Search Results for author:
Found 27 papers, 15 papers with code
A Survey on Automatic Credibility Assessment of Textual Credibility Signals in the Era of Large Language Models
In the current era of social media and generative AI, an ability to automatically assess the credibility of online social media content is of tremendous importance.
Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation for Classification
We evaluate this on in-distribution and out-of-distribution classifier performance.
Task Prompt Vectors: Effective Initialization through Multi-Task Soft-Prompt Transfer
In this way, we provide a competitive alternative to state-of-the-art baselines by arithmetic addition of task prompt vectors from multiple tasks.
Fighting Randomness with Randomness: Mitigating Optimisation Instability of Fine-Tuning using Delayed Ensemble and Noisy Interpolation
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.
On Sensitivity of Learning with Limited Labelled Data to the Effects of Randomness: Impact of Interactions and Systematic Choices
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.
Comparing Specialised Small and General Large Language Models on Text Classification: 100 Labelled Samples to Achieve Break-Even Performance
When performance variance is taken into consideration, the number of required labels increases on average by $100 - 200\%$ and even up to $1500\%$ in specific cases.
Automatic Combination of Sample Selection Strategies for Few-Shot Learning
In few-shot learning, such as meta-learning, few-shot fine-tuning or in-context learning, the limited number of samples used to train a model have a significant impact on the overall success.
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).
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.
A Survey on Stability of Learning with Limited Labelled Data and its Sensitivity to the Effects of Randomness
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.
Disinformation Capabilities of Large Language Models
Automated disinformation generation is often listed as an important risk associated with large language models (LLMs).
MULTITuDE: Large-Scale Multilingual Machine-Generated Text Detection Benchmark
There is a lack of research into capabilities of recent LLMs to generate convincing text in languages other than English and into performance of detectors of machine-generated text in multilingual settings.
FUTURE-AI: International consensus guideline for trustworthy and deployable artificial intelligence in healthcare
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.
Multilingual Previously Fact-Checked Claim Retrieval
Fact-checkers are often hampered by the sheer amount of online content that needs to be fact-checked.
Eye Tracking as a Source of Implicit Feedback in Recommender Systems: A Preliminary Analysis
Eye tracking in recommender systems can provide an additional source of implicit feedback, while helping to evaluate other sources of feedback.
Searching for Discriminative Words in Multidimensional Continuous Feature Space
We demonstrate the effectiveness of our approach by achieving state-of-the-art results on text categorisation task using just a small number of extracted keywords.
Autonomation, not Automation: Activities and Needs of Fact-checkers as a Basis for Designing Human-Centered AI Systems
In addition, we mapped our findings on the fact-checkers' activities and needs to the relevant tasks for AI research.
Auditing YouTube's Recommendation Algorithm for Misinformation Filter Bubbles
We also observe a sudden decrease of misinformation filter bubble effect when misinformation debunking videos are watched after misinformation promoting videos, suggesting a strong contextuality of recommendations.
Monant Medical Misinformation Dataset: Mapping Articles to Fact-Checked Claims
It also contains 573 manually and more than 51k automatically labelled mappings between claims and articles.
An Audit of Misinformation Filter Bubbles on YouTube: Bubble Bursting and Recent Behavior Changes
We present a study in which pre-programmed agents (acting as YouTube users) delve into misinformation filter bubbles by watching misinformation promoting content (for various topics).
Exploring Customer Price Preference and Product Profit Role in Recommender Systems
We propose an adjustment of a predicted ranking for score-based recommender systems and explore the effect of the profit and customers' price preferences on two industry datasets from the fashion domain.
A Study of Fake News Reading and Annotating in Social Media Context
In this paper, we present an eye-tracking study, in which we let 44 lay participants to casually read through a social media feed containing posts with news articles, some of which were fake.
The Cold-start Problem: Minimal Users' Activity Estimation
Cold-start problem, which arises upon the new users arrival, is one of the fundamental problems in today's recommender approaches.
Session-based k-NNs with Semantic Suggestions for Next-item Prediction
One of the most critical problems in e-commerce domain is the information overload problem.
Improving Sentiment Classification in Slovak Language
We performed experiments utilizing different methods of model ensemble.
NL-FIIT at SemEval-2019 Task 9: Neural Model Ensemble for Suggestion Mining
We participated in both subtasks for domain specific and also cross-domain suggestion mining.
NL-FIIT at IEST-2018: Emotion Recognition utilizing Neural Networks and Multi-level Preprocessing
In some cases, we proposed to remove some parts of the text, as they do not affect emotion of the original sentence.
