8 citations · 30 across the 22 of their papers we have counts for
9 papers · 1 filter
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…
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…
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…
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…
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…
VIANA: Visual Interactive Annotation of Argumentation
Fabian Sperrle, Rita Sevastjanova, Rebecca Kehlbeck +1
Argumentation Mining addresses the challenging tasks of identifying boundaries of argumentative text fragments and extracting their relationships. Fully automated solutions do not…