Build, Borrow, or Just Fine-Tune? A Political Scientist's Guide to Choosing NLP Models

• URL: http://arxiv.org/abs/2603.09595v1
• Date: Tue, 10 Mar 2026 12:42:12 GMT
• Title: Build, Borrow, or Just Fine-Tune? A Political Scientist's Guide to Choosing NLP Models
• Abstract summary: Political scientists increasingly face a consequential choice when adopting natural language processing tools.<n>Each approach occupies a different point on the spectrum of performance, cost, and required expertise.<n>This paper provides empirical guidance on how to navigate this trade-off.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Political scientists increasingly face a consequential choice when adopting natural language processing tools: build a domain-specific model from scratch, borrow and adapt an existing one, or simply fine-tune a general-purpose model on task data? Each approach occupies a different point on the spectrum of performance, cost, and required expertise, yet the discipline has offered little empirical guidance on how to navigate this trade-off. This paper provides such guidance. Using conflict event classification as a test case, I fine-tune ModernBERT on the Global Terrorism Database (GTD) to create Confli-mBERT and systematically compare it against ConfliBERT, a domain-specific pretrained model that represents the current gold standard. Confli-mBERT achieves 75.46% accuracy compared to ConfliBERT's 79.34%. Critically, the four-percentage-point gap is not uniform: on high-frequency attack types such as Bombing/Explosion (F1 = 0.95 vs. 0.96) and Kidnapping (F1 = 0.92 vs. 0.91), the models are nearly indistinguishable. Performance differences concentrate in rare event categories comprising fewer than 2% of all incidents. I use these findings to develop a practical decision framework for political scientists considering any NLP-assisted research task: when does the research question demand a specialized model, and when does an accessible fine-tuned alternative suffice? The answer, I argue, depends not on which model is "better" in the abstract, but on the specific intersection of class prevalence, error tolerance, and available resources. The model, training code, and data are publicly available on Hugging Face.

Related papers

• How Hard is it to Confuse a World Model? [6.896797484250302]
  In reinforcement learning theory, the concept of most confusing instances is central to establishing regret lower bounds.<n>We formalize this problem for neural network world models as a constrained optimization.<n>Our results suggest that the degree of achievable confusion correlates with uncertainty in the approximate model.
  arXiv  Detail & Related papers  (2025-10-24T08:08:12Z)
• DISCO: Diversifying Sample Condensation for Efficient Model Evaluation [59.01400190971061]
  Costly evaluation reduces inclusivity, slows the cycle of innovation, and worsens environmental impact.<n>We argue that promoting diversity among samples is not essential; what matters is to select samples thatmaximise diversity in model responses.<n>Our method, $textbfDiversifying Sample Condensation (DISCO)$, selects the top-k samples with the greatest model disagreements.
  arXiv  Detail & Related papers  (2025-10-09T08:53:59Z)
• Confidence-Based Model Selection: When to Take Shortcuts for Subpopulation Shifts [119.22672589020394]
  We propose COnfidence-baSed MOdel Selection (CosMoS), where model confidence can effectively guide model selection. We evaluate CosMoS on four datasets with spurious correlations, each with multiple test sets with varying levels of data distribution shift.
  arXiv  Detail & Related papers  (2023-06-19T18:48:15Z)
• Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases [62.54519787811138]
  We present a simple but effective method to measure and mitigate model biases caused by reliance on spurious cues. We rank images within their classes based on spuriosity, proxied via deep neural features of an interpretable network. Our results suggest that model bias due to spurious feature reliance is influenced far more by what the model is trained on than how it is trained.
  arXiv  Detail & Related papers  (2022-12-05T23:15:43Z)
• A Differentiable Distance Approximation for Fairer Image Classification [31.471917430653626]
  We propose a differentiable approximation of the variance of demographics, a metric that can be used to measure the bias, or unfairness, in an AI model. Our approximation can be optimised alongside the regular training objective which eliminates the need for any extra models during training. We demonstrate that our approach improves the fairness of AI models in varied task and dataset scenarios.
  arXiv  Detail & Related papers  (2022-10-09T23:02:18Z)
• Resilience from Diversity: Population-based approach to harden models against adversarial attacks [0.0]
  This work introduces a model that is resilient to adversarial attacks. Our model leverages a well established principle from biological sciences: population diversity produces resilience against environmental changes. A Counter-Linked Model (CLM) consists of submodels of the same architecture where a periodic random similarity examination is conducted.
  arXiv  Detail & Related papers  (2021-11-19T15:22:21Z)
• Exploring Strategies for Generalizable Commonsense Reasoning with Pre-trained Models [62.28551903638434]
  We measure the impact of three different adaptation methods on the generalization and accuracy of models. Experiments with two models show that fine-tuning performs best, by learning both the content and the structure of the task, but suffers from overfitting and limited generalization to novel answers. We observe that alternative adaptation methods like prefix-tuning have comparable accuracy, but generalize better to unseen answers and are more robust to adversarial splits.
  arXiv  Detail & Related papers  (2021-09-07T03:13:06Z)
• Federated Multi-Armed Bandits [18.95281057580889]
  Federated multi-armed bandits (FMAB) is a new bandit paradigm that parallels the federated learning (FL) framework in supervised learning. This paper proposes a general framework of FMAB and then studies two specific federated bandit models. We show that, somewhat surprisingly, the order-optimal regret can be achieved independent of the number of clients with a careful choice of the update periodicity.
  arXiv  Detail & Related papers  (2021-01-28T18:59:19Z)
• How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering [80.82194311274694]
  We examine the question "how can we know when language models know, with confidence, the answer to a particular query?" We examine three strong generative models -- T5, BART, and GPT-2 -- and study whether their probabilities on QA tasks are well calibrated. We then examine methods to calibrate such models to make their confidence scores correlate better with the likelihood of correctness.
  arXiv  Detail & Related papers  (2020-12-02T03:53:13Z)
• The Right Tool for the Job: Matching Model and Instance Complexities [62.95183777679024]
  As NLP models become larger, executing a trained model requires significant computational resources incurring monetary and environmental costs. We propose a modification to contextual representation fine-tuning which, during inference, allows for an early (and fast) "exit" We test our proposed modification on five different datasets in two tasks: three text classification datasets and two natural language inference benchmarks.
  arXiv  Detail & Related papers  (2020-04-16T04:28:08Z)

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.