A thorough benchmark of automatic text classification: From traditional approaches to large language models

• URL: http://arxiv.org/abs/2504.01930v1
• Date: Wed, 02 Apr 2025 17:40:08 GMT
• Title: A thorough benchmark of automatic text classification: From traditional approaches to large language models
• Authors: Washington Cunha, Leonardo Rocha, Marcos André Gonçalves,
• Abstract summary: This study investigates whether the effectiveness gains of recent approaches compensate their much higher costs.<n>It includes a scientifically sound comparative analysis of the cost-benefit of twelve traditional and recent ATC solutions.<n>The release of code, data, and documentation enables the community to replicate experiments and advance the field.
• Score: 9.069939079065298
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Automatic text classification (ATC) has experienced remarkable advancements in the past decade, best exemplified by recent small and large language models (SLMs and LLMs), leveraged by Transformer architectures. Despite recent effectiveness improvements, a comprehensive cost-benefit analysis investigating whether the effectiveness gains of these recent approaches compensate their much higher costs when compared to more traditional text classification approaches such as SVMs and Logistic Regression is still missing in the literature. In this context, this work's main contributions are twofold: (i) we provide a scientifically sound comparative analysis of the cost-benefit of twelve traditional and recent ATC solutions including five open LLMs, and (ii) a large benchmark comprising {22 datasets}, including sentiment analysis and topic classification, with their (train-validation-test) partitions based on folded cross-validation procedures, along with documentation, and code. The release of code, data, and documentation enables the community to replicate experiments and advance the field in a more scientifically sound manner. Our comparative experimental results indicate that LLMs outperform traditional approaches (up to 26%-7.1% on average) and SLMs (up to 4.9%-1.9% on average) in terms of effectiveness. However, LLMs incur significantly higher computational costs due to fine-tuning, being, on average 590x and 8.5x slower than traditional methods and SLMs, respectively. Results suggests the following recommendations: (1) LLMs for applications that require the best possible effectiveness and can afford the costs; (2) traditional methods such as Logistic Regression and SVM for resource-limited applications or those that cannot afford the cost of tuning large LLMs; and (3) SLMs like Roberta for near-optimal effectiveness-efficiency trade-off.

Related papers

• Reward-Guided Speculative Decoding for Efficient LLM Reasoning [80.55186052123196]
  We introduce Reward-Guided Speculative Decoding (RSD), a novel framework aimed at improving the efficiency of inference in large language models (LLMs) RSD incorporates a controlled bias to prioritize high-reward outputs, in contrast to existing speculative decoding methods that enforce strict unbiasedness. RSD delivers significant efficiency gains against decoding with the target model only, while achieving significant better accuracy than parallel decoding method on average.
  arXiv  Detail & Related papers  (2025-01-31T17:19:57Z)
• LLM2: Let Large Language Models Harness System 2 Reasoning [65.89293674479907]
  Large language models (LLMs) have exhibited impressive capabilities across a myriad of tasks, yet they occasionally yield undesirable outputs.<n>We introduce LLM2, a novel framework that combines an LLM with a process-based verifier.<n>LLMs2 is responsible for generating plausible candidates, while the verifier provides timely process-based feedback to distinguish desirable and undesirable outputs.
  arXiv  Detail & Related papers  (2024-12-29T06:32:36Z)
• Adaptive Pruning for Large Language Models with Structural Importance Awareness [66.2690963378878]
  Large language models (LLMs) have significantly improved language understanding and generation capabilities.<n>LLMs are difficult to deploy on resource-constrained edge devices due to their high computational and storage resource demands.<n>We propose structurally-aware adaptive pruning (SAAP) to significantly reduce the computational and memory costs while maintaining model performance.
  arXiv  Detail & Related papers  (2024-12-19T18:08:04Z)
• AutoElicit: Using Large Language Models for Expert Prior Elicitation in Predictive Modelling [53.54623137152208]
  We introduce AutoElicit to extract knowledge from large language models and construct priors for predictive models.<n>We show these priors are informative and can be refined using natural language.<n>We find that AutoElicit yields priors that can substantially reduce error over uninformative priors, using fewer labels, and consistently outperform in-context learning.
  arXiv  Detail & Related papers  (2024-11-26T10:13:39Z)
• A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs [74.35290684163718]
  A primary challenge in large language model (LLM) development is their onerous pre-training cost. This paper explores a promising paradigm to improve LLM pre-training efficiency and quality by leveraging a small language model (SLM)
  arXiv  Detail & Related papers  (2024-10-24T14:31:52Z)
• Achieving Peak Performance for Large Language Models: A Systematic Review [0.0]
  Large language models (LLMs) have achieved remarkable success in natural language processing (NLP) As models grow into the trillion- parameter range, computational and memory costs increase significantly. This makes it difficult for many researchers to access the resources needed to train or apply these models.
  arXiv  Detail & Related papers  (2024-09-07T13:57:41Z)
• PoliPrompt: A High-Performance Cost-Effective LLM-Based Text Classification Framework for Political Science [1.6967824074619953]
  This paper introduces a three-stage in-context learning approach that leverages large language models to improve classification accuracy. We validate our approach using datasets from the BBC news reports, Kavanaugh Supreme Court confirmation, and 2018 election campaign ads. The results show significant improvements in classification F1 score (+0.36 for zero-shot classification) with manageable economic costs.
  arXiv  Detail & Related papers  (2024-09-02T21:05:31Z)
• LLMs vs Established Text Augmentation Techniques for Classification: When do the Benefits Outweight the Costs? [2.7820774076399957]
  We compare effects of recent LLM augmentation methods with established ones on 6 datasets, 3 classifiers and 2 fine-tuning methods. We show that LLM-based methods are worthy of deployment only when very small number of seeds is used.
  arXiv  Detail & Related papers  (2024-08-29T13:01:42Z)
• LLMEmbed: Rethinking Lightweight LLM's Genuine Function in Text Classification [13.319594321038926]
  We propose a simple and effective transfer learning strategy, namely LLMEmbed, to address this classical but challenging task. We perform extensive experiments on publicly available datasets, and the results show that LLMEmbed achieves strong performance while enjoys low training overhead.
  arXiv  Detail & Related papers  (2024-06-06T03:46:59Z)
• Learning from Litigation: Graphs and LLMs for Retrieval and Reasoning in eDiscovery [6.037276428689637]
  This paper introduces DISCOvery Graph (DISCOG), a hybrid approach that combines the strengths of two worlds: a graph-based method for accurate document relevance prediction. Our approach drastically reduces document review costs by 99.9% compared to manual processes and by 95% compared to LLM-based classification methods.
  arXiv  Detail & Related papers  (2024-05-29T15:08:55Z)
• RepEval: Effective Text Evaluation with LLM Representation [55.26340302485898]
  RepEval is a metric that leverages the projection of Large Language Models (LLMs) representations for evaluation. Our work underscores the richness of information regarding text quality embedded within LLM representations, offering insights for the development of new metrics.
  arXiv  Detail & Related papers  (2024-04-30T13:50:55Z)
• ChatGPT Based Data Augmentation for Improved Parameter-Efficient Debiasing of LLMs [65.9625653425636]
  Large Language models (LLMs) exhibit harmful social biases. This work introduces a novel approach utilizing ChatGPT to generate synthetic training data.
  arXiv  Detail & Related papers  (2024-02-19T01:28:48Z)
• Making LLMs Worth Every Penny: Resource-Limited Text Classification in Banking [3.9412826185755017]
  Few-shot and large language models (LLMs) can perform effectively with just 1-5 examples per class. Our work addresses the performance-cost trade-offs of these methods over the Banking77 financial intent detection dataset. To inspire future research, we provide a human expert's curated subset of Banking77, along with extensive error analysis.
  arXiv  Detail & Related papers  (2023-11-10T15:10:36Z)

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.