GRAID: Synthetic Data Generation with Geometric Constraints and Multi-Agentic Reflection for Harmful Content Detection

We address the problem of data scarcity in harmful text classification for guardrailing applications and introduce GRAID (Geometric and Reflective AI-Driven Data Augmentation), a novel pipeline that leverages Large Language Models (LLMs) for dataset augmentation. GRAID consists of two stages: (i) generation of geometrically controlled examples using a constrained LLM, and (ii) augmentation through a multi-agentic reflective process that promotes stylistic diversity and uncovers edge cases. This combination enables both reliable coverage of the input space and nuanced exploration of harmful content. Using two benchmark data sets, we demonstrate that augmenting a harmful text classification dataset with GRAID leads to significant improvements in downstream guardrail model performance.

PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability

The proliferation of Large Language Models (LLMs) in real-world applications poses unprecedented risks of generating harmful, biased, or misleading information to vulnerable populations including LGBTQ+ individuals, single parents, and marginalized communities. While existing safety approaches rely on post-hoc filtering or generic alignment techniques, they fail to proactively prevent harmful outputs at the generation source. This paper introduces PromptGuard, a novel modular prompting framework with our breakthrough contribution: VulnGuard Prompt, a hybrid technique that prevents harmful information generation using real-world data-driven contrastive learning. VulnGuard integrates few-shot examples from curated GitHub repositories, ethical chain-of-thought reasoning, and adaptive role-prompting to create population-specific protective barriers. Our framework employs theoretical multi-objective optimization with formal proofs demonstrating 25-30% analytical harm reduction through entropy bounds and Pareto optimality. PromptGuard orchestrates six core modules: Input Classification, VulnGuard Prompting, Ethical Principles Integration, External Tool Interaction, Output Validation, and User-System Interaction, creating an intelligent expert system for real-time harm prevention. We provide comprehensive mathematical formalization including convergence proofs, vulnerability analysis using information theory, and theoretical validation framework using GitHub-sourced datasets, establishing mathematical foundations for systematic empirical research.

Scalable and consistent few-shot classification of survey responses using text embeddings

Qualitative analysis of open-ended survey responses is a commonly-used research method in the social sciences, but traditional coding approaches are often time-consuming and prone to inconsistency. Existing solutions from Natural Language Processing such as supervised classifiers, topic modeling techniques, and generative large language models have limited applicability in qualitative analysis, since they demand extensive labeled data, disrupt established qualitative workflows, and/or yield variable results. In this paper, we introduce a text embedding-based classification framework that requires only a handful of examples per category and fits well with standard qualitative workflows. When benchmarked against human analysis of a conceptual physics survey consisting of 2899 open-ended responses, our framework achieves a Cohen's Kappa ranging from 0.74 to 0.83 as compared to expert human coders in an exhaustive coding scheme. We further show how performance of this framework improves with fine-tuning of the text embedding model, and how the method can be used to audit previously-analyzed datasets. These findings demonstrate that text embedding-assisted coding can flexibly scale to thousands of responses without sacrificing interpretability, opening avenues for deductive qualitative analysis at scale.

Noisy Label Refinement with Semantically Reliable Synthetic Images

Semantic noise in image classification datasets, where visually similar categories are frequently mislabeled, poses a significant challenge to conventional supervised learning approaches. In this paper, we explore the potential of using synthetic images generated by advanced text-to-image models to address this issue. Although these high-quality synthetic images come with reliable labels, their direct application in training is limited by domain gaps and diversity constraints. Unlike conventional approaches, we propose a novel method that leverages synthetic images as reliable reference points to identify and correct mislabeled samples in noisy datasets. Extensive experiments across multiple benchmark datasets show that our approach significantly improves classification accuracy under various noise conditions, especially in challenging scenarios with semantic label noise. Additionally, since our method is orthogonal to existing noise-robust learning techniques, when combined with state-of-the-art noise-robust training methods, it achieves superior performance, improving accuracy by 30% on CIFAR-10 and by 11% on CIFAR-100 under 70% semantic noise, and by 24% on ImageNet-100 under real-world noise conditions.

Efficient Zero-Shot Long Document Classification by Reducing Context Through Sentence Ranking

Transformer-based models like BERT excel at short text classification but struggle with long document classification (LDC) due to input length limitations and computational inefficiencies. In this work, we propose an efficient, zero-shot approach to LDC that leverages sentence ranking to reduce input context without altering the model architecture. Our method enables the adaptation of models trained on short texts, such as headlines, to long-form documents by selecting the most informative sentences using a TF-IDF-based ranking strategy. Using the MahaNews dataset of long Marathi news articles, we evaluate three context reduction strategies that prioritize essential content while preserving classification accuracy. Our results show that retaining only the top 50\% ranked sentences maintains performance comparable to full-document inference while reducing inference time by up to 35\%. This demonstrates that sentence ranking is a simple yet effective technique for scalable and efficient zero-shot LDC.

Spoken in Jest, Detected in Earnest: A Systematic Review of Sarcasm Recognition -- Multimodal Fusion, Challenges, and Future Prospects

Sarcasm, a common feature of human communication, poses challenges in interpersonal interactions and human-machine interactions. Linguistic research has highlighted the importance of prosodic cues, such as variations in pitch, speaking rate, and intonation, in conveying sarcastic intent. Although previous work has focused on text-based sarcasm detection, the role of speech data in recognizing sarcasm has been underexplored. Recent advancements in speech technology emphasize the growing importance of leveraging speech data for automatic sarcasm recognition, which can enhance social interactions for individuals with neurodegenerative conditions and improve machine understanding of complex human language use, leading to more nuanced interactions. This systematic review is the first to focus on speech-based sarcasm recognition, charting the evolution from unimodal to multimodal approaches. It covers datasets, feature extraction, and classification methods, and aims to bridge gaps across diverse research domains. The findings include limitations in datasets for sarcasm recognition in speech, the evolution of feature extraction techniques from traditional acoustic features to deep learning-based representations, and the progression of classification methods from unimodal approaches to multimodal fusion techniques. In so doing, we identify the need for greater emphasis on cross-cultural and multilingual sarcasm recognition, as well as the importance of addressing sarcasm as a multimodal phenomenon, rather than a text-based challenge.

ReflectivePrompt: Reflective evolution in autoprompting algorithms

Autoprompting is the process of automatically selecting optimized prompts for language models, which has been gaining popularity with the rapid advancement of prompt engineering, driven by extensive research in the field of large language models (LLMs). This paper presents ReflectivePrompt - a novel autoprompting method based on evolutionary algorithms that employs a reflective evolution approach for more precise and comprehensive search of optimal prompts. ReflectivePrompt utilizes short-term and long-term reflection operations before crossover and elitist mutation to enhance the quality of the modifications they introduce. This method allows for the accumulation of knowledge obtained throughout the evolution process and updates it at each epoch based on the current population. ReflectivePrompt was tested on 33 datasets for classification and text generation tasks using open-access large language models: t-lite-instruct-0.1 and gemma3-27b-it. The method demonstrates, on average, a significant improvement (e.g., 28% on BBH compared to EvoPrompt) in metrics relative to current state-of-the-art approaches, thereby establishing itself as one of the most effective solutions in evolutionary algorithm-based autoprompting.

Comparing energy consumption and accuracy in text classification inference

The increasing deployment of large language models (LLMs) in natural language processing (NLP) tasks raises concerns about energy efficiency and sustainability. While prior research has largely focused on energy consumption during model training, the inference phase has received comparatively less attention. This study systematically evaluates the trade-offs between model accuracy and energy consumption in text classification inference across various model architectures and hardware configurations. Our empirical analysis shows that the best-performing model in terms of accuracy can also be energy-efficient, while larger LLMs tend to consume significantly more energy with lower classification accuracy. We observe substantial variability in inference energy consumption ($<$mWh to $>$kWh), influenced by model type, model size, and hardware specifications. Additionally, we find a strong correlation between inference energy consumption and model runtime, indicating that execution time can serve as a practical proxy for energy usage in settings where direct measurement is not feasible. These findings have implications for sustainable AI development, providing actionable insights for researchers, industry practitioners, and policymakers seeking to balance performance and resource efficiency in NLP applications.

Randomly Removing 50% of Dimensions in Text Embeddings has Minimal Impact on Retrieval and Classification Tasks

In this paper, we study the surprising impact that truncating text embeddings has on downstream performance. We consistently observe across 6 state-of-the-art text encoders and 26 downstream tasks, that randomly removing up to 50% of embedding dimensions results in only a minor drop in performance, less than 10%, in retrieval and classification tasks. Given the benefits of using smaller-sized embeddings, as well as the potential insights about text encoding, we study this phenomenon and find that, contrary to what is suggested in prior work, this is not the result of an ineffective use of representation space. Instead, we find that a large number of uniformly distributed dimensions actually cause an increase in performance when removed. This would explain why, on average, removing a large number of embedding dimensions results in a marginal drop in performance. We make similar observations when truncating the embeddings used by large language models to make next-token predictions on generative tasks, suggesting that this phenomenon is not isolated to classification or retrieval tasks.

Occlusion Robustness of CLIP for Military Vehicle Classification

Vision-language models (VLMs) like CLIP enable zero-shot classification by aligning images and text in a shared embedding space, offering advantages for defense applications with scarce labeled data. However, CLIP's robustness in challenging military environments, with partial occlusion and degraded signal-to-noise ratio (SNR), remains underexplored. We investigate CLIP variants' robustness to occlusion using a custom dataset of 18 military vehicle classes and evaluate using Normalized Area Under the Curve (NAUC) across occlusion percentages. Four key insights emerge: (1) Transformer-based CLIP models consistently outperform CNNs, (2) fine-grained, dispersed occlusions degrade performance more than larger contiguous occlusions, (3) despite improved accuracy, performance of linear-probed models sharply drops at around 35% occlusion, (4) by finetuning the model's backbone, this performance drop occurs at more than 60% occlusion. These results underscore the importance of occlusion-specific augmentations during training and the need for further exploration into patch-level sensitivity and architectural resilience for real-world deployment of CLIP.