Evaluation of Embedding-Based and Generative Methods for LLM-Driven Document Classification: Opportunities and Challenges

• URL: http://arxiv.org/abs/2604.04997v1
• Date: Sun, 05 Apr 2026 20:56:19 GMT
• Title: Evaluation of Embedding-Based and Generative Methods for LLM-Driven Document Classification: Opportunities and Challenges
• Abstract summary: generative Vision-Language Models (VLMs) like Qwen2.5-VL, enhanced with Chain-of-Thought (CoT) prompting, achieve superior zero-shot accuracy.<n>Supervised fine-tuning (SFT) can improve VLM performance, but it is sensitive to training data imbalance.
• Score: 4.146941837017164
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This work presents a comparative analysis of embedding-based and generative models for classifying geoscience technical documents. Using a multi-disciplinary benchmark dataset, we evaluated the trade-offs between model accuracy, stability, and computational cost. We find that generative Vision-Language Models (VLMs) like Qwen2.5-VL, enhanced with Chain-of-Thought (CoT) prompting, achieve superior zero-shot accuracy (82%) compared to state-of-the-art multimodal embedding models like QQMM (63%). We also demonstrate that while supervised fine-tuning (SFT) can improve VLM performance, it is sensitive to training data imbalance.

Related papers

• On Predicting the Post-training Potential of Pre-trained LLMs [60.07459271263409]
  We introduce a new task of predicting post-training potential - forecasting a base model's performance before post-training.<n>We propose RuDE, a unified framework that bypasses the generation gap of base models by leveraging response discrimination.<n>Experiments demonstrate a correlation greater than 90% with post-training performance.
  arXiv  Detail & Related papers  (2026-05-12T11:33:49Z)
• Portfolio Optimization Proxies under Label Scarcity and Regime Shifts via Bayesian and Deterministic Students under Semi-Supervised Sandwich Training [0.0]
  This paper proposes a machine learning assisted portfolio optimization framework designed for low data environments and regime uncertainty.<n>We construct a teacher student learning pipeline in which a Conditional Value at Risk (CVaR) generates supervisory labels, and neural models are trained using both real and synthetically augmented data.<n>Student models can match or outperform the CVaR teacher in several settings, while achieving improved robustness under regime shifts and reduced turnover.
  arXiv  Detail & Related papers  (2026-04-04T06:42:38Z)
• D-Models and E-Models: Diversity-Stability Trade-offs in the Sampling Behavior of Large Language Models [91.21455683212224]
  In large language models (LLMs), the probability of relevance for the next piece of information is linked to the probability of relevance for the next product.<n>But whether fine-grained sampling probabilities faithfully align with task requirements remains an open question.<n>We identify two model types: D-models, whose P_token exhibits large step-to-step variability and poor alignment with P_task; and E-models, whose P_token is more stable and better aligned with P_task.
  arXiv  Detail & Related papers  (2026-01-25T14:59:09Z)
• Model Utility Law: Evaluating LLMs beyond Performance through Mechanism Interpretable Metric [99.56567010306807]
  Large Language Models (LLMs) have become indispensable across academia, industry, and daily applications.<n>One core challenge of evaluation in the large language model (LLM) era is the generalization issue.<n>We propose Model Utilization Index (MUI), a mechanism interpretability enhanced metric that complements traditional performance scores.
  arXiv  Detail & Related papers  (2025-04-10T04:09:47Z)
• Linear Discriminant Analysis in Credit Scoring: A Transparent Hybrid Model Approach [9.88281854509076]
  We implement Linear Discriminant Analysis (LDA) as a feature reduction technique, which reduces the burden of the models complexity.<n>Our hybrid model, XG-DNN, outperformed other models with the highest accuracy of 99.45% and a 99% F1 score with LDA.<n>To interpret model decisions, we have applied 2 different explainable AI techniques named LIME (local) and Morris Sensitivity Analysis (global)
  arXiv  Detail & Related papers  (2024-12-05T14:21:18Z)
• LLaVA-Critic: Learning to Evaluate Multimodal Models [110.06665155812162]
  We introduce LLaVA-Critic, the first open-source large multimodal model (LMM) designed as a generalist evaluator.<n>LLaVA-Critic is trained using a high-quality critic instruction-following dataset that incorporates diverse evaluation criteria and scenarios.
  arXiv  Detail & Related papers  (2024-10-03T17:36:33Z)
• Improving Retrieval Augmented Language Model with Self-Reasoning [20.715106330314605]
  We propose a novel self-reasoning framework aimed at improving the reliability and traceability of RALMs.<n>The framework involves constructing self-reason trajectories with three processes: a relevance-aware process, an evidence-aware selective process, and a trajectory analysis process.<n>We have evaluated our framework across four public datasets to demonstrate the superiority of our method.
  arXiv  Detail & Related papers  (2024-07-29T09:05:10Z)
• Predictive Analytics of Varieties of Potatoes [2.336821989135698]
  We explore the application of machine learning algorithms specifically to enhance the selection process of Russet potato clones in breeding trials. This study addresses the challenge of efficiently identifying high-yield, disease-resistant, and climate-resilient potato varieties.
  arXiv  Detail & Related papers  (2024-04-04T00:49:05Z)
• AI enhanced data assimilation and uncertainty quantification applied to Geological Carbon Storage [0.0]
  We introduce the Surrogate-based hybrid ESMDA (SH-ESMDA), an adaptation of the traditional Ensemble Smoother with Multiple Data Assimilation (ESMDA) We also introduce Surrogate-based Hybrid RML (SH-RML), a variational data assimilation approach that relies on the randomized maximum likelihood (RML) Our comparative analyses show that SH-RML offers better uncertainty compared to conventional ESMDA for the case study.
  arXiv  Detail & Related papers  (2024-02-09T00:24:46Z)
• QualEval: Qualitative Evaluation for Model Improvement [82.73561470966658]
  We propose QualEval, which augments quantitative scalar metrics with automated qualitative evaluation as a vehicle for model improvement. QualEval uses a powerful LLM reasoner and our novel flexible linear programming solver to generate human-readable insights. We demonstrate that leveraging its insights, for example, improves the absolute performance of the Llama 2 model by up to 15% points relative.
  arXiv  Detail & Related papers  (2023-11-06T00:21:44Z)
• From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning [52.257422715393574]
  We introduce a self-guided methodology for Large Language Models (LLMs) to autonomously discern and select cherry samples from open-source datasets. Our key innovation, the Instruction-Following Difficulty (IFD) metric, emerges as a pivotal metric to identify discrepancies between a model's expected responses and its intrinsic generation capability.
  arXiv  Detail & Related papers  (2023-08-23T09:45:29Z)
• Scaling Relationship on Learning Mathematical Reasoning with Large Language Models [75.29595679428105]
  We investigate how the pre-training loss, supervised data amount, and augmented data amount influence the reasoning performances of a supervised LLM. We find that rejection samples from multiple models push LLaMA-7B to an accuracy of 49.3% on GSM8K which outperforms the supervised fine-tuning (SFT) accuracy of 35.9% significantly.
  arXiv  Detail & Related papers  (2023-08-03T15:34:01Z)

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.