61.17793165194077]
  We introduce mFollowIR, a benchmark for measuring instruction-following ability in retrieval models.<n>We present results for both multilingual (XX-XX) and cross-lingual (En-XX) performance.<n>We see strong cross-lingual performance with English-based retrievers that trained using instructions, but find a notable drop in performance in the multilingual setting.
  arXiv  Detail & Related papers  (2025-01-31T16:24:46Z)
• HindiLLM: Large Language Model for Hindi [0.09363323206192666]
  We have pre-trained two autoregressive Large Language Model (LLM) models for the Hindi language.<n>We use a two-step process comprising unsupervised pre-training and supervised fine-tuning.<n>The evaluation shows that the HindiLLM-based fine-tuned models outperform several models in most of the language related tasks.
  arXiv  Detail & Related papers  (2024-12-29T05:28:15Z)
• Breaking the Script Barrier in Multilingual Pre-Trained Language Models with Transliteration-Based Post-Training Alignment [50.27950279695363]
  The transfer performance is often hindered when a low-resource target language is written in a different script than the high-resource source language. Inspired by recent work that uses transliteration to address this problem, our paper proposes a transliteration-based post-pretraining alignment (PPA) method.
  arXiv  Detail & Related papers  (2024-06-28T08:59:24Z)
• Paramanu: A Family of Novel Efficient Generative Foundation Language Models for Indian Languages [3.9018931027384056]
  We present "Paramanu", a family of novel language models (LM) for Indian languages. It covers 10 languages (Assamese, Bangla, Hindi, Konkani, Maithili, Marathi, Odia, Sanskrit, Tamil, Telugu) across 5 scripts. The models are pretrained on a single GPU with context size of 1024 and vary in size from 13.29 million (M) to 367.5 M parameters.
  arXiv  Detail & Related papers  (2024-01-31T17:58:10Z)
• Investigating Lexical Sharing in Multilingual Machine Translation for Indian Languages [8.858671209228536]
  We investigate lexical sharing in multilingual machine translation from Hindi, Gujarati, Nepali into English. We find that transliteration does not give pronounced improvements. Our analysis suggests that our multilingual MT models trained on original scripts seem to already be robust to cross-script differences.
  arXiv  Detail & Related papers  (2023-05-04T23:35:15Z)
• H-AES: Towards Automated Essay Scoring for Hindi [33.755800922763946]
  We reproduce and compare state-of-the-art methods for Automated Essay Scoring (AES) in the Hindi domain. We employ classical feature-based Machine Learning (ML) and advanced end-to-end models, including LSTM Networks and Fine-Tuned Transformer Architecture. We train and evaluate our models using translated English essays and empirically measure their performance on our own small-scale, real-world Hindi corpus.
  arXiv  Detail & Related papers  (2023-02-28T15:14:15Z)
• Crosslingual Generalization through Multitask Finetuning [80.8822603322471]
  Multitask prompted finetuning (MTF) has been shown to help large language models generalize to new tasks in a zero-shot setting. We apply MTF to the pretrained multilingual BLOOM and mT5 model families to produce finetuned variants called BLOOMZ and mT0. We find finetuning large multilingual language models on English tasks with English prompts allows for task generalization to non-English languages.
  arXiv  Detail & Related papers  (2022-11-03T13:19:32Z)
• XRICL: Cross-lingual Retrieval-Augmented In-Context Learning for Cross-lingual Text-to-SQL Semantic Parsing [70.40401197026925]
  In-context learning using large language models has recently shown surprising results for semantic parsing tasks. This work introduces the XRICL framework, which learns to retrieve relevant English exemplars for a given query. We also include global translation exemplars for a target language to facilitate the translation process for large language models.
  arXiv  Detail & Related papers  (2022-10-25T01:33:49Z)
• UNKs Everywhere: Adapting Multilingual Language Models to New Scripts [103.79021395138423]
  Massively multilingual language models such as multilingual BERT (mBERT) and XLM-R offer state-of-the-art cross-lingual transfer performance on a range of NLP tasks. Due to their limited capacity and large differences in pretraining data, there is a profound performance gap between resource-rich and resource-poor target languages. We propose novel data-efficient methods that enable quick and effective adaptation of pretrained multilingual models to such low-resource languages and unseen scripts.
  arXiv  Detail & Related papers  (2020-12-31T11:37:28Z)
• Indic-Transformers: An Analysis of Transformer Language Models for Indian Languages [0.8155575318208631]
  Language models based on the Transformer architecture have achieved state-of-the-art performance on a wide range of NLP tasks. However, this performance is usually tested and reported on high-resource languages, like English, French, Spanish, and German. Indian languages, on the other hand, are underrepresented in such benchmarks.
  arXiv  Detail & Related papers  (2020-11-04T14:43:43Z)
• Cross-lingual Machine Reading Comprehension with Language Branch Knowledge Distillation [105.41167108465085]
  Cross-lingual Machine Reading (CLMRC) remains a challenging problem due to the lack of large-scale datasets in low-source languages. We propose a novel augmentation approach named Language Branch Machine Reading (LBMRC) LBMRC trains multiple machine reading comprehension (MRC) models proficient in individual language. We devise a multilingual distillation approach to amalgamate knowledge from multiple language branch models to a single model for all target languages.
  arXiv  Detail & Related papers  (2020-10-27T13:12:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.