Are LLMs Enough for Hyperpartisan, Fake, Polarized and Harmful Content Detection? Evaluating In-Context Learning vs. Fine-Tuning

• URL: http://arxiv.org/abs/2509.07768v1
• Date: Tue, 09 Sep 2025 14:01:15 GMT
• Title: Are LLMs Enough for Hyperpartisan, Fake, Polarized and Harmful Content Detection? Evaluating In-Context Learning vs. Fine-Tuning
• Authors: Michele Joshua Maggini, Dhia Merzougui, Rabiraj Bandyopadhyay, Gaël Dias, Fabrice Maurel, Pablo Gamallo,
• Abstract summary: This study presents an overview of different Large Language Models adaptation paradigms for the detection of hyperpartisan and fake news, harmful tweets, and political bias.<n>We tested different strategies ranging from parameter efficient Fine-Tuning of language models to a variety of different In-Context Learning strategies and prompts.
• Score: 20.193445005516363
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The spread of fake news, polarizing, politically biased, and harmful content on online platforms has been a serious concern. With large language models becoming a promising approach, however, no study has properly benchmarked their performance across different models, usage methods, and languages. This study presents a comprehensive overview of different Large Language Models adaptation paradigms for the detection of hyperpartisan and fake news, harmful tweets, and political bias. Our experiments spanned 10 datasets and 5 different languages (English, Spanish, Portuguese, Arabic and Bulgarian), covering both binary and multiclass classification scenarios. We tested different strategies ranging from parameter efficient Fine-Tuning of language models to a variety of different In-Context Learning strategies and prompts. These included zero-shot prompts, codebooks, few-shot (with both randomly-selected and diversely-selected examples using Determinantal Point Processes), and Chain-of-Thought. We discovered that In-Context Learning often underperforms when compared to Fine-Tuning a model. This main finding highlights the importance of Fine-Tuning even smaller models on task-specific settings even when compared to the largest models evaluated in an In-Context Learning setup - in our case LlaMA3.1-8b-Instruct, Mistral-Nemo-Instruct-2407 and Qwen2.5-7B-Instruct.

Related papers

• Large Language Models For Text Classification: Case Study And Comprehensive Review [0.3428444467046467]
  We evaluate the performance of different Large Language Models (LLMs) in comparison with state-of-the-art deep-learning and machine-learning models.<n>Our work reveals significant variations in model responses based on the prompting strategies.
  arXiv  Detail & Related papers  (2025-01-14T22:02:38Z)
• The Impact of Model Scaling on Seen and Unseen Language Performance [2.012425476229879]
  We study the performance and scaling behavior of multilingual Large Language Models across 204 languages.<n>Our findings show significant differences in scaling behavior between zero-shot and two-shot scenarios.<n>In two-shot settings, larger models show clear linear improvements in multilingual text classification.
  arXiv  Detail & Related papers  (2025-01-10T00:10:21Z)
• Language Models for Text Classification: Is In-Context Learning Enough? [54.869097980761595]
  Recent foundational language models have shown state-of-the-art performance in many NLP tasks in zero- and few-shot settings. An advantage of these models over more standard approaches is the ability to understand instructions written in natural language (prompts) This makes them suitable for addressing text classification problems for domains with limited amounts of annotated instances.
  arXiv  Detail & Related papers  (2024-03-26T12:47:39Z)
• The Impact of Demonstrations on Multilingual In-Context Learning: A Multidimensional Analysis [23.757767581876063]
  In-context learning is a popular inference strategy where large language models solve a task using only a few labeled demonstrations. We show that the effectiveness of demonstrations varies significantly across models, tasks, and languages. We also find that strong instruction-following models including Llama 2-Chat, GPT-3.5, and GPT-4 are largely insensitive to the quality of demonstrations.
  arXiv  Detail & Related papers  (2024-02-20T12:53:31Z)
• Beyond Contrastive Learning: A Variational Generative Model for Multilingual Retrieval [109.62363167257664]
  We propose a generative model for learning multilingual text embeddings. Our model operates on parallel data in $N$ languages. We evaluate this method on a suite of tasks including semantic similarity, bitext mining, and cross-lingual question retrieval.
  arXiv  Detail & Related papers  (2022-12-21T02:41:40Z)
• A Multi-level Supervised Contrastive Learning Framework for Low-Resource Natural Language Inference [54.678516076366506]
  Natural Language Inference (NLI) is a growingly essential task in natural language understanding. Here we propose a multi-level supervised contrastive learning framework named MultiSCL for low-resource natural language inference.
  arXiv  Detail & Related papers  (2022-05-31T05:54:18Z)
• Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units [56.52704348773307]
  We propose a novel LSTM-based generative speech LM based on linguistic units including syllables and phonemes. With a limited dataset, orders of magnitude smaller than that required by contemporary generative models, our model closely approximates babbling speech. We show the effect of training with auxiliary text LMs, multitask learning objectives, and auxiliary articulatory features.
  arXiv  Detail & Related papers  (2021-10-31T22:48:30Z)
• Sentiment analysis in tweets: an assessment study from classical to modern text representation models [59.107260266206445]
  Short texts published on Twitter have earned significant attention as a rich source of information. Their inherent characteristics, such as the informal, and noisy linguistic style, remain challenging to many natural language processing (NLP) tasks. This study fulfils an assessment of existing language models in distinguishing the sentiment expressed in tweets by using a rich collection of 22 datasets.
  arXiv  Detail & Related papers  (2021-05-29T21:05:28Z)
• Comparison of Interactive Knowledge Base Spelling Correction Models for Low-Resource Languages [81.90356787324481]
  Spelling normalization for low resource languages is a challenging task because the patterns are hard to predict. This work shows a comparison of a neural model and character language models with varying amounts on target language data. Our usage scenario is interactive correction with nearly zero amounts of training examples, improving models as more data is collected.
  arXiv  Detail & Related papers  (2020-10-20T17:31:07Z)
• Zero-Shot Cross-Lingual Transfer with Meta Learning [45.29398184889296]
  We consider the setting of training models on multiple languages at the same time, when little or no data is available for languages other than English. We show that this challenging setup can be approached using meta-learning. We experiment using standard supervised, zero-shot cross-lingual, as well as few-shot cross-lingual settings for different natural language understanding tasks.
  arXiv  Detail & Related papers  (2020-03-05T16:07:32Z)

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.