mlsanityData to 14 Oct 2026

Zero- and Few-Shot Prompting with LLMs: A Comparative Study with Fine-tuned Models for Bangla Sentiment Analysis

arXiv 2308.10783 ↗First posted 21 Aug 2023cs.CL cs.LGcited by 20

Not on the map. Why?

Abstract (arXiv)

The rapid expansion of the digital world has propelled sentiment analysis into a critical tool across diverse sectors such as marketing, politics, customer service, and healthcare. While there have been significant advancements in sentiment analysis for widely spoken languages, low-resource languages, such as Bangla, remain largely under-researched due to resource constraints. Furthermore, the recent unprecedented performance of Large Language Models (LLMs) in various applications highlights the need to evaluate them in the context of low-resource languages. In this study, we present a sizeable manually annotated dataset encompassing 33,606 Bangla news tweets and Facebook comments. We also investigate zero- and few-shot in-context learning with several language models, including Flan-T5, GPT-4, and Bloomz, offering a comparative analysis against fine-tuned models. Our findings suggest that monolingual transformer-based models consistently outperform other models, even in zero and few-shot scenarios. To foster continued exploration, we intend to make this dataset and our research tools publicly available to the broader research community.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 22 of its 54 references that are in the map. First posted on arXiv 21 Aug 2023.

Builds on

22 of 54 references.

References · 22

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  5. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  6. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  7. 2023A Survey of Large Language Modelscited by 2,576
  8. 2023MEGA: Multilingual Evaluation of Generative AIcited by 293
  9. 2022PromptSource: An Integrated Development Environment and Repository for Natural Language Promptscited by 289
  10. 2019SemEval-2017 Task 4: Sentiment Analysis in Twittercited by 210
  11. 2021BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Banglacited by 125
  12. 2021XLM-T: Multilingual Language Models in Twitter for Sentiment Analysis and Beyondcited by 114
10 more
  1. 2022Complementary Explanations for Effective In-Context Learningcited by 71
  2. 2023AfriSenti: A Twitter Sentiment Analysis Benchmark for African Languagescited by 68
  3. 2021HumAID: Human-Annotated Disaster Incidents Data from Twitter with Deep Learning Benchmarkscited by 39
  4. 2020Classification Benchmarks for Under-resourced Bengali Language based on Multichannel Convolutional-LSTM Networkcited by 30
  5. 2023LLMeBench: A Flexible Framework for Accelerating LLMs Benchmarkingcited by 20
  6. 2022MSCTD: A Multimodal Sentiment Chat Translation Datasetcited by 15
  7. 2023BanglaBook: A Large-scale Bangla Dataset for Sentiment Analysis from Book Reviewscited by 14
  8. 2021A Review of Bangla Natural Language Processing Tasks and the Utility of Transformer Modelscited by 13
  9. 2020Sentiment Classification in Bangla Textual Content: A Comparative Studycited by 8
  10. 2023SentiGOLD: A Large Bangla Gold Standard Multi-Domain Sentiment Analysis Dataset and its Evaluationcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 6; 2024: 3; 2025: 8; 2026: 3.

20 papers.

Sort:

By area:

  1. 2025LLaMAs Have Feelings Too: Unveiling Sentiment and Emotion Representations in LLaMA Models Through Probingcited by 15
  2. 2024Better to Ask in English: Evaluation of Large Language Models on English, Low-resource and Cross-Lingual Settingscited by 14
  3. 2025TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarkingcited by 9
  4. 2023BLP-2023 Task 2: Sentiment Analysiscited by 7
  5. 2023Crosslingual Retrieval Augmented In-context Learning for Banglacited by 7
  6. 2024Harnessing Large Language Models Over Transformer Models for Detecting Bengali Depressive Social Media Text: A Comprehensive Studycited by 6
  7. 2024Do Large Language Models Speak All Languages Equally? A Comparative Study in Low-Resource Settingscited by 6
  8. 2023LowResource at BLP-2023 Task 2: Leveraging BanglaBert for Low Resource Sentiment Analysis of Bangla Languagecited by 3
  9. 2025Parameter-Efficient Fine-Tuning for Low-Resource Languages: A Comparative Study of LLMs for Bengali Hate Speech Detectioncited by 3
  10. 2023nlpBDpatriots at BLP-2023 Task 2: A Transfer Learning Approach to Bangla Sentiment Analysiscited by 2
  11. 2023RSM-NLP at BLP-2023 Task 2: Bangla Sentiment Analysis using Weighted and Majority Voted Fine-Tuned Transformerscited by 1
  12. 2026MultiSoc-4D: A Benchmark for Diagnosing Instruction-Induced Label Collapse in Closed-Set LLM Annotation of Bengali Social Mediacited by 1
8 more
  1. 2023BanglaNLP at BLP-2023 Task 2: Benchmarking different Transformer Models for Sentiment Analysis of Bangla Social Media Postscited by 0
  2. 2025Random Forest-of-Thoughts: Uncertainty-aware Reasoning for Computational Social Sciencecited by 0
  3. 2025HausaNLP at SemEval-2025 Task 11: Hausa Text Emotion Detectioncited by 0
  4. 2025PromptGuard at BLP-2025 Task 1: A Few-Shot Classification Framework Using Majority Voting and Keyword Similarity for Bengali Hate Speech Detectioncited by 0
  5. 2025AI-Powered Early Diagnosis of Mental Health Disorders from Real-World Clinical Conversationscited by 0
  6. 2025Accelerating Bangla NLP Tasks with Automatic Mixed Precision: Resource-Efficient Training Preserving Model Efficacycited by 0
  7. 2026AnnoABSA: A Web-Based Annotation Tool for Aspect-Based Sentiment Analysis with Retrieval-Augmented Suggestionscited by 0
  8. 2026Prompting Is All You Need: Multi-view Prompting Large Language Models for Aspect-Based Sentiment Analysiscited by 0