Papers by Rebecca Kehlbeck
Revealing the Unwritten: Visual Investigation of Beam Search Trees to Address Language Model Prompting Challenges (2025.acl-demo)
Copied to clipboard
Thilo Spinner, Rita Sevastjanova, Rebecca Kehlbeck, Tobias Stähle, Daniel A. Keim, Oliver Deussen, Andreas Spitz, Mennatallah El-Assady
| Challenge: | generative language models have become popular, but comprehending their outputs remains challenging for NLP practitioners and linguistic experts. |
| Approach: | They propose to use a beam search tree to examine model outputs to provide information on runner-up candidates and their corresponding probabilities to address these challenges. |
| Outcome: | The proposed method validates existing results and offers additional insights. |