Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Rebecca Ramnauth

Rebecca Ramnauth

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

NLP×1AI×1

Frequent co-authors

Brian Scassellati1×

Research Timeline

2026
The Attentional White Bear Effect in Transformer Language Models

The paper demonstrates that content suppression techniques used in language models only mask prohibited content at the output level, failing to eliminate the underlying concepts from the model's internal representations or attention mechanisms.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.AIRecentMay 27, 2026

The Attentional White Bear Effect in Transformer Language Models

Rebecca Ramnauth, Brian Scassellati

The paper demonstrates that content suppression techniques used in language models only mask prohibited content at the output level, failing to eliminate the underlying concepts from the model's inter…

View →