8 citations · 30 across the 22 of their papers we have counts for
25 papers
Let Me Clarify: Interactive Modeling of Soft Attributes
Steffen Holter, Rita Sevastjanova, Michaela Benk +1
People commonly express preferences through soft attributes such as is interesting,'' which are difficult to operationalize for computational preference modeling. Latent representa…
Fetch Me If You Can: A Comprehensive Analysis of Fetch Metadata
Pedro Bernardo, Alex Ploner, Marco Squarcina +2
Effective server-side defenses against cross-site attacks depend on understanding the context in which browser requests are generated. However, servers often lack the information n…
MIVAIS: A Study Environment for Multi-Agent Mixed-Initiative Visual Analytics Applications
Tobias Stähle, Simon Schneider, Rita Sevastjanova +1
Mixed-initiative Visual Analytics (VA) systems empower human users by interleaving human intuition with software agents and their machine intelligence. However, the development and…
Creativity from Friction: Human-AI Interaction for Exploratory Structural Design
Ricardo Maia Avelino, Rita Sevastjanova, Tom Van Mele +2
AI agents that generate final answers based on user input often do not meet the needs of creative fields. Fields such as structural design and architecture need interactive systems…
Exposing the Unsaid: Visualizing Hidden LLM Bias through Stochastic Path Aggregation
Matteo Pelossi, Rita Sevastjanova, Thilo Spinner +1
Large Language Models (LLMs) exhibit representational and syntactic biases that are difficult to evaluate due to the stochastic nature of text generation. Standard auditing methods…
TopoAlign: Topology-Aware Visual Representation Alignment
Xinyuan Yan, Rita Sevastjanova, Mennatallah El-Assady +1
Neural networks encode inputs as high-dimensional vectors, known as representations, that capture how models process data by encoding task-relevant structure and semantics. Represe…
VACP: Visual Analytics Context Protocol
Tobias Stähle, Péter Ferenc Gyarmati, Thilo Spinner +3
The rise of AI agents introduces a fundamental shift in Visual Analytics (VA), in which agents act as a new user group. Current agentic approaches - based on computer vision and ra…
PleaSQLarify: Visual Pragmatic Repair for Natural Language Database Querying
Robin Shing Moon Chan, Rita Sevastjanova, Mennatallah El-Assady
Natural language database interfaces broaden data access, yet they remain brittle under input ambiguity. Standard approaches often collapse uncertainty into a single query, offerin…
A Design Space for Intelligent Agents in Mixed-Initiative Visual Analytics
Tobias Stähle, Matthijs Jansen op de Haar, Sophia Boyer +3
Mixed-initiative visual analytics (VA) systems, where human and artificial intelligence (AI) agents collaborate as equal partners during analysis, represented a paradigm shift in h…
Dia-Lingle: A Gamified Interface for Dialectal Data Collection
Jiugeng Sun, Rita Sevastjanova, Sina Ahmadi +2
Dialects suffer from the scarcity of computational textual resources as they exist predominantly in spoken rather than written form and exhibit remarkable geographical diversity. C…
Is General-Purpose AI Reasoning Sensitive to Data-Induced Cognitive Biases? Dynamic Benchmarking on Typical Software Engineering Dilemmas
Francesco Sovrano, Gabriele Dominici, Rita Sevastjanova +2
Human cognitive biases in software engineering can lead to costly errors. While general-purpose AI (GPAI) systems may help mitigate these biases due to their non-human nature, thei…
Explainable Mapper: Charting LLM Embedding Spaces Using Perturbation-Based Explanation and Verification Agents
Xinyuan Yan, Rita Sevastjanova, Sinie van der Ben +2
Large language models (LLMs) produce high-dimensional embeddings that capture rich semantic and syntactic relationships between words, sentences, and concepts. Investigating the to…
Concept-Level Explainability for Auditing & Steering LLM Responses
Kenza Amara, Rita Sevastjanova, Mennatallah El-Assady
As large language models (LLMs) become widely deployed, concerns about their safety and alignment grow. An approach to steer LLM behavior, such as mitigating biases or defending ag…
LayerFlow: Layer-wise Exploration of LLM Embeddings using Uncertainty-aware Interlinked Projections
Rita Sevastjanova, Robin Gerling, Thilo Spinner +1
Large language models (LLMs) represent words through contextual word embeddings encoding different language properties like semantics and syntax. Understanding these properties is…
Feature Clock: High-Dimensional Effects in Two-Dimensional Plots
Olga Ovcharenko, Rita Sevastjanova, Valentina Boeva
Humans struggle to perceive and interpret high-dimensional data. Therefore, high-dimensional data are often projected into two dimensions for visualization. Many applications benef…
Challenges and Opportunities in Text Generation Explainability
Kenza Amara, Rita Sevastjanova, Mennatallah El-Assady
The necessity for interpretability in natural language processing (NLP) has risen alongside the growing prominence of large language models. Among the myriad tasks within NLP, text…
generAItor: Tree-in-the-Loop Text Generation for Language Model Explainability and Adaptation
Thilo Spinner, Rebecca Kehlbeck, Rita Sevastjanova +4
Large language models (LLMs) are widely deployed in various downstream tasks, e.g., auto-completion, aided writing, or chat-based text generation. However, the considered output ca…
SyntaxShap: Syntax-aware Explainability Method for Text Generation
Kenza Amara, Rita Sevastjanova, Mennatallah El-Assady
To harness the power of large language models in safety-critical domains, we need to ensure the explainability of their predictions. However, despite the significant attention to m…
Revealing the Unwritten: Visual Investigation of Beam Search Trees to Address Language Model Prompting Challenges
Thilo Spinner, Rebecca Kehlbeck, Rita Sevastjanova +5
The growing popularity of generative language models has amplified interest in interactive methods to guide model outputs. Prompt refinement is considered one of the most effective…
Negation, Coordination, and Quantifiers in Contextualized Language Models
Aikaterini-Lida Kalouli, Rita Sevastjanova, Christin Beck +1
With the success of contextualized language models, much research explores what these models really learn and in which cases they still fail. Most of this work focuses on specific…
Visual Comparison of Language Model Adaptation
Rita Sevastjanova, Eren Cakmak, Shauli Ravfogel +2
Neural language models are widely used; however, their model parameters often need to be adapted to the specific domains and tasks of an application, which is time- and resource-co…
Beware the Rationalization Trap! When Language Model Explainability Diverges from our Mental Models of Language
Rita Sevastjanova, Mennatallah El-Assady
Language models learn and represent language differently than humans; they learn the form and not the meaning. Thus, to assess the success of language model explainability, we need…
CommAID: Visual Analytics for Communication Analysis through Interactive Dynamics Modeling
Maximilian T. Fischer, Daniel Seebacher, Rita Sevastjanova +2
Communication consists of both meta-information as well as content. Currently, the automated analysis of such data often focuses either on the network aspects via social network an…
Visual Analytics of Conversational Dynamics
Daniel Seebacher, Maximilian T. Fischer, Rita Sevastjanova +2
Large-scale interaction networks of human communication are often modeled as complex graph structures, obscuring temporal patterns within individual conversations. To facilitate th…