Search Results for author:
Found 20 papers, 14 papers with code
BERTtime Stories: Investigating the Role of Synthetic Story Data in Language pre-training
To measure the effect of synthetic story data, we train LTG-BERT encoder models on a combined dataset of: a subset of TinyStories, story completions generated by GPT-Neo, and a subset of the BabyLM dataset.
RISCORE: Enhancing In-Context Riddle Solving in Language Models through Context-Reconstructed Example Augmentation
Riddle-solving requires advanced reasoning skills, pushing LLMs to engage in abstract thinking and creative problem-solving, often revealing limitations in their cognitive abilities.
"I Never Said That": A dataset, taxonomy and baselines on response clarity classification
Equivocation and ambiguity in public speech are well-studied discourse phenomena, especially in political science and analysis of political interviews.
GOSt-MT: A Knowledge Graph for Occupation-related Gender Biases in Machine Translation
This paper introduces a novel approach to studying occupation-related gender bias through the creation of the GOSt-MT (Gender and Occupation Statistics for Machine Translation) Knowledge Graph.
Enhancing adversarial robustness in Natural Language Inference using explanations
The surge of state-of-the-art Transformer-based models has undoubtedly pushed the limits of NLP model performance, excelling in a variety of tasks.
Prompt2Fashion: An automatically generated fashion dataset
Despite the provided fine-grained insights on the quality and relevance of generation, we extend the discussion on the importance of expert knowledge for the evaluation of artistic AI-generated datasets such as this one.
Optimal and efficient text counterfactuals using Graph Neural Networks
As NLP models become increasingly integral to decision-making processes, the need for explainability and interpretability has become paramount.
Automatic Generation of Fashion Images using Prompting in Generative Machine Learning Models
Emphasizing adaptability in AI-driven fashion creativity, we depart from traditional approaches and focus on prompting techniques, such as zero-shot and few-shot learning, as well as Chain-of-Thought (CoT), which results in a variety of colors and textures, enhancing the diversity of the outputs.
Semantic Prototypes: Enhancing Transparency Without Black Boxes
As machine learning (ML) models and datasets increase in complexity, the demand for methods that enhance explainability and interpretability becomes paramount.
AILS-NTUA at SemEval-2024 Task 6: Efficient model tuning for hallucination detection and analysis
In this paper, we present our team's submissions for SemEval-2024 Task-6 - SHROOM, a Shared-task on Hallucinations and Related Observable Overgeneration Mistakes.
AILS-NTUA at SemEval-2024 Task 9: Cracking Brain Teasers: Transformer Models for Lateral Thinking Puzzles
In this paper, we outline our submission for the SemEval-2024 Task 9 competition: 'BRAINTEASER: A Novel Task Defying Common Sense'.
Masked Generative Story Transformer with Character Guidance and Caption Augmentation
Story Visualization (SV) is a challenging generative vision task, that requires both visual quality and consistency between different frames in generated image sequences.
Structure Your Data: Towards Semantic Graph Counterfactuals
With a focus on the visual domain, we represent images as scene graphs and obtain their GNN embeddings to bypass solving the NP-hard graph similarity problem for all input pairs, an integral part of the CE computation process.
Puzzle Solving using Reasoning of Large Language Models: A Survey
Exploring the capabilities of Large Language Models (LLMs) in puzzle solving unveils critical insights into their potential and challenges in AI, marking a significant step towards understanding their applicability in complex reasoning tasks.
Choose your Data Wisely: A Framework for Semantic Counterfactuals
In this work, we build on these ideas, and propose a framework that provides counterfactual explanations in terms of knowledge graphs.
Counterfactuals of Counterfactuals: a back-translation-inspired approach to analyse counterfactual editors
We propose a new back translation-inspired evaluation methodology that utilises earlier outputs of the explainer as ground truth proxies to investigate the consistency of explainers.
Counterfactual Edits for Generative Evaluation
Evaluation of generative models has been an underrepresented field despite the surge of generative architectures.
An Impartial Transformer for Story Visualization
Story Visualization is an advanced task of computed vision that targets sequential image synthesis, where the generated samples need to be realistic, faithful to their conditioning and sequentially consistent.
Ranked #1 on
Story Visualization
on CLEVR-SV
Conceptual Edits as Counterfactual Explanations
We propose a framework for generating counterfactual explanations of black-box classifiers, which answer the question “What has to change for this to be classified as X instead of Y?” in terms of given domain knowledge.
Semantic Enrichment of Pretrained Embedding Output for Unsupervised IR
The rapid growth of scientific literature in the biomedical and clinical domain has significantly com- plicated the identification of information of interest by researchers as well as other practitioners.
Ranked #1 on
Information Retrieval
on Ohsumed
