Gradient Masters at BLP-2025 Task 1: Advancing Low-Resource NLP for Bengali using Ensemble-Based Adversarial Training for Hate Speech Detection

• URL: http://arxiv.org/abs/2511.18324v1
• Date: Sun, 23 Nov 2025 07:29:09 GMT
• Title: Gradient Masters at BLP-2025 Task 1: Advancing Low-Resource NLP for Bengali using Ensemble-Based Adversarial Training for Hate Speech Detection
• Authors: Syed Mohaiminul Hoque, Naimur Rahman, Md Sakhawat Hossain,
• Abstract summary: We present an ensemble-based fine-tuning strategy for addressing subtasks 1A (hate-type classification) and 1B (target group classification) in YouTube comments.<n>We propose a hybrid approach on a Bangla Language Model, which outperformed the baseline models and secured the 6th position in subtask 1A.
• Score: 1.2744523252873352
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper introduces the approach of "Gradient Masters" for BLP-2025 Task 1: "Bangla Multitask Hate Speech Identification Shared Task". We present an ensemble-based fine-tuning strategy for addressing subtasks 1A (hate-type classification) and 1B (target group classification) in YouTube comments. We propose a hybrid approach on a Bangla Language Model, which outperformed the baseline models and secured the 6th position in subtask 1A with a micro F1 score of 73.23% and the third position in subtask 1B with 73.28%. We conducted extensive experiments that evaluated the robustness of the model throughout the development and evaluation phases, including comparisons with other Language Model variants, to measure generalization in low-resource Bangla hate speech scenarios and data set coverage. In addition, we provide a detailed analysis of our findings, exploring misclassification patterns in the detection of hate speech.

Related papers

• SyntaxMind at BLP-2025 Task 1: Leveraging Attention Fusion of CNN and GRU for Hate Speech Detection [0.0]
  This paper describes our system used in the BLP-2025 Task 1: Hate Speech Detection.<n>Our approach integrates BanglaBERT embeddings with multiple parallel processing branches based on GRUs and CNNs, followed by attention and dense layers for final classification.<n>The proposed system demonstrated high competitiveness, obtaining 0.7345 micro F1-Score (2nd place) in Subtask 1A and 0.7317 micro F1-Score (5th place) in Subtask 1B.
  arXiv  Detail & Related papers  (2026-01-09T20:54:54Z)
• Retriv at BLP-2025 Task 1: A Transformer Ensemble and Multi-Task Learning Approach for Bangla Hate Speech Identification [7.459430148112738]
  This paper addresses the problem of Bangla hate speech identification, a socially impactful yet linguistically challenging task.<n>Our team "Retriv" participated in all three subtasks: (1A) hate type classification, (1B) target group identification, and (1C) joint detection of type, severity, and target.<n>Our systems achieved micro-f1 scores of 72.75% (1A) and 72.69% (1B), and a weighted micro-f1 score of 72.62% (1C)
  arXiv  Detail & Related papers  (2025-11-10T17:07:09Z)
• SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment [78.4550589538805]
  We propose an efficient multilingual reasoning alignment approach that precisely identifies and fine-tunes the layers responsible for handling multilingualism.<n> Experimental results show that our method, SLAM, only tunes 6 layers' feed-forward sub-layers including 6.5-8% of all parameters within 7B and 13B LLMs.
  arXiv  Detail & Related papers  (2025-01-07T10:29:43Z)
• Mavericks at BLP-2023 Task 1: Ensemble-based Approach Using Language Models for Violence Inciting Text Detection [0.0]
  Social media has accelerated the propagation of hate and violence-inciting speech in society. The problem of detecting violence-inciting texts is further exacerbated in low-resource settings due to sparse research and less data. This paper presents our work for the Violence Inciting Text Detection shared task in the First Workshop on Bangla Language Processing.
  arXiv  Detail & Related papers  (2023-11-30T18:23:38Z)
• nlpBDpatriots at BLP-2023 Task 1: A Two-Step Classification for Violence Inciting Text Detection in Bangla [7.3481279783709805]
  In this paper, we discuss the nlpBDpatriots entry to the shared task on Violence Inciting Text Detection (VITD) The aim of this task is to identify and classify the violent threats, that provoke further unlawful violent acts. Our best-performing approach for the task is two-step classification using back translation and multilinguality which ranked 6th out of 27 teams with a macro F1 score of 0.74.
  arXiv  Detail & Related papers  (2023-11-25T13:47:34Z)
• BanglaNLP at BLP-2023 Task 1: Benchmarking different Transformer Models for Violence Inciting Text Detection in Bengali [0.46040036610482665]
  This paper presents the system that we have developed while solving this shared task on violence inciting text detection in Bangla. We explain both the traditional and the recent approaches that we used to make our models learn. Our proposed system helps to classify if the given text contains any threat.
  arXiv  Detail & Related papers  (2023-10-16T19:35:04Z)
• Bag of Tricks for Effective Language Model Pretraining and Downstream Adaptation: A Case Study on GLUE [93.98660272309974]
  This report briefly describes our submission Vega v1 on the General Language Understanding Evaluation leaderboard. GLUE is a collection of nine natural language understanding tasks, including question answering, linguistic acceptability, sentiment analysis, text similarity, paraphrase detection, and natural language inference. With our optimized pretraining and fine-tuning strategies, our 1.3 billion model sets new state-of-the-art on 4/9 tasks, achieving the best average score of 91.3.
  arXiv  Detail & Related papers  (2023-02-18T09:26:35Z)
• Rethinking the Role of Scale for In-Context Learning: An Interpretability-based Case Study at 66 Billion Scale [60.336655143884904]
  We investigate the hypothesis that the ability of a large language model to in-context learn-perform a task is not uniformly spread across its underlying components. We find substantial overlap in the set of attention heads (unimportant) for in-context learning across tasks and number of in-context examples.
  arXiv  Detail & Related papers  (2022-12-18T14:36:07Z)
• Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE [203.65227947509933]
  This report describes our JDExplore d-team's Vega v2 submission on the SuperGLUE leaderboard. SuperGLUE is more challenging than the widely used general language understanding evaluation (GLUE) benchmark, containing eight difficult language understanding tasks.
  arXiv  Detail & Related papers  (2022-12-04T15:36:18Z)
• HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units [81.53783563025084]
  We propose an offline clustering step to provide aligned target labels for a BERT-like prediction loss. A key ingredient of our approach is applying the prediction loss over the masked regions only. HuBERT shows up to 19% and 13% relative WER reduction on the more challenging dev-other and test-other evaluation subsets.
  arXiv  Detail & Related papers  (2021-06-14T14:14:28Z)
• GUIR at SemEval-2020 Task 12: Domain-Tuned Contextualized Models for Offensive Language Detection [27.45642971636561]
  OffensEval 2020 task includes three English sub-tasks: identifying the presence of offensive language (Sub-task A), identifying the presence of target in offensive language (Sub-task B), and identifying the categories of the target (Sub-task C) Our submissions achieve F1 scores of 91.7% in Sub-task A, 66.5% in Sub-task B, and 63.2% in Sub-task C.
  arXiv  Detail & Related papers  (2020-07-28T20:45:43Z)
• Kungfupanda at SemEval-2020 Task 12: BERT-Based Multi-Task Learning for Offensive Language Detection [55.445023584632175]
  We build an offensive language detection system, which combines multi-task learning with BERT-based models. Our model achieves 91.51% F1 score in English Sub-task A, which is comparable to the first place.
  arXiv  Detail & Related papers  (2020-04-28T11:27:24Z)

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.