# Beyond Clean Text: Evaluating Encoder and Decoder Robustness for Bangla Event Detection in Noisy Text

arXiv: https://arxiv.org/abs/2606.30914 · HTML: https://mlsanity.com/paper/2606.30914/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 39 references that are in the map.
- First posted on arXiv 29 Jun 2026.

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

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla](https://mlsanity.com/paper/2101.00204/) (2021)
- [GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction](https://mlsanity.com/paper/2310.03668/) (2023)
- [MAVEN: A Massive General Domain Event Detection Dataset](https://mlsanity.com/paper/2004.13590/) (2020)
- [Multi-Sentence Argument Linking](https://mlsanity.com/paper/1911.03766/) (2019)
- [Code4Struct: Code Generation for Few-Shot Event Structure Prediction](https://mlsanity.com/paper/2210.12810/) (2022)
- [Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing](https://mlsanity.com/paper/2101.03289/) (2021)
- [A Network Perspective on Stratification of Multi-Label Data](https://mlsanity.com/paper/1704.08756/) (2017)
- [LEVEN: A Large-Scale Chinese Legal Event Detection Dataset](https://mlsanity.com/paper/2203.08556/) (2022)
- [Guideline Learning for In-context Information Extraction](https://mlsanity.com/paper/2310.05066/) (2023)
- [Instruction-Tuning LLMs for Event Extraction with Annotation Guidelines](https://mlsanity.com/paper/2502.16377/) (2025)
- [Explicit, Implicit, and Scattered: Revisiting Event Extraction to Capture Complex Arguments](https://mlsanity.com/paper/2410.03594/) (2024)
- [MINION: a Large-Scale and Diverse Dataset for Multilingual Event Detection](https://mlsanity.com/paper/2211.05958/) (2022)
- [Synthetic Error Dataset Generation Mimicking Bengali Writing Pattern](https://mlsanity.com/paper/2003.03484/) (2020)
- [A Comparative Analysis of Noise Reduction Methods in Sentiment Analysis on Noisy Bangla Texts](https://mlsanity.com/paper/2401.14360/) (2024)
- [Event Detection with a Context-Aware Encoder and LoRA for Improved Performance on Long-Tailed Classes](https://mlsanity.com/paper/2601.11932/) (2026)

## Abstract (arXiv)

Event detection (ED) systems are typically evaluated on clean, curated text, leaving their robustness to real-world noise largely unexplored, particularly for low-resource languages such as Bangla. We introduce a generalized Bangla news event ontology and a benchmark comprising 9,979 annotated sentences across 40 event subtypes, spanning clean news text, real-world Automatic Speech Recognition (ASR) transcripts, and orthographically corrupted text. We systematically evaluate fine-tuned encoder-only models (BanglaBERT and XLM-R) alongside instruction-tuned decoder-only large language models (Llama 3 and Gemma 3). Our results reveal a clear architectural trade-off: encoder models achieve higher performance on clean text but degrade substantially under noise, whereas decoder-only LLMs are markedly more robust, particularly when event triggers are corrupted. We further show that embedding annotation guidelines during instruction tuning establishes a higher performance baseline on noisy text but yields inconsistent reductions in performance degradation across noisy conditions. Finally, model scaling consistently improves the robustness of decoder-only LLMs, while combined training on clean and noisy data serves as an effective regularization strategy that disproportionately benefits encoder architectures, significantly narrowing the robustness gap.