Good Papers

Showing papers from University of Roma "Tor Vergata" Show all papers

78%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026U Rome "La Sapienza"U Roma "La Sapienza"U Roma "Tor Vergata"University La Sapienza of RomeFondazione Icaro ETSJailbreaks & red teaming

Metaphor Is Not All Attention Needs

Poetic jailbreaks bypass LLM safety not via specific devices or format confusion, but through accumulated stylistic irregularities altering processing independently of harm detection, requiring style-aware defenses.

Olga Sorokoletova, Francesco Giarrusso, Giacomo De Luca, Piercosma Bisconti and 5 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
11/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 11 of 20 reviewers recommend it
lenient 5/5
medium 5/10
strict 1/5
80%Must read
?Must readVote to see the score
NeurIPS 2026U Roma "Tor Vergata"U BaselU Rome Tor VergataBocconiUiT the Arctic University of NorGraph neural networks

Hyperbolic Graph Neural Networks Under the Microscope: The Role of Geometry–Task Alignment

Hyperbolic graph neural networks outperform Euclidean models only when tasks align with hyperbolic geometry, not merely when graphs are tree-like.

Dionisia Naddeo, Jonas Linkerhägner, Nicola Toschi, Geri Skenderi and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it
lenient 4/5
medium 7/10
strict 1/5