# Where Does Retrieval Fail? Evaluating RAG Architectures for Agricultural Advisory

arXiv: https://arxiv.org/abs/2608.14886 · HTML: https://mlsanity.com/paper/2608.14886/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Time series and agricultural RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 18 of its 26 references that are in the map.
- First posted on arXiv 14 Aug 2026.

## Placed in

- Retrieval-augmented generation / [Time series and agricultural RAG](https://mlsanity.com/rag/time-series-and-agricultural-rag/)

## Builds on (most cited first, 18 of 18)

- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Multilingual E5 Text Embeddings: A Technical Report](https://mlsanity.com/paper/2402.05672/) (2024)
- [Mr. TyDi: A Multi-lingual Benchmark for Dense Retrieval](https://mlsanity.com/paper/2108.08787/) (2021)
- [RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2407.11005/) (2024)
- [BenLLMEval: A Comprehensive Evaluation into the Potentials and Pitfalls of Large Language Models on Bengali NLP](https://mlsanity.com/paper/2309.13173/) (2023)
- [GaRAGe: A Benchmark with Grounding Annotations for RAG Evaluation](https://mlsanity.com/paper/2506.07671/) (2025)
- [TigerLLM - A Family of Bangla Large Language Models](https://mlsanity.com/paper/2503.10995/) (2025)
- [Farmer.Chat: Scaling AI-Powered Agricultural Services for Smallholder Farmers](https://mlsanity.com/paper/2409.08916/) (2024)
- [Dense Retrieval for Low Resource Languages -- the Case of Amharic Language](https://mlsanity.com/paper/2503.18570/) (2025)
- [Improving Semantic Proximity in Information Retrieval through Cross-Lingual Alignment](https://mlsanity.com/paper/2604.05684/) (2026)
- [CLEAR: Cross-Lingual Enhancement in Alignment via Reverse-training](https://mlsanity.com/paper/2604.05821/) (2026)
- [Cost-Efficient Cross-Lingual Retrieval-Augmented Generation for Low-Resource Languages: A Case Study in Bengali Agricultural Advisory](https://mlsanity.com/paper/2601.02065/) (2026)
- [Coverage, Not Averages: Semantic Stratification for Trustworthy Retrieval Evaluation](https://mlsanity.com/paper/2604.20763/) (2026)
- [Cross-genre Document Retrieval: Matching between Conversational and Formal Writings](https://mlsanity.com/paper/1707.04538/) (2017)
- [What are the limits of cross-lingual dense passage retrieval for low-resource languages?](https://mlsanity.com/paper/2408.11942/) (2024)
- [KrishokBondhu: A Retrieval-Augmented Voice-Based Agricultural Advisory Call Center for Bengali Farmers](https://mlsanity.com/paper/2510.18355/) (2025)
- [KrishokChat: A Provenance-Traceable Multi-Task Bengali Agricultural Benchmark with Safety-Critical Chemical Advisory](https://mlsanity.com/paper/2606.29243/) (2026)

## Abstract (arXiv)

Retrieval quality in RAG systems is commonly reported as a single aggregate score, which can hide large differences across query types and language conditions. We study this problem in Bengali agricultural advisory, where farmer queries are often colloquial while official advisory documents use formal scientific terminology. We construct a test collection of 1,000 queries and 2,882 knowledge nodes extracted from 284 official Bangladeshi agricultural publications, and use it to evaluate five retrieval architectures and six embedding models under three controlled language conditions. The results show that no single retrieval method is consistently best. For native Bengali queries, BM25 is the strongest single retriever (R@10 = 0.506) while Hybrid RRF reaches the highest overall R@10 of 0.539. However, dense retrieval performance varies sharply by query type: R@10 is 0.093 on colloquial farmer queries and 0.970 on formal safety queries. Across language conditions, BM25 R@10 drops from 0.506 on Bengali queries to 0.004 when English queries are matched against the Bengali corpus, while dense retrieval falls only from 0.464 to 0.425. We also find that embedding task configuration and passage length can each change reported R@10 by a factor of seven, independent of architecture. These results show why low-resource RAG evaluation should report performance by language condition and query type rather than relying on aggregate scores alone. The dataset and evaluation scripts are available at https://huggingface.co/datasets/RaiyanKhaan/AgriTrust-RAG.