Get started
Author

Berk Atil

Observed names: Atil, B., Atil, Berk, Berk Atıl
Observed institution: Pennsylvania State University
OpenAlex ID: A5093902741
Non-Determinism of "Deterministic" LLM Settings
2024 · Atil, Berk, Aykent, Sarp, et al. · arXiv (Cornell University) · 301
PDF
Do Methods to Jailbreak and Defend LLMs Generalize Across Languages?
2025 · Atil, Berk, Passonneau, Rebecca J., et al. · arXiv (Cornell University) · 7
PDF
Self-Explaining Hate Speech Detection with Moral Rationales
2026 · Vargas, Francielle, Trager, Jackson, et al. · arXiv (Cornell University) · 3
PDF
Something Just Like TRuST : Toxicity Recognition of Span and Target
2025 · Atil, Berk, Sureddy, Namrata, et al. · arXiv (Cornell University) · 3
PDF
Bridging the Know-Act Gap via Task-Level Autoregressive Reasoning
2026 · Ahn, Jihyun Janice, Kamoi, Ryo, et al. · arXiv (Cornell University) · 2
PDF
Self-Explaining Hate Speech Detection with Moral Rationales
2026 · Francielle Vargas, Jackson Trager, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · 2
PDF
Robust Persona-Aware Toxicity Detection with Prompt Optimization and Learned Ensembling
2026 · Atil, Berk, Passonneau, Rebecca J., et al. · arXiv (Cornell University) · 1
PDF
VerAs: Verify Then Assess STEM Lab Reports
2024 · Berk Atil, Mahsa Sheikhi Karizaki, et al. · Lecture notes in computer science · 1
PDF
Beyond Better Ideas: How Human-AI Collaboration Shapes Scientific Ideas and Human Perceptions
2026 · Chen, Qian, Pradhan, Saatvik, et al. · arXiv (Cornell University)
PDF
Something Just Like TRuST ♪ *: Toxicity Recognition of Span and Target
2026 · Association for Computational Linguistics 2026, Atil, Berk, et al. · Underline Science Inc.
Self-Explaining Hate Speech Detection with Moral Rationales
2026 · Association for Computational Linguistics 2026, Agrawal, Ameeta, et al. · Underline Science Inc.
Model Unlearning Objectives Vary for Distinct Language Functions
2026 · Atil, Berk, Gupta, Vipul, et al. · arXiv (Cornell University)
PDF
Non-Determinism of “Deterministic” LLM System Settings in Hosted Environments
2025 · Association for Computational Linguistics 2025, Atil, Berk · Underline Science Inc.
Can LLMs Rank the Harmfulness of Smaller LLMs? We are Not There Yet
2025 · Atil, Berk, Gupta, Vipul, et al. · arXiv (Cornell University)
PDF
Works count: 16
Citation count: 321
H-index: 3
I10-index: 1
Year
Topic
Type