Yehonatan Elisha

Yehonatan Elisha

Auto-generated profile, based on publicly available information

Yehonatan Elisha

Tel Aviv University, Tel Aviv, Israel

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 October 2023
Verified
Conference Paper
Open access
OBOren Barkan
Oren Barkan
YEYehonatan Elisha
Yehonatan Elisha
JWJonathan Weill
Jonathan Weill
YAYuval Asher
Yuval Asher
AEAmit Eshel
Amit Eshel
Noam KoenigsteinNoam Koenigstein
Noam Koenigstein
This paper presents Deep Integrated Explanations (DIX) - a universal method for explaining vision models. DIX generates explanation maps by integrating information from the intermediate representations of the model, coupled with their corresponding gradients. Through an extensive array of both objective and subjective evaluations spanning diverse tasks, datasets, and model configurations, we showcase the efficacy of DIX in generating faithful and accurate explanation maps, while surpassing current state-of-the-art methods. Our code is available at: https://github.com/dix-cikm23/dix

21 October 2024
Verified
Conference Paper
Open access
OBOren Barkan
Oren Barkan
YTYonatan Toib
Yonatan Toib
YEYehonatan Elisha
Yehonatan Elisha
Noam KoenigsteinNoam Koenigstein
Noam Koenigstein
We present Learning Attributions (LA), a novel method for explaining language models. The core idea behind LA is to train a dedicated attribution model that functions as a surrogate explainer for the language model. This attribution model is designed to identify which tokens are most influential in driving the model's predictions. By optimizing the attribution model to mask the minimal amount of information necessary to induce substantial changes in the language model's output, LA provides a mechanism to understand which tokens in the input are critical for the model's decisions. We demonstrate the effectiveness of LA across several language models, highlighting its superiority over multiple state-of-the-art explanation methods across various datasets and evaluation metrics.

22 November 2025 in ACM Transactions on Recommender Systems
Verified
Journal Article
Open access
LGLiya Gurevitch
Liya Gurevitch
VBVeronika Bogina
Veronika Bogina
OBOren Barkan
Oren Barkan
YSYahlly Schein
Yahlly Schein
YEYehonatan Elisha
Yehonatan Elisha
Noam KoenigsteinNoam Koenigstein
Noam Koenigstein
Recommender systems have become integral to many online services, leveraging user data to provide personalized recommendations. However, as these systems grow in complexity, understanding the rationale behind their recommendations becomes increasingly difficult. Explainable Artificial Intelligence (XAI) has emerged as a crucial field addressing this challenge, particularly in ensuring transparency and trustworthiness in automated decision-making processes. In this article, we introduce Learning to eXplain Recommendations (LXR) , a scalable, model-agnostic framework designed to generate counterfactually correct explanations for recommender systems. LXR generates explanations for recommendations produced by any differentiable recommender system. By leveraging both factual and counterfactual loss terms, LXR offers robust, accurate, and computationally efficient explanations that reflect the model’s internal decision-making process. A key feature of LXR is its focus on the factual correctness of explanations through counterfactual reasoning, bridging the gap between plausible and accurate explanations. Unlike traditional approaches that rely on exhaustive perturbations of user data, LXR uses a self-supervised learning method to generate explanations efficiently, without sacrificing accuracy. LXR operates in two stages: a pre-training step and a novel Inference-Time Fine-tuning (ITF) step that refines explanations at the individual recommendation level, significantly improving accuracy with minimal computational overhead. Additionally, LXR is applied to hybrid recommender models incorporating demographic data, demonstrating its versatility across real-world scenarios. Finally, we also showcase LXR’s ability to explain recommendations at various ranks within a user’s recommendation list. As a secondary contribution, we introduce several novel evaluation metrics, inspired by saliency maps from computer vision, to rigorously assess the counterfactual correctness of explanations in recommender systems. Our results demonstrate that LXR sets a new benchmark for explainability, providing accurate, transparent, and interpretable explanations. The code is available on our GitHub repository: https://github.com/DeltaLabTLV/LXR_ .

13 July 2025
Verified
Conference Paper
Open access
MBMikhail Baklanov
Mikhail Baklanov
VBVeronika Bogina
Veronika Bogina
YEYehonatan Elisha
Yehonatan Elisha
YSYahlly Schein
Yahlly Schein
LALiron Allerhand
Liron Allerhand
Noam KoenigsteinNoam Koenigstein
Noam Koenigstein

21 October 2024
Verified
Conference Paper
Open access
YEYehonatan Elisha
Yehonatan Elisha
OBOren Barkan
Oren Barkan
Noam KoenigsteinNoam Koenigstein
Noam Koenigstein
Path integration methods generate attributions by integrating along a trajectory from a baseline to the input. These techniques have demonstrated considerable effectiveness in the field of explainability research. While multiple types of baselines for the path integration process have been explored in the literature, there is no consensus on the ultimate one. This work examines the performance of different baseline distributions on explainability metrics and proposes a probabilistic path integration approach where the baseline distribution is modeled as a mixture of distributions, learned for each combination of model architecture and explanation metric. Extensive evaluations on various model architectures show that our method outperforms state-of-the-art explanation methods across multiple metrics.