Adi Simhi

According to our database, Adi Simhi authored at least 9 papers between 2023 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Old Habits Die Hard: How Conversational History Geometrically Traps LLMs.

Adi Simhi, Fazl Barez, Martin Tutek, Yonatan Belinkov, Shay B. Cohen

CoRR, March, 2026

2025

BlackboxNLP-2025 MIB Shared Task: Improving Circuit Faithfulness via Better Edge Selection.

Yaniv Nikankin, Dana Arad, Itay Itzhak, Anja Reusch, Adi Simhi, Gal Kesten-Pomeranz, Yonatan Belinkov

CoRR, October, 2025

HACK: Hallucinations Along Certainty and Knowledge Axes.

Adi Simhi, Jonathan Herzig, Itay Itzhak, Dana Arad, Zorik Gekhman, Roi Reichart, Fazl Barez, Gabriel Stanovsky, Idan Szpektor, Yonatan Belinkov

CoRR, October, 2025

ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs.

Adi Simhi, Jonathan Herzig, Martin Tutek, Itay Itzhak, Idan Szpektor, Yonatan Belinkov

CoRR, October, 2025

Trust Me, I'm Wrong: High-Certainty Hallucinations in LLMs.

Adi Simhi, Itay Itzhak, Fazl Barez, Gabriel Stanovsky, Yonatan Belinkov

CoRR, February, 2025

Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer.

Adi Simhi, Itay Itzhak, Fazl Barez, Gabriel Stanovsky, Yonatan Belinkov

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

2024

Distinguishing Ignorance from Error in LLM Hallucinations.

Adi Simhi, Jonathan Herzig, Idan Szpektor, Yonatan Belinkov

CoRR, 2024

Constructing Benchmarks and Interventions for Combating Hallucinations in LLMs.

Adi Simhi, Jonathan Herzig, Idan Szpektor, Yonatan Belinkov

CoRR, 2024

2023

Interpreting Embedding Spaces by Conceptualization.

Adi Simhi, Shaul Markovitch

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023