Dmitriy Bespalov
8 papers · 2023–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Conference Polyglot (3) π Interdisciplinary Bridge π§ Keyword Pioneer πΊοΈ Taxonomy Completionist (18) π Cross-Pollinator (7)
π
Renaissance Researcher
(5)
β‘
Prolific Year
(6)
Conferences
EMNLP (4)
ACL (2)
NAACL (2)
Top co-authors
Keywords
large language model
(3)
adversarial attack
(3)
content moderation
(3)
llm safety
(2)
prompt engineering
(2)
adversarial learning
(2)
jailbreak prompt
(2)
toxicity detection
(2)
prompt injection
(2)
chain-of-thought reasoning
(1)
efficient computing
(1)
graph structure
(1)
safety alignment
(1)
graph optimization
(1)
model selection
(1)
adversarial training
(1)
tool use
(1)
in-context learning
(1)
autonomous agent
(1)
latent variable
(1)
Papers
TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice
NAACL 2025
Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt. Generation for Enhanced LLM Content Moderation
ACL 2025
IPR: Intelligent Prompt Routing with User-Controlled Quality-Cost Trade-offs
EMNLP 2025
TaeBench: Improving Quality of Toxic Adversarial Examples
NAACL 2025
Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt Generation for Enhanced LLM Content Moderation
EMNLP 2025
Agent vs. Agent: Automated Data Generation and Red-Teaming for Custom Agentic Workflows
EMNLP 2025
LaRS: Latent Reasoning Skills for Chain-of-Thought Reasoning
EMNLP 2024
Towards Building a Robust Toxicity Predictor
ACL 2023