---
title: Abstract Classification: SVM vs BERT vs GPT-3.5
url: https://www.ml-quant.com/papers/repec/spr-scient-v-130-y-2025-i-1-d-10-1007-s11192-024-05217-7/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: RePEc:spr:scient:v:130:y:2025:i:1:d:10.1007_s11192-024-05217-7
source_url: https://econpapers.repec.org/scripts/redir.pf?u=http%3A%2F%2Flink.springer.com%2F10.1007%2Fs11192-024-05217-7%3Bh%3Drepec%3Aspr%3Ascient%3Av%3A130%3Ay%3A2025%3Ai%3A1%3Ad%3A10.1007_s11192-024-05217-7
featured: 2025-10-27
citations: unknown
topic: LLMs & Text
---


# Abstract Classification: SVM vs BERT vs GPT-3.5

SVM vs BERT vs GPT-3.5: Compares SVM, SPECTER, BERT, and GPT-3.5 for classifying abstracts: BERT performs best, while GPT-3.5 is inconsistent with limited training data.

- Source: https://econpapers.repec.org/scripts/redir.pf?u=http%3A%2F%2Flink.springer.com%2F10.1007%2Fs11192-024-05217-7%3Bh%3Drepec%3Aspr%3Ascient%3Av%3A130%3Ay%3A2025%3Ai%3A1%3Ad%3A10.1007_s11192-024-05217-7
- Identifier: RePEc:spr:scient:v:130:y:2025:i:1:d:10.1007_s11192-024-05217-7
- Released: 2025-10-27
- First featured: Quant Letter No. 117 (2025-10-27): https://www.ml-quant.com/issues/2025-10-27/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: LLMs & Text

## Related

- [Planning In Natural Language Improves LLM Search For Code Generation](https://www.ml-quant.com/papers/arxiv/2409.03733/): PLANSEARCH is a new search algorithm that creates diverse solutions for natural language problems, outperforming traditional methods in various benchmarks.
- [AmbigNLG: Addressing Task Ambiguity in Instruction for NLG](https://www.ml-quant.com/papers/arxiv/2402.17717/): Task Ambiguity in NLG: AmbigNLG, a new task and dataset, tackles task ambiguity in instructions for Natural Language Generation, improving the alignment of generated text with user expectations and boosting the performance of Large Language Models.
- [SYNTHEVAL: Hybrid Behavioral Testing of NLP Models with Synthetic CheckLists](https://www.ml-quant.com/papers/arxiv/2408.17437/): SYNTHEVAL is a testing framework that uses large language models to generate tests for evaluating NLP models, particularly in sentiment analysis and toxic language detection.
- [Beyond Scale: The Diversity Coefficient as a Data Quality Metric for Variability in Natural Language Data](https://www.ml-quant.com/papers/arxiv/2306.13840/): The study introduces a measure called the diversity coefficient to formalize data quality in pre-training Large Language Models (LLMs), demonstrating its alignment with diversity and variability properties, and its usefulness in evaluating downstream model performance.
- [Arrows of Time for Large Language Models](https://www.ml-quant.com/papers/arxiv/2401.17505/): A study shows a time asymmetry in Autoregressive Large Language Models' ability to learn natural language, explained by sparsity and computational complexity.
- [BioFinBERT: Finetuning Large Language Models (LLMs) to Analyze Sentiment of Press Releases and Financial Text Around Inflection Points of Biotech Stocks](https://www.ml-quant.com/papers/arxiv/2401.11011/): LLMs for Financial Sentiment Analysis: BioFinBERT, a finetuned Large Language Model, is introduced for financial sentiment analysis of biotech press releases and financial texts, which greatly impact biotech stock prices.