Yehonatan Elisha

Venues

Frequent coauthors

Papers

1. Extracting Interaction-Aware Monosemantic Concepts in Recommender Systems
   AAAI 2026 ·

   Dor Arviv

   DBLP profile ↗ORCID search ↗
2. Fidelity-Aware Recommendation Explanations via Stochastic Path Integration
   AAAI 2026 ·

   Oren Barkan

   DBLP profile ↗ORCID search ↗
3. Rethinking Saliency Maps: A Cognitive Human Aligned Taxonomy and Evaluation Framework for Explanations
   AAAI 2026 · Yehonatan Elisha
4. BEE: Metric-Adapted Explanations via Baseline Exploration-Exploitation
   AAAI 2025 ·

   Oren Barkan

   DBLP profile ↗ORCID search ↗
5. Forget What You Know about LLMs Evaluations - LLMs are Like a Chameleon
   EMNLP 2025 ·

   Nurit Cohen-Inger

   DBLP profile ↗ORCID search ↗
6. Refining Fidelity Metrics for Explainable Recommendations
   SIGIR 2025 ·

   Mikhail Baklanov

   DBLP profile ↗ORCID search ↗
7. Soft Local Completeness: Rethinking Completeness in XAI
   ICCV 2025 ·

   Ziv Weiss Haddad

   DBLP profile ↗ORCID search ↗
8. A Learning-based Approach for Explaining Language Models
   CIKM 2024 ·

   Oren Barkan

   DBLP profile ↗ORCID search ↗
9. Improving LLM Attributions with Randomized Path-Integration
   EMNLP 2024 ·

   Oren Barkan

   DBLP profile ↗ORCID search ↗
10. LLM Explainability via Attributive Masking Learning
    EMNLP 2024 ·

    Oren Barkan

    DBLP profile ↗ORCID search ↗
11. Probabilistic Path Integration with Mixture of Baseline Distributions
    CIKM 2024 · Yehonatan Elisha