Zero-Shot Text Classification

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.

This paper studies whether a lightweight supervised aggregator can combine diverse zero-shot large language model outputs into a stronger downstream signal for corporate disclosure classification. Zero-shot LLMs can read disclosures without task-specific fine-tuning, but their predictions often vary across prompt perspectives, model families, and confidence levels. I examine this problem with a multi-prompt framework in which three fixed zero-shot LLM classifiers read each disclosure from different financial perspectives and output a sentiment label, a confidence score, and a short rationale. A logistic meta-classifier then aggregates these outputs to predict next-day stock return direction. To reduce pretrained-model contamination, I restrict evaluation to a post-release sample of 9{,}860 U.S.\ corporate disclosures issued by large publicly traded firms between January 2025 and March 2026, after the release of the frozen base LLMs used in the experiment. Results show that the trained aggregator outperforms single classifiers, majority vote, confidence-weighted voting, a zero-shot LLM judge, and a FinBERT baseline. Balanced accuracy rises from 0.566 for the best single classifier to 0.606 for the trained aggregator. The gain is largest in mixed-signal disclosures where classifiers disagree. The results suggest that zero-shot LLM outputs contain complementary financial signals, while also showing that the strongest gains come from supervised aggregation rather than from zero-shot voting alone.

Zero-shot text classification (ZSC) offers the promise of eliminating costly task-specific annotation by matching texts directly to human-readable label descriptions. While early approaches have predominantly relied on cross-encoder models fine-tuned for natural language inference (NLI), recent advances in text-embedding models, rerankers, and instruction-tuned large language models (LLMs) have challenged the dominance of NLI-based architectures. Yet, systematically comparing these diverse approaches remains difficult. Existing evaluations, such as MTEB, often incorporate labeled examples through supervised probes or fine-tuning, leaving genuine zero-shot capabilities underexplored. To address this, we introduce BTZSC, a comprehensive benchmark of 22 public datasets spanning sentiment, topic, intent, and emotion classification, capturing diverse domains, class cardinalities, and document lengths. Leveraging BTZSC, we conduct a systematic comparison across four major model families, NLI cross-encoders, embedding models, rerankers and instruction-tuned LLMs, encompassing 38 public and custom checkpoints. Our results show that: (i) modern rerankers, exemplified by Qwen3-Reranker-8B, set a new state-of-the-art with macro F1 = 0.72; (ii) strong embedding models such as GTE-large-en-v1.5 substantially close the accuracy gap while offering the best trade-off between accuracy and latency; (iii) instruction-tuned LLMs at 4--12B parameters achieve competitive performance (macro F1 up to 0.67), excelling particularly on topic classification but trailing specialized rerankers; (iv) NLI cross-encoders plateau even as backbone size increases; and (v) scaling primarily benefits rerankers and LLMs over embedding models. BTZSC and accompanying evaluation code are publicly released to support fair and reproducible progress in zero-shot text understanding.

This work presents a systematic and in-depth investigation of the utility of large language models as text classifiers for biomedical article classification. The study uses several small and mid-size open source models, as well as selected closed source ones, and is more comprehensive than most prior work with respect to the scope of evaluated configurations: different types of prompts, output processing methods for generating both class and class probability predictions, as well as few-shot example counts and selection methods. The performance of the most successful configurations is compared to that of conventional classification algorithms. The obtained average PR AUC over 15 challenging datasets above 0.4 for zero-shot prompting and nearly 0.5 for few-shot prompting comes close to that of the naïve Bayes classifier (0.5), the random forest algorithm (0.5 with default settings or 0.55 with hyperparameter tuning) and fine-tuned transformer models (0.5). These results confirm the utility of large language models as text classifiers for non-trivial domains and provide practical recommendations of the most promising setups, including in particular using output token probabilities for class probability prediction.

This paper describes the KCLarity team's participation in CLARITY, a shared task at SemEval 2026 on classifying ambiguity and evasion techniques in political discourse. We investigate two modelling formulations: (i) directly predicting the clarity label, and (ii) predicting the evasion label and deriving clarity through the task taxonomy hierarchy. We further explore several auxiliary training variants and evaluate decoder-only models in a zero-shot setting under the evasion-first formulation. Overall, the two formulations yield comparable performance. Among encoder-based models, RoBERTa-large achieves the strongest results on the public test set, while zero-shot GPT-5.2 generalises better on the hidden evaluation set.