arXiv subjects

Language models

Find arXiv papers on language models and computational linguistics, including cs.CL metadata. Use abstracts to explore model training, evaluation and natural-language processing.

Follow this topic with RSS

At least 595 records · Page 33Linked to original sources

arXiv2025

Strategies for political-statement segmentation and labelling in unstructured text

Analysis of parliamentary speeches and political-party manifestos has become an integral area of computational study of political texts. While speeches have been overwhelmingly analysed using unsupervised methods, a large corpus of manifestos with by-statement political-stance labels has been created by the participants of the MARPOR project. It has been recently shown that these labels can be predicted by a neural model; however, the current approach relies on provided statement boundaries, limiting out-of-domain applicability. In this work, we propose and test a range of unified split-and-label frameworks -- based on linear-chain CRFs, fine-tuned text-to-text models, and the combination of in-context learning with constrained decoding -- that can be used to jointly segment and classify statements from raw textual data. We show that our approaches achieve competitive accuracy when applied to raw text of political manifestos, and then demonstrate the research potential of our method by applying it to the records of the UK House of Commons and tracing the political trajectories of four major parties in the last three decades.

cs.CL↗

arXiv2025

Multi-Modal 3D Mesh Reconstruction from Images and Text

6D object pose estimation for unseen objects is essential in robotics but traditionally relies on trained models that require large datasets, high computational costs, and struggle to generalize. Zero-shot approaches eliminate the need for training but depend on pre-existing 3D object models, which are often impractical to obtain. To address this, we propose a language-guided few-shot 3D reconstruction method, reconstructing a 3D mesh from few input images. In the proposed pipeline, receives a set of input images and a language query. A combination of GroundingDINO and Segment Anything Model outputs segmented masks from which a sparse point cloud is reconstructed with VGGSfM. Subsequently, the mesh is reconstructed with the Gaussian Splatting method SuGAR. In a final cleaning step, artifacts are removed, resulting in the final 3D mesh of the queried object. We evaluate the method in terms of accuracy and quality of the geometry and texture. Furthermore, we study the impact of imaging conditions such as viewing angle, number of input images, and image overlap on 3D object reconstruction quality, efficiency, and computational scalability.

cs.CV↗

arXiv2025

Cross-Lingual IPA Contrastive Learning for Zero-Shot NER

Existing approaches to zero-shot Named Entity Recognition (NER) for low-resource languages have primarily relied on machine translation, whereas more recent methods have shifted focus to phonemic representation. Building upon this, we investigate how reducing the phonemic representation gap in IPA transcription between languages with similar phonetic characteristics enables models trained on high-resource languages to perform effectively on low-resource languages. In this work, we propose CONtrastive Learning with IPA (CONLIPA) dataset containing 10 English and high resource languages IPA pairs from 10 frequently used language families. We also propose a cross-lingual IPA Contrastive learning method (IPAC) using the CONLIPA dataset. Furthermore, our proposed dataset and methodology demonstrate a substantial average gain when compared to the best performing baseline.

cs.CL↗

arXiv2025

Multi-Agent System for AI-Assisted Extraction of Narrative Arcs in TV Series

Serialized TV shows are built on complex storylines that can be hard to track and evolve in ways that defy straightforward analysis. This paper introduces a multi-agent system designed to extract and analyze these narrative arcs. Tested on the first season of Grey's Anatomy (ABC 2005-), the system identifies three types of arcs: Anthology (self-contained), Soap (relationship-focused), and Genre-Specific (strictly related to the series' genre). Episodic progressions of these arcs are stored in both relational and semantic (vectorial) databases, enabling structured analysis and comparison. To bridge the gap between automation and critical interpretation, the system is paired with a graphical interface that allows for human refinement using tools to enhance and visualize the data. The system performed strongly in identifying Anthology Arcs and character entities, but its reliance on textual paratexts (such as episode summaries) revealed limitations in recognizing overlapping arcs and subtler dynamics. This approach highlights the potential of combining computational and human expertise in narrative analysis. Beyond television, it offers promise for serialized written formats, where the narrative resides entirely in the text. Future work will explore the integration of multimodal inputs, such as dialogue and visuals, and expand testing across a wider range of genres to refine the system further.

cs.CL↗

arXiv2025

Self-Supervised Learning for Neural Topic Models with Variance-Invariance-Covariance Regularization

In our study, we propose a self-supervised neural topic model (NTM) that combines the power of NTMs and regularized self-supervised learning methods to improve performance. NTMs use neural networks to learn latent topics hidden behind the words in documents, enabling greater flexibility and the ability to estimate more coherent topics compared to traditional topic models. On the other hand, some self-supervised learning methods use a joint embedding architecture with two identical networks that produce similar representations for two augmented versions of the same input. Regularizations are applied to these representations to prevent collapse, which would otherwise result in the networks outputting constant or redundant representations for all inputs. Our model enhances topic quality by explicitly regularizing latent topic representations of anchor and positive samples. We also introduced an adversarial data augmentation method to replace the heuristic sampling method. We further developed several variation models including those on the basis of an NTM that incorporates contrastive learning with both positive and negative samples. Experimental results on three datasets showed that our models outperformed baselines and state-of-the-art models both quantitatively and qualitatively.

cs.LG↗

arXiv2021

Semiparametric Latent Topic Modeling on Consumer-Generated Corpora

Legacy procedures for topic modelling have generally suffered problems of overfitting and a weakness towards reconstructing sparse topic structures. With motivation from a consumer-generated corpora, this paper proposes semiparametric topic model, a two-step approach utilizing nonnegative matrix factorization and semiparametric regression in topic modeling. The model enables the reconstruction of sparse topic structures in the corpus and provides a generative model for predicting topics in new documents entering the corpus. Assuming the presence of auxiliary information related to the topics, this approach exhibits better performance in discovering underlying topic structures in cases where the corpora are small and limited in vocabulary. In an actual consumer feedback corpus, the model also demonstrably provides interpretable and useful topic definitions comparable with those produced by other methods.

cs.CL↗

arXiv2025

What is a Digital Twin Anyway? Deriving the Definition for the Built Environment from over 15,000 Scientific Publications

The concept of digital twins has attracted significant attention across various domains, particularly within the built environment. However, there is a sheer volume of definitions and the terminological consensus remains out of reach. The lack of a universally accepted definition leads to ambiguities in their conceptualization and implementation, and may cause miscommunication for both researchers and practitioners. We employed Natural Language Processing (NLP) techniques to systematically extract and analyze definitions of digital twins from a corpus of more than 15,000 full-text articles spanning diverse disciplines. The study compares these findings with insights from an expert survey that included 52 experts. The study identifies concurrence on the components that comprise a ``Digital Twin'' from a practical perspective across various domains, contrasting them with those that do not, to identify deviations. We investigate the evolution of digital twin definitions over time and across different scales, including manufacturing, building, and urban/geospatial perspectives. We extracted the main components of Digital Twins using Text Frequency Analysis and N-gram analysis. Subsequently, we identified components that appeared in the literature and conducted a Chi-square test to assess the significance of each component in different domains. Our analysis identified key components of digital twins and revealed significant variations in definitions based on application domains, such as manufacturing, building, and urban contexts. The analysis of DT components reveal two major groups of DT types: High-Performance Real-Time (HPRT) DTs, and Long-Term Decision Support (LTDS) DTs. Contrary to common assumptions, we found that components such as simulation, AI/ML, real-time capabilities, and bi-directional data flow are not yet fully mature in the digital twins of the built environment.

cs.CL↗

arXiv2025

Geo-Semantic-Parsing: AI-powered geoparsing by traversing semantic knowledge graphs

Online social networks convey rich information about geospatial facets of reality. However in most cases, geographic information is not explicit and structured, thus preventing its exploitation in real-time applications. We address this limitation by introducing a novel geoparsing and geotagging technique called Geo-Semantic-Parsing (GSP). GSP identifies location references in free text and extracts the corresponding geographic coordinates. To reach this goal, we employ a semantic annotator to identify relevant portions of the input text and to link them to the corresponding entity in a knowledge graph. Then, we devise and experiment with several efficient strategies for traversing the knowledge graph, thus expanding the available set of information for the geoparsing task. Finally, we exploit all available information for learning a regression model that selects the best entity with which to geotag the input text. We evaluate GSP on a well-known reference dataset including almost 10k event-related tweets, achieving $F1=0.66$. We extensively compare our results with those of 2 baselines and 3 state-of-the-art geoparsing techniques, achieving the best performance. On the same dataset, competitors obtain $F1 \leq 0.55$. We conclude by providing in-depth analyses of our results, showing that the overall superior performance of GSP is mainly due to a large improvement in recall, with respect to existing techniques.

cs.CL↗

arXiv2025

A Systematic Review of Open Datasets Used in Text-to-Image (T2I) Gen AI Model Safety

Novel research aimed at text-to-image (T2I) generative AI safety often relies on publicly available datasets for training and evaluation, making the quality and composition of these datasets crucial. This paper presents a comprehensive review of the key datasets used in the T2I research, detailing their collection methods, compositions, semantic and syntactic diversity of prompts and the quality, coverage, and distribution of harm types in the datasets. By highlighting the strengths and limitations of the datasets, this study enables researchers to find the most relevant datasets for a use case, critically assess the downstream impacts of their work given the dataset distribution, particularly regarding model safety and ethical considerations, and also identify the gaps in dataset coverage and quality that future research may address.

cs.CL↗

arXiv2025

Advancements in Natural Language Processing for Automatic Text Summarization

The substantial growth of textual content in diverse domains and platforms has led to a considerable need for Automatic Text Summarization (ATS) techniques that aid in the process of text analysis. The effectiveness of text summarization models has been significantly enhanced in a variety of technical domains because of advancements in Natural Language Processing (NLP) and Deep Learning (DL). Despite this, the process of summarizing textual information continues to be significantly constrained by the intricate writing styles of a variety of texts, which involve a range of technical complexities. Text summarization techniques can be broadly categorized into two main types: abstractive summarization and extractive summarization. Extractive summarization involves directly extracting sentences, phrases, or segments of text from the content without making any changes. On the other hand, abstractive summarization is achieved by reconstructing the sentences, phrases, or segments from the original text using linguistic analysis. Through this study, a linguistically diverse categorizations of text summarization approaches have been addressed in a constructive manner. In this paper, the authors explored existing hybrid techniques that have employed both extractive and abstractive methodologies. In addition, the pros and cons of various approaches discussed in the literature are also investigated. Furthermore, the authors conducted a comparative analysis on different techniques and matrices to evaluate the generated summaries using language generation models. This survey endeavors to provide a comprehensive overview of ATS by presenting the progression of language processing regarding this task through a breakdown of diverse systems and architectures accompanied by technical and mathematical explanations of their operations.

cs.CL↗

arXiv2024

Using LLMs to Establish Implicit User Sentiment of Software Desirability

This study explores the use of LLMs for providing quantitative zero-shot sentiment analysis of implicit software desirability, addressing a critical challenge in product evaluation where traditional review scores, though convenient, fail to capture the richness of qualitative user feedback. Innovations include establishing a method that 1) works with qualitative user experience data without the need for explicit review scores, 2) focuses on implicit user satisfaction, and 3) provides scaled numerical sentiment analysis, offering a more nuanced understanding of user sentiment, instead of simply classifying sentiment as positive, neutral, or negative. Data is collected using the Microsoft Product Desirability Toolkit (PDT), a well-known qualitative user experience analysis tool. For initial exploration, the PDT metric was given to users of two software systems. PDT data was fed through several LLMs (Claude Sonnet 3 and 3.5, GPT4, and GPT4o) and through a leading transfer learning technique, Twitter-Roberta-Base-Sentiment, and Vader, a leading sentiment analysis tool. Each system was asked to evaluate the data in two ways, by looking at the sentiment expressed in the PDT word/explanation pairs; and by looking at the sentiment expressed by the users in their grouped selection of five words and explanations, as a whole. Each LLM provided a sentiment score, its confidence (low, medium, high) in the score, and an explanation of the score. All LLMs tested were able to statistically detect user sentiment from the users' grouped data, whereas TRBS and Vader were not. The confidence and explanation of confidence provided by the LLMs assisted in understanding user sentiment. This study adds deeper understanding of evaluating user experiences, toward the goal of creating a universal tool that quantifies implicit sentiment.

cs.CL↗

arXiv2024

DrawTalking: Building Interactive Worlds by Sketching and Speaking

We introduce DrawTalking, an approach to building and controlling interactive worlds by sketching and speaking while telling stories. It emphasizes user control and flexibility, and gives programming-like capability without requiring code. An early open-ended study with our prototype shows that the mechanics resonate and are applicable to many creative-exploratory use cases, with the potential to inspire and inform research in future natural interfaces for creative exploration and authoring.

cs.HC↗

arXiv2025

MobileSteward: Integrating Multiple App-Oriented Agents with Self-Evolution to Automate Cross-App Instructions

Mobile phone agents can assist people in automating daily tasks on their phones, which have emerged as a pivotal research spotlight. However, existing procedure-oriented agents struggle with cross-app instructions, due to the following challenges: (1) complex task relationships, (2) diverse app environment, and (3) error propagation and information loss in multi-step execution. Drawing inspiration from object-oriented programming principles, we recognize that object-oriented solutions is more suitable for cross-app instruction. To address these challenges, we propose a self-evolving multi-agent framework named MobileSteward, which integrates multiple app-oriented StaffAgents coordinated by a centralized StewardAgent. We design three specialized modules in MobileSteward: (1) Dynamic Recruitment generates a scheduling graph guided by information flow to explicitly associate tasks among apps. (2) Assigned Execution assigns the task to app-oriented StaffAgents, each equipped with app-specialized expertise to address the diversity between apps. (3) Adjusted Evaluation conducts evaluation to provide reflection tips or deliver key information, which alleviates error propagation and information loss during multi-step execution. To continuously improve the performance of MobileSteward, we develop a Memory-based Self-evolution mechanism, which summarizes the experience from successful execution, to improve the performance of MobileSteward. We establish the first English Cross-APP Benchmark (CAPBench) in the real-world environment to evaluate the agents' capabilities of solving complex cross-app instructions. Experimental results demonstrate that MobileSteward achieves the best performance compared to both single-agent and multi-agent frameworks, highlighting the superiority of MobileSteward in better handling user instructions with diverse complexity.

cs.MA↗

arXiv2025

Towards a Robust Framework for Multimodal Hate Detection: A Study on Video vs. Image-based Content

Social media platforms enable the propagation of hateful content across different modalities such as textual, auditory, and visual, necessitating effective detection methods. While recent approaches have shown promise in handling individual modalities, their effectiveness across different modality combinations remains unexplored. This paper presents a systematic analysis of fusion-based approaches for multimodal hate detection, focusing on their performance across video and image-based content. Our comprehensive evaluation reveals significant modality-specific limitations: while simple embedding fusion achieves state-of-the-art performance on video content (HateMM dataset) with a 9.9% points F1-score improvement, it struggles with complex image-text relationships in memes (Hateful Memes dataset). Through detailed ablation studies and error analysis, we demonstrate how current fusion approaches fail to capture nuanced cross-modal interactions, particularly in cases involving benign confounders. Our findings provide crucial insights for developing more robust hate detection systems and highlight the need for modality-specific architectural considerations. The code is available at https://github.com/gak97/Video-vs-Meme-Hate.

cs.CV↗

arXiv2025

AI on My Shoulder: Supporting Emotional Labor in Front-Office Roles with an LLM-based Empathetic Coworker

Client-Service Representatives (CSRs) are vital to organizations. Frequent interactions with disgruntled clients, however, disrupt their mental well-being. To help CSRs regulate their emotions while interacting with uncivil clients, we designed Care-Pilot, an LLM-powered assistant, and evaluated its efficacy, perception, and use. Our comparative analyses between 665 human and Care-Pilot-generated support messages highlight Care-Pilot's ability to adapt to and demonstrate empathy in various incivility incidents. Additionally, 143 CSRs assessed Care-Pilot's empathy as more sincere and actionable than human messages. Finally, we interviewed 20 CSRs who interacted with Care-Pilot in a simulation exercise. They reported that Care-Pilot helped them avoid negative thinking, recenter thoughts, and humanize clients; showing potential for bridging gaps in coworker support. Yet, they also noted deployment challenges and emphasized the indispensability of shared experiences. We discuss future designs and societal implications of AI-mediated emotional labor, underscoring empathy as a critical function for AI assistants for worker mental health.

cs.HC↗

arXiv2025

Lost in Moderation: How Commercial Content Moderation APIs Over- and Under-Moderate Group-Targeted Hate Speech and Linguistic Variations

Commercial content moderation APIs are marketed as scalable solutions to combat online hate speech. However, the reliance on these APIs risks both silencing legitimate speech, called over-moderation, and failing to protect online platforms from harmful speech, known as under-moderation. To assess such risks, this paper introduces a framework for auditing black-box NLP systems. Using the framework, we systematically evaluate five widely used commercial content moderation APIs. Analyzing five million queries based on four datasets, we find that APIs frequently rely on group identity terms, such as ``black'', to predict hate speech. While OpenAI's and Amazon's services perform slightly better, all providers under-moderate implicit hate speech, which uses codified messages, especially against LGBTQIA+ individuals. Simultaneously, they over-moderate counter-speech, reclaimed slurs and content related to Black, LGBTQIA+, Jewish, and Muslim people. We recommend that API providers offer better guidance on API implementation and threshold setting and more transparency on their APIs' limitations. Warning: This paper contains offensive and hateful terms and concepts. We have chosen to reproduce these terms for reasons of transparency.

cs.HC↗

arXiv2025

Scaffolding Empathy: Training Counselors with Simulated Patients and Utterance-level Performance Visualizations

Learning therapeutic counseling involves significant role-play experience with mock patients, with current manual training methods providing only intermittent granular feedback. We seek to accelerate and optimize counselor training by providing frequent, detailed feedback to trainees as they interact with a simulated patient. Our first application domain involves training motivational interviewing skills for counselors. Motivational interviewing is a collaborative counseling style in which patients are guided to talk about changing their behavior, with empathetic counseling an essential ingredient. We developed and evaluated an LLM-powered training system that features a simulated patient and visualizations of turn-by-turn performance feedback tailored to the needs of counselors learning motivational interviewing. We conducted an evaluation study with professional and student counselors, demonstrating high usability and satisfaction with the system. We present design implications for the development of automated systems that train users in counseling skills and their generalizability to other types of social skills training.

cs.HC↗

arXiv2024

FinTextQA: A Dataset for Long-form Financial Question Answering

Accurate evaluation of financial question answering (QA) systems necessitates a comprehensive dataset encompassing diverse question types and contexts. However, current financial QA datasets lack scope diversity and question complexity. This work introduces FinTextQA, a novel dataset for long-form question answering (LFQA) in finance. FinTextQA comprises 1,262 high-quality, source-attributed QA pairs extracted and selected from finance textbooks and government agency websites.Moreover, we developed a Retrieval-Augmented Generation (RAG)-based LFQA system, comprising an embedder, retriever, reranker, and generator. A multi-faceted evaluation approach, including human ranking, automatic metrics, and GPT-4 scoring, was employed to benchmark the performance of different LFQA system configurations under heightened noisy conditions. The results indicate that: (1) Among all compared generators, Baichuan2-7B competes closely with GPT-3.5-turbo in accuracy score; (2) The most effective system configuration on our dataset involved setting the embedder, retriever, reranker, and generator as Ada2, Automated Merged Retrieval, Bge-Reranker-Base, and Baichuan2-7B, respectively; (3) models are less susceptible to noise after the length of contexts reaching a specific threshold.

cs.CL↗