DR
Domenic Rosati
cs.CLcs.AIcs.DLcs.LGcs.CRcs.CYmath.OCscientific communication and educationstat.AP
On Valency
published · living versionsW_chv26fje·v1 · currentpublished
ZEMA: confidence-calibrated signed descent with only one state
with Ali Dadsetan, Frank Rudzicz
1 version
Preprints & journals
28 papers in the corpus · 2021–2026Removing Information Content Does Not Certify Tamper Resistance in Open-Weight Models2610.09004v1 · Domenic Rosati, Alessa Carbo, Ali Dadsetan et al.2026 · 0 citationsarXiv
Distribution-Specific Curvature Control with Finite-Sample Guarantees for Open-Weight Safety2607.22929v1 · Domenic Rosati, Ali Dadsetan, Hong Huang et al.2026 · 0 citationsarXiv
LLMs Underperform Graph-Based Parsers on Supervised Relation Extraction for Complex Graphs2604.08752v1 · Paolo Gajo, Domenic Rosati, Hassan Sajjad et al.2026 · 0 citationsarXiv
Limits of Convergence-Rate Control for Open-Weight Safety2602.18868v1 · Domenic Rosati, Xijie Zeng, Hong Huang et al.2026 · 0 citationsarXiv
Dependency Parsing is More Parameter-Efficient with Normalization2505.20215v2 · Paolo Gajo, Domenic Rosati, Hassan Sajjad et al.2025 · 0 citationsarXiv
Consistency in Language Models: Current Landscape, Challenges, and Future Directions2505.00268v2 · Jekaterina Novikova, Carol Anderson, Borhane Blili-Hamelin et al.2025 · 0 citationsarXiv
Content-aware rankings: a new approach to rankings in scholarship2504.05206v1 · Sean C. Rife, Joshua M. Nicholson, Beatriz Bosques et al.2025 · 1 citationarXiv
Improving Consistency in Large Language Models through Chain of Guidance2502.15924v1 · Harsh Raj, Vipul Gupta, Domenic Rosati et al.2025 · 0 citationsarXiv
Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities2502.05209v4 · Zora Che, Stephen Casper, Robert Kirk et al.2025 · 0 citationsarXiv
Evaluating Defences against Unsafe Feedback in RLHF2409.12914v3 · Domenic Rosati, Giles Edkins, Harsh Raj et al.2024 · 0 citationsarXiv
Resolving Lexical Bias in Model Editing2408.10411v3 · Hammad Rizwan, Domenic Rosati, Ga Wu et al.2024 · 0 citationsProceedings of the 42nd International Conference on Machine Learning, PMLR 267:51747-51769, 2025
Representation Noising: A Defence Mechanism Against Harmful Finetuning2405.14577v4 · Domenic Rosati, Jan Wehner, Kai Williams et al.2024 · 1 citationarXiv
Immunization against harmful fine-tuning attacks2402.16382v2 · Domenic Rosati, Jan Wehner, Kai Williams et al.2024 · 5 citationsarXiv
Long-form evaluation of model editing2402.09394v2 · Domenic Rosati, Robie Gonzales, Jinkun Chen et al.2024 · 3 citationsarXiv
Self-Consistency of Large Language Models under Ambiguity2310.13439v1 · Henning Bartsch, Ole Jorgensen, Domenic Rosati et al.2023 · 11 citationsarXiv
Semantic Consistency for Assuring Reliability of Large Language Models2308.09138v2 · Harsh Raj, Vipul Gupta, Domenic Rosati et al.2023 · 5 citationsarXiv
Background Knowledge Grounding for Readable, Relevant, and Factual Biomedical Lay Summaries2305.02104v1 · Domenic Rosati2023 · 0 citationsarXiv
Discovering substantive disagreement with review articles?2303.04219v1 · Domenic Rosati, Brian Simboli2023 · 0 citationsarXiv
Mixture of Soft Prompts for Controllable Data Generation2303.01580v2 · Derek Chen, Celine Lee, Yunan Lu et al.2023 · 8 citationsarXiv
Measuring Reliability of Large Language Models through Semantic Consistency2211.05853v2 · Harsh Raj, Domenic Rosati, Subhabrata Majumdar2022 · 10 citationsarXiv
Moving beyond word lists: towards abstractive topic labels for human-like topics of scientific documents2211.05599v1 · Domenic Rosati2022 · 0 citationsarXiv
Title detection: a novel approach to automatically finding retractions and other editorial notices in the scholarly literature2210.09553v1 · Ashish Uppala, Domenic Rosati, Josh M. Nicholson et al.2022 · 2 citationsarXiv
Using contradictions improves question answering systems2211.05598v2 · 'Etienne Fortier-Dubois, Domenic Rosati2022 · 1 citationarXiv
SynSciPass: detecting appropriate uses of scientific text generation2209.03742v2 · Domenic Rosati2022 · 5 citationsarXiv
Learning to pronounce as measuring cross-lingual joint orthography-phonology complexity2202.00794v2 · Domenic Rosati2022 · 4 citationsarXiv
Citations are not opinions: a corpus linguistics approach to understanding how citations are made2104.08087v1 · Domenic Rosati2021 · 0 citationsarXiv
scite: a smart citation index that displays the context of citations and classifies their intent using deep learning10.1101/2021.03.15.435418v1 · Nicholson, J. M., Mordaunt, M., Lopez, P. et al.2021 · 158 citationsbioRxiv
How are journals cited? characterizing journal citations by type of citation2102.11043v1 · Domenic Rosati2021 · 2 citationsarXiv
Career total: 56 works. 28 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.