arXiv subjects

Maria Bielikova

Publications and source records attributed to Maria Bielikova.

At least 19 recordsLinked to original sources

arXiv2026

From Latent to Observable Position-Based Click Models in Carousel Interfaces

Click models are a central component of learning and evaluation in recommender systems, yet most existing models are designed for single ranked list interfaces. In contrast, modern recommender platforms increasingly use complex interfaces, such as carousels, which consist of multiple swipeable lists that enable complex user browsing behaviors. In this paper, we study position-based click models in carousel interfaces and examine optimization methods, model structure, and alignment with user behavior. We propose three novel position-based models tailored to carousels, including the first position-based model without latent variables that incorporates observed examination signals derived from eye tracking data, called the Observed Examination Position-Based Model (OEPBM). We develop a general implementation of these carousel click models, supporting multiple optimization techniques and conduct experiments comparing gradient-based methods with classic approaches, namely expectation-maximization and maximum likelihood estimation. Our results show that gradient-based optimization consistently achieves better click likelihoods. Among the evaluated models, the OEPBM achieves the strongest performance in click prediction and produces examination patterns that most closely align to user behavior. However, we also demonstrate that strong click fit does not imply realistic modeling of user examination and browsing patterns. This reveals a fundamental limitation of click-only models in complex interfaces and the need for incorporating additional behavioral signals when designing click models for carousel-based recommender systems.

cs.IR↗

arXiv2026

Task Prompt Vectors: Effective Initialization through Multi-Task Soft-Prompt Transfer

Prompt tuning is an efficient solution for training large language models (LLMs). However, current soft-prompt-based methods often sacrifice multi-task modularity, requiring the training process to be fully or partially repeated for each newly added task. While recent work on task vectors applied arithmetic operations on full model weights to achieve the desired multi-task performance, a similar approach for soft-prompts is still missing. To this end, we introduce Task Prompt Vectors, created by element-wise difference between weights of tuned soft-prompts and their random initialization. Experimental results on 12 NLU datasets show that task prompt vectors can be used in low-resource settings to effectively initialize prompt tuning on similar tasks. In addition, we show that task prompt vectors are independent of the random initialization of prompt tuning on 2 different language model architectures. This allows prompt arithmetics with the pre-trained vectors from different tasks. In this way, we provide a competitive alternative to state-of-the-art baselines by arithmetic addition of task prompt vectors from multiple tasks.

cs.CL↗

arXiv2026

PEFT-Factory: Unified Parameter-Efficient Fine-Tuning of Autoregressive Large Language Models

Parameter-Efficient Fine-Tuning (PEFT) methods address the increasing size of Large Language Models (LLMs). Currently, many newly introduced PEFT methods are challenging to replicate, deploy, or compare with one another. To address this, we introduce PEFT-Factory, a unified framework for efficient fine-tuning LLMs using both off-the-shelf and custom PEFT methods. While its modular design supports extensibility, it natively provides a representative set of 19 PEFT methods, 27 classification and text generation datasets addressing 12 tasks, and both standard and PEFT-specific evaluation metrics. As a result, PEFT-Factory provides a ready-to-use, controlled, and stable environment, improving replicability and benchmarking of PEFT methods. PEFT-Factory is a downstream framework that originates from the popular LLaMA-Factory, and is publicly available at https://github.com/kinit-sk/PEFT-Factory.

cs.CL↗

arXiv2026

PEFT-Bench: A Parameter-Efficient Fine-Tuning Methods Benchmark

Despite the state-of-the-art performance of Large Language Models (LLMs) achieved on many tasks, their massive scale often leads to high computational and environmental costs, limiting their accessibility. Parameter-Efficient Fine-Tuning (PEFT) methods address this challenge by reducing the number of trainable parameters while maintaining strong downstream performance. Despite the advances in PEFT methods, current evaluations remain limited (in terms of evaluated models and datasets) and difficult to reproduce. To bridge this gap, we introduce PEFT-Bench, a unified end-to-end benchmark for evaluating diverse PEFT methods on autoregressive LLMs. We demonstrate its usage across 27 NLP datasets and 7 PEFT methods. To account for different PEFT training and inference factors, we also introduce the PEFT Soft Cost Penalties (PSCP) metric, which takes trainable parameters, inference speed, and training memory usage into account.

cs.CL↗

arXiv2026

Automatic Combination of Sample Selection Strategies for Few-Shot Learning

In few-shot learning, the selection of samples has a significant impact on the performance of the model. While effective sample selection strategies are well-established in supervised settings, research on large language models largely overlooks them, favouring strategies specifically tailored to individual in-context learning settings. In this paper, we propose a new method for Automatic Combination of SamplE Selection Strategies (ACSESS) to leverage the strengths and complementarity of various well-established selection objectives. We investigate and compare the impact of 23 sample selection strategies on the performance of 5 in-context learning models and 3 few-shot learning approaches (meta-learning, few-shot fine-tuning) over 6 text and 8 image datasets. The experimental results show that the combination of strategies through the ACSESS method consistently outperforms all individual selection strategies and performs on par or exceeds the in-context learning specific baselines. Lastly, we demonstrate that sample selection remains effective even on smaller datasets, yielding the greatest benefits when only a few shots are selected, while its advantage diminishes as the number of shots increases.

cs.LG↗

arXiv2026

Riding the Carousel: The First Extensive Eye Tracking Analysis of Browsing Behavior in Carousel Recommenders

Carousels have become the de-facto standard user interface in online services. However, there is a lack of research in carousels, particularly examining how recommender systems may be designed differently than the traditional single-list interfaces. One of the key elements for understanding how to design a system for a particular interface is understanding how users browse. For carousels, users may browse in a number of different ways due to the added complexity of multiple topic defined-lists and swiping to see more items. Eye tracking is the key to understanding user behavior by providing valuable, direct information on how users see and navigate. In this work, we provide the first extensive analysis of the eye tracking behavior in carousel recommenders under the free-browsing setting. To understand how users browse and model their behavior, we examine the following research questions : 1) where do users start browsing, 2) how do users transition from item to item within the same carousel and across carousels, and 3) how does genre preference impact transitions? This work addresses a gap in the field and provides the first extensive empirical results of eye tracked browsing behavior in carousels for improving recommenders. Taking into account the insights learned from the above questions, our final contribution is to provide takeaways for carousel recommender system designers to better optimize their systems for user browsing behavior. The most important being an improved reordering of the ranked item positions to account for browsing behavior after swiping. These contributions aim not only to help improve current systems, but also to encourage and allow the design of new user models, systems, and metrics that are better suited to the complexity of carousel interfaces.

cs.IR↗

arXiv2026

Comparing Specialised Small and General Large Language Models on Text Classification: 100 Labelled Samples to Achieve Break-Even Performance

When solving NLP tasks with limited labelled data, researchers typically either use a general large language model without further update, or use a small number of labelled samples to tune a specialised smaller model. In this work, we answer an important question -- how many labelled samples are required for the specialised small models to outperform general large models, while taking the performance variance into consideration. By observing the behaviour of fine-tuning, instruction-tuning, prompting and in-context learning on 8 language models, we identify such performance break-even points across 8 representative text classification tasks of varying characteristics. We show that the specialised models often need only few samples (on average $100$) to be on par or better than the general ones. At the same time, the number of required labels strongly depends on the dataset or task characteristics, with fine-tuning on binary datasets requiring significantly more samples. When performance variance is taken into consideration, the number of required labels increases on average by $100 - 200\%$. Finally, larger models do not consistently lead to better performance and lower variance, with 4-bit quantisation having negligible impact.

cs.CL↗

arXiv2026

Better as Generators Than Classifiers: Leveraging LLMs and Synthetic Data for Low-Resource Multilingual Classification

Large Language Models (LLMs) have demonstrated remarkable multilingual capabilities, making them promising tools in both high- and low-resource languages. One particularly valuable use case is generating synthetic samples that can be used to train smaller models in low-resource scenarios where human-labelled data is scarce. In this work, we investigate whether these synthetic data generation capabilities can serve as a form of distillation, producing smaller models that perform on par with or even better than massive LLMs across languages and tasks. To this end, we use a state-of-the-art multilingual LLM to generate synthetic datasets covering 11 languages and 4 classification tasks. These datasets are then used to train smaller models via fine-tuning or instruction tuning, or as synthetic in-context examples for compact LLMs. Our experiments show that even small amounts of synthetic data enable smaller models to outperform the large generator itself, particularly in low-resource languages. Overall, the results suggest that LLMs are best utilised as generators (teachers) rather than classifiers, producing data that empowers smaller and more efficient multilingual models.

cs.CL↗

arXiv2025

A Survey on Automatic Credibility Assessment Using Textual Credibility Signals in the Era of Large Language Models

In the age of social media and generative AI, the ability to automatically assess the credibility of online content has become increasingly critical, complementing traditional approaches to false information detection. Credibility assessment relies on aggregating diverse credibility signals - small units of information, such as content subjectivity, bias, or a presence of persuasion techniques - into a final credibility label/score. However, current research in automatic credibility assessment and credibility signals detection remains highly fragmented, with many signals studied in isolation and lacking integration. Notably, there is a scarcity of approaches that detect and aggregate multiple credibility signals simultaneously. These challenges are further exacerbated by the absence of a comprehensive and up-to-date overview of research works that connects these research efforts under a common framework and identifies shared trends, challenges, and open problems. In this survey, we address this gap by presenting a systematic and comprehensive literature review of 175 research papers, focusing on textual credibility signals within the field of Natural Language Processing (NLP), which undergoes a rapid transformation due to advancements in Large Language Models (LLMs). While positioning the NLP research into the the broader multidisciplinary landscape, we examine both automatic credibility assessment methods as well as the detection of nine categories of credibility signals. We provide an in-depth analysis of three key categories: 1) factuality, subjectivity and bias, 2) persuasion techniques and logical fallacies, and 3) check-worthy and fact-checked claims. In addition to summarising existing methods, datasets, and tools, we outline future research direction and emerging opportunities, with particular attention to evolving challenges posed by generative AI.

cs.CL↗

arXiv2025

Autonomation, Not Automation: Activities and Needs of European Fact-checkers as a Basis for Designing Human-Centered AI Systems

To mitigate the negative effects of false information more effectively, the development of Artificial Intelligence (AI) systems to assist fact-checkers is needed. Nevertheless, the lack of focus on the needs of these stakeholders results in their limited acceptance and skepticism toward automating the whole fact-checking process. In this study, we conducted semi-structured in-depth interviews with Central European fact-checkers. Their activities and problems were analyzed using iterative content analysis. The most significant problems were validated with a survey of European fact-checkers, in which we collected 24 responses from 20 countries, i.e., 62% of active European signatories of the International Fact-Checking Network (IFCN). Our contributions include an in-depth examination of the variability of fact-checking work in non-English-speaking regions, which still remained largely uncovered. By aligning them with the knowledge from prior studies, we created conceptual models that help to understand the fact-checking processes. In addition, we mapped our findings on the fact-checkers' activities and needs to the relevant tasks for AI research, while providing a discussion on three AI tasks that were not covered by previous similar studies. The new opportunities identified for AI researchers and developers have implications for the focus of AI research in this domain.

cs.CY↗

arXiv2025

RecGaze: The First Eye Tracking and User Interaction Dataset for Carousel Interfaces

Carousel interfaces are widely used in e-commerce and streaming services, but little research has been devoted to them. Previous studies of interfaces for presenting search and recommendation results have focused on single ranked lists, but it appears their results cannot be extrapolated to carousels due to the added complexity. Eye tracking is a highly informative approach to understanding how users click, yet there are no eye tracking studies concerning carousels. There are very few interaction datasets on recommenders with carousel interfaces and none that contain gaze data. We introduce the RecGaze dataset: the first comprehensive feedback dataset on carousels that includes eye tracking results, clicks, cursor movements, and selection explanations. The dataset comprises of interactions from 3 movie selection tasks with 40 different carousel interfaces per user. In total, 87 users and 3,477 interactions are logged. In addition to the dataset, its description and possible use cases, we provide results of a survey on carousel design and the first analysis of gaze data on carousels, which reveals a golden triangle or F-pattern browsing behavior. Our work seeks to advance the field of carousel interfaces by providing the first dataset with eye tracking results on carousels. In this manner, we provide and encourage an empirical understanding of interactions with carousel interfaces, for building better recommender systems through gaze information, and also encourage the development of gaze-based recommenders.

cs.IR↗

arXiv2024

Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation for Classification

The generative large language models (LLMs) are increasingly used for data augmentation tasks, where text samples are paraphrased (or generated anew) and then used for classifier fine-tuning. Existing works on augmentation leverage the few-shot scenarios, where samples are given to LLMs as part of prompts, leading to better augmentations. Yet, the samples are mostly selected randomly and a comprehensive overview of the effects of other (more ``informed'') sample selection strategies is lacking. In this work, we compare sample selection strategies existing in few-shot learning literature and investigate their effects in LLM-based textual augmentation. We evaluate this on in-distribution and out-of-distribution classifier performance. Results indicate, that while some ``informed'' selection strategies increase the performance of models, especially for out-of-distribution data, it happens only seldom and with marginal performance increases. Unless further advances are made, a default of random sample selection remains a good option for augmentation practitioners.

cs.CL↗

arXiv2024

Authorship Obfuscation in Multilingual Machine-Generated Text Detection

High-quality text generation capability of recent Large Language Models (LLMs) causes concerns about their misuse (e.g., in massive generation/spread of disinformation). Machine-generated text (MGT) detection is important to cope with such threats. However, it is susceptible to authorship obfuscation (AO) methods, such as paraphrasing, which can cause MGTs to evade detection. So far, this was evaluated only in monolingual settings. Thus, the susceptibility of recently proposed multilingual detectors is still unknown. We fill this gap by comprehensively benchmarking the performance of 10 well-known AO methods, attacking 37 MGT detection methods against MGTs in 11 languages (i.e., 10 $\times$ 37 $\times$ 11 = 4,070 combinations). We also evaluate the effect of data augmentation on adversarial robustness using obfuscated texts. The results indicate that all tested AO methods can cause evasion of automated detection in all tested languages, where homoglyph attacks are especially successful. However, some of the AO methods severely damaged the text, making it no longer readable or easily recognizable by humans (e.g., changed language, weird characters).

cs.CL↗

arXiv2024

On Sensitivity of Learning with Limited Labelled Data to the Effects of Randomness: Impact of Interactions and Systematic Choices

While learning with limited labelled data can improve performance when the labels are lacking, it is also sensitive to the effects of uncontrolled randomness introduced by so-called randomness factors (e.g., varying order of data). We propose a method to systematically investigate the effects of randomness factors while taking the interactions between them into consideration. To measure the true effects of an individual randomness factor, our method mitigates the effects of other factors and observes how the performance varies across multiple runs. Applying our method to multiple randomness factors across in-context learning and fine-tuning approaches on 7 representative text classification tasks and meta-learning on 3 tasks, we show that: 1) disregarding interactions between randomness factors in existing works caused inconsistent findings due to incorrect attribution of the effects of randomness factors, such as disproving the consistent sensitivity of in-context learning to sample order even with random sample selection; and 2) besides mutual interactions, the effects of randomness factors, especially sample order, are also dependent on more systematic choices unexplored in existing works, such as number of classes, samples per class or choice of prompt format.

cs.CL↗

arXiv2024

Fighting Randomness with Randomness: Mitigating Optimisation Instability of Fine-Tuning using Delayed Ensemble and Noisy Interpolation

While fine-tuning of pre-trained language models generally helps to overcome the lack of labelled training samples, it also displays model performance instability. This instability mainly originates from randomness in initialisation or data shuffling. To address this, researchers either modify the training process or augment the available samples, which typically results in increased computational costs. We propose a new mitigation strategy, called Delayed Ensemble with Noisy Interpolation (DENI), that leverages the strengths of ensembling, noise regularisation and model interpolation, while retaining computational efficiency. We compare DENI with 9 representative mitigation strategies across 3 models, 4 tuning strategies and 7 text classification datasets. We show that: 1) DENI outperforms the best performing mitigation strategy (Ensemble), while using only a fraction of its cost; 2) the mitigation strategies are beneficial for parameter-efficient fine-tuning (PEFT) methods, outperforming full fine-tuning in specific cases; and 3) combining DENI with data augmentation often leads to even more effective instability mitigation.

cs.CL↗

arXiv2024

A Survey on Stability of Learning with Limited Labelled Data and its Sensitivity to the Effects of Randomness

Learning with limited labelled data, such as prompting, in-context learning, fine-tuning, meta-learning or few-shot learning, aims to effectively train a model using only a small amount of labelled samples. However, these approaches have been observed to be excessively sensitive to the effects of uncontrolled randomness caused by non-determinism in the training process. The randomness negatively affects the stability of the models, leading to large variances in results across training runs. When such sensitivity is disregarded, it can unintentionally, but unfortunately also intentionally, create an imaginary perception of research progress. Recently, this area started to attract research attention and the number of relevant studies is continuously growing. In this survey, we provide a comprehensive overview of 415 papers addressing the effects of randomness on the stability of learning with limited labelled data. We distinguish between four main tasks addressed in the papers (investigate/evaluate; determine; mitigate; benchmark/compare/report randomness effects), providing findings for each one. Furthermore, we identify and discuss seven challenges and open problems together with possible directions to facilitate further research. The ultimate goal of this survey is to emphasise the importance of this growing research area, which so far has not received an appropriate level of attention, and reveal impactful directions for future research.

cs.LG↗

arXiv2024

Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation

The latest generative large language models (LLMs) have found their application in data augmentation tasks, where small numbers of text samples are LLM-paraphrased and then used to fine-tune downstream models. However, more research is needed to assess how different prompts, seed data selection strategies, filtering methods, or model settings affect the quality of paraphrased data (and downstream models). In this study, we investigate three text diversity incentive methods well established in crowdsourcing: taboo words, hints by previous outlier solutions, and chaining on previous outlier solutions. Using these incentive methods as part of instructions to LLMs augmenting text datasets, we measure their effects on generated texts lexical diversity and downstream model performance. We compare the effects over 5 different LLMs, 6 datasets and 2 downstream models. We show that diversity is most increased by taboo words, but downstream model performance is highest with hints.

cs.CL↗

arXiv2024

FUTURE-AI: International consensus guideline for trustworthy and deployable artificial intelligence in healthcare

Despite major advances in artificial intelligence (AI) for medicine and healthcare, the deployment and adoption of AI technologies remain limited in real-world clinical practice. In recent years, concerns have been raised about the technical, clinical, ethical and legal risks associated with medical AI. To increase real world adoption, it is essential that medical AI tools are trusted and accepted by patients, clinicians, health organisations and authorities. This work describes the FUTURE-AI guideline as the first international consensus framework for guiding the development and deployment of trustworthy AI tools in healthcare. The FUTURE-AI consortium was founded in 2021 and currently comprises 118 inter-disciplinary experts from 51 countries representing all continents, including AI scientists, clinicians, ethicists, and social scientists. Over a two-year period, the consortium defined guiding principles and best practices for trustworthy AI through an iterative process comprising an in-depth literature review, a modified Delphi survey, and online consensus meetings. The FUTURE-AI framework was established based on 6 guiding principles for trustworthy AI in healthcare, i.e. Fairness, Universality, Traceability, Usability, Robustness and Explainability. Through consensus, a set of 28 best practices were defined, addressing technical, clinical, legal and socio-ethical dimensions. The recommendations cover the entire lifecycle of medical AI, from design, development and validation to regulation, deployment, and monitoring. FUTURE-AI is a risk-informed, assumption-free guideline which provides a structured approach for constructing medical AI tools that will be trusted, deployed and adopted in real-world practice. Researchers are encouraged to take the recommendations into account in proof-of-concept stages to facilitate future translation towards clinical practice of medical AI.

cs.CY↗