The expansion of the Internet and social networks has led to an explosion of user-generated content. Author intent understanding plays a crucial role in interpreting social media content. This paper addresses author intent classification in Bangla social media posts by leveraging both textual and visual data. Recognizing limitations in previous unimodal approaches, we systematically benchmark transformer-based language models (mBERT, DistilBERT, XLM-RoBERTa) and vision architectures (ViT, Swin, SwiftFormer, ResNet, DenseNet, MobileNet), utilizing the Uddessho dataset of 3,048 posts spanning six practical intent categories. We introduce a novel intermediate fusion strategy that significantly outperforms early and late fusion on this task. Experimental results show that intermediate fusion, particularly with mBERT and Swin Transformer, achieves 84.11% macro-F1 score, establishing a new state-of-the-art with an 8.4 percentage-point improvement over prior Bangla multimodal approaches. Our analysis demonstrates that integrating visual context substantially enhances intent classification. Cross-modal feature integration at intermediate levels provides optimal balance between modality-specific representation and cross-modal learning. This research establishes new benchmarks and methodological standards for Bangla and other low-resource languages. We call our proposed framework BangACMM (Bangla Author Content MultiModal).

Accurate intent classification is critical for efficient routing in customer service, ensuring customers are connected with the most suitable agents while reducing handling times and operational costs. However, as companies expand their product lines, intent classification faces scalability challenges due to the increasing number of intents and variations in taxonomy across different verticals. In this paper, we introduce REIC, a Retrieval-augmented generation Enhanced Intent Classification approach, which addresses these challenges effectively. REIC leverages retrieval-augmented generation (RAG) to dynamically incorporate relevant knowledge, enabling precise classification without the need for frequent retraining. Through extensive experiments on real-world datasets, we demonstrate that REIC outperforms traditional fine-tuning, zero-shot, and few-shot methods in large-scale customer service settings. Our results highlight its effectiveness in both in-domain and out-of-domain scenarios, demonstrating its potential for real-world deployment in adaptive and large-scale intent classification systems.

Abstract--Detecting out-of-scope (OOS) user utterances remains a key challenge in task-oriented dialogue systems and, more broadly, in open-set intent recognition. Existing approaches often depend on strong distributional assumptions or auxiliary calibration modules. We present DROID (Dual Representation for Out-of-Scope Intent Detection), a compact end-to-end framework that combines two complementary encoders--the Universal Sentence Encoder (USE) for broad semantic generalization and a domain-adapted Transformer-based Denoising Autoencoder (TSDAE) for domain-specific contextual distinctions. Their fused representations are processed by a lightweight branched classifier with a single calibrated threshold that separates in-domain and OOS intents without post-hoc scoring. T o enhance boundary learning under limited supervision, DROID incorporates both synthetic and open-domain outlier augmentation. Despite using only 1.5M trainable parameters, DROID consistently outperforms recent state-of-the-art baselines across multiple intent benchmarks, achieving macro-F1 improvements of 6-15% for known and 8-20% for OOS intents, with the largest gains in low-resource settings. These results demonstrate that dual-encoder representations with simple calibration can yield robust, scalable, and reliable OOS detection for neural dialogue systems. ONVERSA TIONAL AI systems are a primary interface for user assistance across sectors such as customer service, healthcare, and finance. A core requirement is intent classification--mapping utterances to predefined intents so downstream components can act appropriately [1].

We present MAFA (Multi-Agent Framework for Annotation), a production-deployed system that transforms enterprise-scale annotation workflows through configurable multi-agent collaboration. Addressing the critical challenge of annotation backlogs in financial services, where millions of customer utterances require accurate categorization, MAFA combines specialized agents with structured reasoning and a judge-based consensus mechanism. Our framework uniquely supports dynamic task adaptation, allowing organizations to define custom annotation types (FAQs, intents, entities, or domain-specific categories) through configuration rather than code changes. Deployed at JP Morgan Chase, MAFA has eliminated a 1 million utterance backlog while achieving, on average, 86% agreement with human annotators, annually saving over 5,000 hours of manual annotation work. The system processes utterances with annotation confidence classifications, which are typically 85% high, 10% medium, and 5% low across all datasets we tested. This enables human annotators to focus exclusively on ambiguous and low-coverage cases. We demonstrate MAFA's effectiveness across multiple datasets and languages, showing consistent improvements over traditional and single-agent annotation baselines: 13.8% higher Top-1 accuracy, 15.1% improvement in Top-5 accuracy, and 16.9% better F1 in our internal intent classification dataset and similar gains on public benchmarks.

Research on cross-dialectal transfer from a standard to a non-standard dialect variety has typically focused on text data. However, dialects are primarily spoken, and non-standard spellings are known to cause issues in text processing. We compare standard-to-dialect transfer in three settings: text models, speech models, and cascaded systems where speech first gets automatically transcribed and then further processed by a text model. In our experiments, we focus on German and multiple German dialects in the context of written and spoken intent and topic classification. To that end, we release the first dialectal audio intent classification dataset. We find that the speech-only setup provides the best results on the dialect data while the text-only setup works best on the standard data. While the cascaded systems lag behind the text-only models for German, they perform relatively well on the dialectal data if the transcription system generates normalized, standard-like output.

The proliferation of artificial intelligence (AI) systems, from virtual assistants [Kepuska and Bohouta, 2018] to recommendation engines [Gomez-Uribe and Hunt, 2015] and autonomous vehicles [Shladover, 2018], has reshaped human-machine interaction. Y et, African languages, with over 2,000 spoken across the continent [Eberhard et al., 2023], remain severely underrepresented in NLP due to their low-resource status [Ahia and Boakye, 2023, Nekoto et al., 2020]. This exclusion risks exacerbating the digital divide, limiting access to AI-driven services in critical domains like education, healthcare, and governance [Ndichu et al., 2024, Joshi et al., 2020]. Shona, a Bantu language spoken by millions in Zimbabwe and southern Zambia, exemplifies this challenge. Existing Shona corpora primarily consist of formal texts, such as news articles or religious documents [Eberhard et al., 2023], while everyday communication, particularly among younger speakers, is dominated by slang, code-mixing with English, and informal expressions [Eisenstein, 2013]. Standard NLP models, trained on formal data, struggle to process these dynamic linguistic patterns, hindering the development of culturally relevant conversational AI.

In this paper, we provide an extensive analysis of multi-label intent classification using Large Language Models (LLMs) that are open-source, publicly available, and can be run in consumer hardware. We use the MultiWOZ 2.1 dataset, a benchmark in the dialogue system domain, to investigate the efficacy of three popular open-source pre-trained LLMs, namely LLama2-7B-hf, Mistral-7B-v0.1, and Yi-6B. We perform the classification task in a few-shot setup, giving 20 examples in the prompt with some instructions. Our approach focuses on the differences in performance of these models across several performance metrics by methodically assessing these models on multi-label intent classification tasks. Additionally, we compare the performance of the instruction-based fine-tuning approach with supervised learning using the smaller transformer model BertForSequenceClassification as a baseline. To evaluate the performance of the models, we use evaluation metrics like accuracy, precision, and recall as well as micro, macro, and weighted F1 score. We also report the inference time, VRAM requirements, etc. The Mistral-7B-v0.1 outperforms two other generative models on 11 intent classes out of 14 in terms of F-Score, with a weighted average of 0.50. It also has relatively lower Humming Loss and higher Jaccard Similarity, making it the winning model in the few-shot setting. We find BERT based supervised classifier having superior performance compared to the best performing few-shot generative LLM. The study provides a framework for small open-source LLMs in detecting complex multi-intent dialogues, enhancing the Natural Language Understanding aspect of task-oriented chatbots.

Failure Analysis (FA) is a highly intricate and knowledge-intensive process. The integration of AI components within the computational infrastructure of FA labs has the potential to automate a variety of tasks, including the detection of non-conformities in images, the retrieval of analogous cases from diverse data sources, and the generation of reports from annotated images. However, as the number of deployed AI models increases, the challenge lies in orchestrating these components into cohesive and efficient workflows that seamlessly integrate with the FA process. This paper investigates the design and implementation of an agentic AI system for semiconductor FA using a Large Language Model (LLM)-based Planning Agent (LPA). The LPA integrates LLMs with advanced planning capabilities and external tool utilization, allowing autonomous processing of complex queries, retrieval of relevant data from external systems, and generation of human-readable responses. The evaluation results demonstrate the agent's operational effectiveness and reliability in supporting FA tasks.

Spoken Language Understanding (SLU) systems must balance performance and efficiency, particularly in resource-constrained environments. Existing methods apply distillation and quantization separately, leading to suboptimal compression as distillation ignores quantization constraints. We propose QUADS, a unified framework that optimizes both through multi-stage training with a pre-tuned model, enhancing adaptability to low-bit regimes while maintaining accuracy. QUADS achieves 71.13\% accuracy on SLURP and 99.20\% on FSC, with only minor degradations of up to 5.56\% compared to state-of-the-art models. Additionally, it reduces computational complexity by 60--73$\times$ (GMACs) and model size by 83--700$\times$, demonstrating strong robustness under extreme quantization. These results establish QUADS as a highly efficient solution for real-world, resource-constrained SLU applications.

In recent years, large language models (LLMs) have achieved remarkable advancements in multimodal processing, including end-to-end speech-based language models that enable natural interactions and perform specific tasks in task-oriented dialogue (TOD) systems. However, existing TOD datasets are predominantly text-based, lacking real speech signals that are essential for evaluating the robustness of speech-based LLMs. Moreover, existing speech TOD datasets are primarily English and lack critical aspects such as speech disfluencies and speaker variations. To address these gaps, we introduce RealTalk-CN, the first Chinese multi-turn, multi-domain speech-text dual-modal TOD dataset, comprising 5.4k dialogues (60K utterances, 150 hours) with paired speech-text annotations. RealTalk-CN captures diverse dialogue scenarios with annotated spontaneous speech disfluencies, ensuring comprehensive coverage of real-world complexities in speech dialogue. In addition, we propose a novel cross-modal chat task that authentically simulates real-world user interactions, allowing dynamic switching between speech and text modalities. Our evaluation covers robustness to speech disfluencies, sensitivity to speaker characteristics, and cross-domain performance. Extensive experiments validate the effectiveness of RealTalk-CN, establishing a strong foundation for Chinese speech-based LLMs research.