Itay Itzhak
4 papers · 2022–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
Top co-authors
Research topics
Keywords
language model
(2)
factual accuracy
(1)
llm evaluation
(1)
probing analysis
(1)
sensitivity analysis
(1)
integer programming
(1)
mechanistic interpretability
(1)
pre-trained language model
(1)
hallucination detection
(1)
model reliability
(1)
model optimization
(1)
circuit discovery
(1)
prompt perturbation
(1)
embedding layer
(1)
subword token
(1)
token embedding
(1)
character composition
(1)
large language model
(1)
attribution score
(1)
model certainty
(1)
Papers
BlackboxNLP-2025 MIB Shared Task: Improving Circuit Faithfulness via Better Edge Selection
EMNLP 2025
DOVE: A Large-Scale Multi-Dimensional Predictions Dataset Towards Meaningful LLM Evaluation
ACL 2025
Trust Me, I’m Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer
EMNLP 2025
Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokens
NAACL 2022