LLM-based agentic applications have shown increasingly remarkable capabilities in complex workflows but incur substantial costs due to extensive planning and reasoning requirements. Existing LLM caching techniques (like context caching and semantic caching), primarily designed for serving chatbots, are insufficient for agentic applications where outputs depend on external data or environmental contexts. We propose agentic plan caching, a novel approach that extracts, stores, adapts, and reuses structured plan templates from planning stages of agentic applications across semantically similar tasks to reduce the cost of serving. Unlike traditional semantic caching, our system extracts plan templates from completed agent executions at test-time, employs keyword extraction to match new requests against cached plans, and utilizes lightweight models to adapt these templates to task-specific plans with contexts. Evaluation across multiple real-world agentic applications shows that our system can reduce costs by 46.62% on average while maintaining performance, offering a more efficient solution for serving LLM-based agents that complements existing LLM serving infrastructures.
We introduce $Urania$, a novel framework for generating insights about LLM chatbot interactions with rigorous differential privacy (DP) guarantees. The framework employs a private clustering mechanism and innovative keyword extraction methods, including frequency-based, TF-IDF-based, and LLM-guided approaches. By leveraging DP tools such as clustering, partition selection, and histogram-based summarization, $Urania$ provides end-to-end privacy protection. Our evaluation assesses lexical and semantic content preservation, pair similarity, and LLM-based metrics, benchmarking against a non-private Clio-inspired pipeline (Tamkin et al., 2024). Moreover, we develop a simple empirical privacy evaluation that demonstrates the enhanced robustness of our DP pipeline. The results show the framework's ability to extract meaningful conversational insights while maintaining stringent user privacy, effectively balancing data utility with privacy preservation.
Keyword extraction is a foundational task in natural language processing, underpinning countless real-world applications. A salient example is contextual advertising, where keywords help predict the topical congruence between ads and their surrounding media contexts to enhance advertising effectiveness. Recent advances in artificial intelligence, particularly large language models, have improved keyword extraction capabilities but also introduced concerns about computational cost. Moreover, although the end-user experience is of vital importance, human evaluation of keyword extraction performances remains under-explored. This study provides a comparative evaluation of three prevalent keyword extraction algorithms that vary in complexity: TF-IDF, KeyBERT, and Llama 2. To evaluate their effectiveness, a mixed-methods approach is employed, combining quantitative benchmarking with qualitative assessments from 552 participants through three survey-based experiments. Findings indicate a slight user preference for KeyBERT, which offers a favourable balance between performance and computational efficiency compared to the other two algorithms. Despite a strong overall preference for gold-standard keywords, differences between the algorithmic outputs are not statistically significant, highlighting a long-overlooked gap between traditional precision-focused metrics and user-perceived algorithm efficiency. The study highlights the importance of user-centred evaluation methodologies and proposes analytical tools to support their implementation.
Visual captioning benchmarks have become outdated with the emergence of modern multimodal large language models (MLLMs), as the brief ground-truth sentences and traditional metrics fail to assess detailed captions effectively. While recent benchmarks attempt to address this by focusing on keyword extraction or object-centric evaluation, they remain limited to vague-view or object-view analyses and incomplete visual element coverage. In this paper, we introduce CAPability, a comprehensive multi-view benchmark for evaluating visual captioning across 12 dimensions spanning six critical views. We curate nearly 11K human-annotated images and videos with visual element annotations to evaluate the generated captions. CAPability stably assesses both the correctness and thoroughness of captions using F1-score. By converting annotations to QA pairs, we further introduce a heuristic metric, \textit{know but cannot tell} ($K\bar{T}$), indicating a significant performance gap between QA and caption capabilities. Our work provides the first holistic analysis of MLLMs' captioning abilities, as we identify their strengths and weaknesses across various dimensions, guiding future research to enhance specific aspects of capabilities.
Brand reputation in the banking sector is maintained through insightful analysis of customer opinion on code-mixed and multilingual content. Conventional NLP models misclassify or ignore code-mixed text, when mix with low resource languages such as Sinhala-English and fail to capture domain-specific knowledge. This study introduces a hybrid NLP method to improve keyword extraction, content filtering, and aspect-based classification of banking content. Keyword extraction in English is performed with a hybrid approach comprising a fine-tuned SpaCy NER model, FinBERT-based KeyBERT embeddings, YAKE, and EmbedRank, which results in a combined accuracy of 91.2%. Code-mixed and Sinhala keywords are extracted using a fine-tuned XLM-RoBERTa model integrated with a domain-specific Sinhala financial vocabulary, and it results in an accuracy of 87.4%. To ensure data quality, irrelevant comment filtering was performed using several models, with the BERT-base-uncased model achieving 85.2% for English and XLM-RoBERTa 88.1% for Sinhala, which was better than GPT-4o, SVM, and keyword-based filtering. Aspect classification followed the same pattern, with the BERT-base-uncased model achieving 87.4% for English and XLM-RoBERTa 85.9% for Sinhala, both exceeding GPT-4 and keyword-based approaches. These findings confirm that fine-tuned transformer models outperform traditional methods in multilingual financial text analysis. The present framework offers an accurate and scalable solution for brand reputation monitoring in code-mixed and low-resource banking environments.
Revitalizing Japan's remote areas has become a crucial task, and Matsue City exemplifies this effort in its temporary event spaces, created through collective efforts to foster urban vibrancy and bring together residents and visitors. This research examines the relationship between data-driven in-sights using generative AI and visual attractiveness by evaluating tempo-rary events in Matsue City, particularly considering the cognitive-cultural differences in processing visual information of the participants. The first phase employs semantic keyword extraction from interviews, categorizing responses into physical elements, activities, and atmosphere. The second phase analyzes spatial perception through three categories: layout hierar-chy, product visibility, and visual attention. The correlation indicates that successful event design requires a balance between spatial efficiency and diverse needs, with a spatial organization that optimizes visitor flow and visibility strategies considering cultural and demographic diversity. These findings contribute to understanding the urban quality of temporary event spaces and offer a replicable framework for enhancing the visual appeal of events in remote areas throughout Japan.
This work-in-progress paper presents a novel approach to detecting sponsored advertisement segments in YouTube videos and comparing the advertisement with the main content. Our methodology involves the collection of 421 auto-generated and manual transcripts which are then fed into a prompt-engineered GPT-4o for ad detection, a KeyBERT for keyword extraction, and another iteration of ChatGPT for category identification. The results revealed a significant prevalence of product-related ads across various educational topics, with ad categories refined using GPT-4o into succinct 9 content and 4 advertisement categories. This approach provides a scalable and efficient alternative to traditional ad detection methods while offering new insights into the types and relevance of ads embedded within educational content. This study highlights the potential of LLMs in transforming ad detection processes and improving our understanding of advertisement strategies in digital media.
Conversational Product Search ( CPS ) systems interact with users via natural language to offer personalized and context-aware product lists. However, most existing research on CPS is limited to simulated conversations, due to the lack of a real CPS dataset driven by human-like language. Moreover, existing conversational datasets for e-commerce are constructed for a particular market or a particular language and thus can not support cross-market and multi-lingual usage. In this paper, we propose a CPS data collection protocol and create a new CPS dataset, called PSCon, which assists product search through conversations with human-like language. The dataset is collected by a coached human-human data collection protocol and is available for dual markets and two languages. By formulating the task of CPS, the dataset allows for comprehensive and in-depth research on six subtasks: user intent detection, keyword extraction, system action prediction, question selection, item ranking, and response generation. Moreover, we present a concise analysis of the dataset and propose a benchmark model on the proposed CPS dataset. Our proposed dataset and model will be helpful for facilitating future research on CPS.
Keyword extraction involves identifying the most descriptive words in a document, allowing automatic categorisation and summarisation of large quantities of diverse textual data. Relying on the insight that real-world keyword detection often requires handling of diverse content, we propose a novel supervised keyword extraction approach based on the mixture of experts (MoE) technique. MoE uses a learnable routing sub-network to direct information to specialised experts, allowing them to specialize in distinct regions of the input space. SEKE, a mixture of Specialised Experts for supervised Keyword Extraction, uses DeBERTa as the backbone model and builds on the MoE framework, where experts attend to each token, by integrating it with a recurrent neural network (RNN), to allow successful extraction even on smaller corpora, where specialisation is harder due to lack of training data. The MoE framework also provides an insight into inner workings of individual experts, enhancing the explainability of the approach. We benchmark SEKE on multiple English datasets, achieving state-of-the-art performance compared to strong supervised and unsupervised baselines. Our analysis reveals that depending on data size and type, experts specialize in distinct syntactic and semantic components, such as punctuation, stopwords, parts-of-speech, or named entities. Code is available at: https://github.com/matejMartinc/SEKE_keyword_extraction
In the burgeoning field of AI-driven image generation, the quest for precision and relevance in response to textual prompts remains paramount. This paper introduces GPTDrawer, an innovative pipeline that leverages the generative prowess of GPT-based models to enhance the visual synthesis process. Our methodology employs a novel algorithm that iteratively refines input prompts using keyword extraction, semantic analysis, and image-text congruence evaluation. By integrating ChatGPT for natural language processing and Stable Diffusion for image generation, GPTDrawer produces a batch of images that undergo successive refinement cycles, guided by cosine similarity metrics until a threshold of semantic alignment is attained. The results demonstrate a marked improvement in the fidelity of images generated in accordance with user-defined prompts, showcasing the system's ability to interpret and visualize complex semantic constructs. The implications of this work extend to various applications, from creative arts to design automation, setting a new benchmark for AI-assisted creative processes.
Video question-answering (QA) is a core task in video understanding. Evaluating the quality of video QA and video caption data quality for training video large language models (VideoLLMs) is an essential challenge. Although various methods have been proposed for assessing video caption quality, there remains a lack of dedicated evaluation methods for Video QA. To address this gap, we introduce EVQAScore, a reference-free method that leverages keyword extraction to assess both video caption and video QA data quality. Additionally, we incorporate frame sampling and rescaling techniques to enhance the efficiency and robustness of our evaluation, this enables our score to evaluate the quality of extremely long videos. Our approach achieves state-of-the-art (SOTA) performance (32.8 for Kendall correlation and 42.3 for Spearman correlation, 4.7 and 5.9 higher than the previous method PAC-S++) on the VATEX-EVAL benchmark for video caption evaluation. Furthermore, by using EVQAScore for data selection, we achieved SOTA results with only 12.5\% of the original data volume, outperforming the previous SOTA method PAC-S and 100\% of data.
Recent studies have demonstrated that large language models (LLMs) exhibit significant biases in evaluation tasks, particularly in preferentially rating and favoring self-generated content. However, the extent to which this bias manifests in fact-oriented tasks, especially within retrieval-augmented generation (RAG) frameworks-where keyword extraction and factual accuracy take precedence over stylistic elements-remains unclear. Our study addresses this knowledge gap by simulating two critical phases of the RAG framework. In the first phase, we access the suitability of human-authored versus model-generated passages, emulating the pointwise reranking process. The second phase involves conducting pairwise reading comprehension tests to simulate the generation process. Contrary to previous findings indicating a self-preference in rating tasks, our results reveal no significant self-preference effect in RAG frameworks. Instead, we observe that factual accuracy significantly influences LLMs' output, even in the absence of prior knowledge. Our research contributes to the ongoing discourse on LLM biases and their implications for RAG-based system, offering insights that may inform the development of more robust and unbiased LLM systems.
Rigour is crucial for scientific research as it ensures the reproducibility and validity of results and findings. Despite its importance, little work exists on modelling rigour computationally, and there is a lack of analysis on whether these criteria can effectively signal or measure the rigour of scientific papers in practice. In this paper, we introduce a bottom-up, data-driven framework to automatically identify and define rigour criteria and assess their relevance in scientific writing. Our framework includes rigour keyword extraction, detailed rigour definition generation, and salient criteria identification. Furthermore, our framework is domain-agnostic and can be tailored to the evaluation of scientific rigour for different areas, accommodating the distinct salient criteria across fields. We conducted comprehensive experiments based on datasets collected from two high impact venues for Machine Learning and NLP (i.e., ICLR and ACL) to demonstrate the effectiveness of our framework in modelling rigour. In addition, we analyse linguistic patterns of rigour, revealing that framing certainty is crucial for enhancing the perception of scientific rigour, while suggestion certainty and probability uncertainty diminish it.
Domain dependence and annotation subjectivity pose challenges for supervised keyword extraction. Based on the premises that second-order keyness patterns are existent at the community level and learnable from annotated keyword extraction datasets, this paper proposes a supervised ranking approach to keyword extraction that ranks keywords with keyness patterns consisting of independent features (such as sublanguage domain and term length) and three categories of dependent features -- heuristic features, specificity features, and representavity features. The approach uses two convolutional-neural-network based models to learn keyness patterns from keyword datasets and overcomes annotation subjectivity by training the two models with bootstrap sampling strategy. Experiments demonstrate that the approach not only achieves state-of-the-art performance on ten keyword datasets in general supervised keyword extraction with an average top-10-F-measure of 0.316 , but also robust cross-domain performance with an average top-10-F-measure of 0.346 on four datasets that are excluded in the training process. Such cross-domain robustness is attributed to the fact that community-level keyness patterns are limited in number and temperately independent of language domains, the distinction between independent features and dependent features, and the sampling training strategy that balances excess risk and lack of negative training data.
This study examines integrating EHRs and NLP with large language models (LLMs) to improve healthcare data management and patient care. It focuses on using advanced models to create secure, HIPAA-compliant synthetic patient notes for biomedical research. The study used de-identified and re-identified MIMIC III datasets with GPT-3.5, GPT-4, and Mistral 7B to generate synthetic notes. Text generation employed templates and keyword extraction for contextually relevant notes, with one-shot generation for comparison. Privacy assessment checked PHI occurrence, while text utility was tested using an ICD-9 coding task. Text quality was evaluated with ROUGE and cosine similarity metrics to measure semantic similarity with source notes. Analysis of PHI occurrence and text utility via the ICD-9 coding task showed that the keyword-based method had low risk and good performance. One-shot generation showed the highest PHI exposure and PHI co-occurrence, especially in geographic location and date categories. The Normalized One-shot method achieved the highest classification accuracy. Privacy analysis revealed a critical balance between data utility and privacy protection, influencing future data use and sharing. Re-identified data consistently outperformed de-identified data. This study demonstrates the effectiveness of keyword-based methods in generating privacy-protecting synthetic clinical notes that retain data usability, potentially transforming clinical data-sharing practices. The superior performance of re-identified over de-identified data suggests a shift towards methods that enhance utility and privacy by using dummy PHIs to perplex privacy attacks.
The task of $\textit{keyword extraction}$ is often an important initial step in unsupervised information extraction, forming the basis for tasks such as topic modeling or document classification. While recent methods have proven to be quite effective in the extraction of keywords, the identification of $\textit{class-specific}$ keywords, or only those pertaining to a predefined class, remains challenging. In this work, we propose an improved method for class-specific keyword extraction, which builds upon the popular $\textbf{KeyBERT}$ library to identify only keywords related to a class described by $\textit{seed keywords}$. We test this method using a dataset of German business registry entries, where the goal is to classify each business according to an economic sector. Our results reveal that our method greatly improves upon previous approaches, setting a new standard for $\textit{class-specific}$ keyword extraction.
Domain probe lists--used to determine which URLs to probe for Web censorship--play a critical role in Internet censorship measurement studies. Indeed, the size and accuracy of the domain probe list limits the set of censored pages that can be detected; inaccurate lists can lead to an incomplete view of the censorship landscape or biased results. Previous efforts to generate domain probe lists have been mostly manual or crowdsourced. This approach is time-consuming, prone to errors, and does not scale well to the ever-changing censorship landscape. In this paper, we explore methods for automatically generating probe lists that are both comprehensive and up-to-date for Web censorship measurement. We start from an initial set of 139,957 unique URLs from various existing test lists consisting of pages from a variety of languages to generate new candidate pages. By analyzing content from these URLs (i.e., performing topic and keyword extraction), expanding these topics, and using them as a feed to search engines, our method produces 119,255 new URLs across 35,147 domains. We then test the new candidate pages by attempting to access each URL from servers in eleven different global locations over a span of four months to check for their connectivity and potential signs of censorship. Our measurements reveal that our method discovered over 1,400 domains--not present in the original dataset--we suspect to be blocked. In short, automatically updating probe lists is possible, and can help further automate censorship measurements at scale.
The search for prior art is crucial in patent application processing, it consists in retrieving other documents relevant to the invention of the application. Most methods feed a search engine with keywords that are extracted by frequency-analysis methods. We suggest and demonstrate a new method that relies on the way information is provided in patent claims.
The rapid development of the Internet has profoundly changed human life. Humans are increasingly expressing themselves and interacting with others on social media platforms. However, although artificial intelligence technology has been widely used in many aspects of life, its application in social media content creation is still blank. To solve this problem, we propose a new prompt word generation framework based on multi-modal information fusion, which combines multiple tasks including topic classification, sentiment analysis, scene recognition and keyword extraction to generate more comprehensive prompt words. Subsequently, we use a template containing a set of prompt words to guide ChatGPT to generate high-quality tweets. Furthermore, in the absence of effective and objective evaluation criteria in the field of content generation, we use the ChatGPT tool to evaluate the results generated by the algorithm, making large-scale evaluation of content generation algorithms possible. Evaluation results on extensive content generation demonstrate that our cue word generation framework generates higher quality content compared to manual methods and other cueing techniques, while topic classification, sentiment analysis, and scene recognition significantly enhance content clarity and its consistency with the image.
The pervasive deployment of Large Language Models-LLMs in various sectors often neglects the nuanced requirements of individuals and small organizations, who benefit more from models precisely tailored to their specific business contexts rather than those with broadly superior general capabilities. This work introduces \textbf{AnyTaskTune}, a novel fine-tuning methodology coined as \textbf{Task-Fine-Tune}, specifically developed to elevate model performance on a diverse array of domain-specific tasks. This method involves a meticulous process to identify and define targeted sub-tasks within a domain, followed by the creation of specialized enhancement datasets for fine-tuning, thereby optimizing task-specific model performance. We conducted comprehensive fine-tuning experiments not only in the legal domain for tasks such as keyword extraction and sentence prediction but across over twenty different sub-tasks derived from the domains of finance, healthcare, law, psychology, consumer services, and human resources. To substantiate our approach and facilitate community engagement, we will open-source these bilingual task datasets. Our findings demonstrate that models fine-tuned using the \textbf{Task-Fine-Tune} methodology not only achieve superior performance on these specific tasks but also significantly outperform models with higher general capabilities in their respective domains. Our work is publicly available at \url{https://github.com/PandaVT/DataTager}.