Rebecca Ramnauth
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
NLP×1AI×1
Frequent co-authors
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