Avi Caciularu

Research Scientist @ Google

I am a Research Scientist at Google Research, where I focus on natural language processing (NLP), and in particular making large language models (LLMs) more factual, consistent, and knowledgeable.

My academic journey includes completing a Ph.D. in Computer Science at the BIU NLP Lab, where I had the privilege of working with Prof. Ido Dagan, Prof. Jacob Goldberger, and Dr. Arman Cohan (from Yale). My previous education includes an M.Sc in Electrical Engineering under the supervision of Prof. David Burshtein, and a B.Sc in Computer Science and Electrical Engineering, both from Tel-Aviv University.

During my graduate studies, I had the opportunity to intern with leading teams at AI2 (Semantic Scholar team), Microsoft, and Meta AI (FAIR Labs).

My research interests focus on developing and exploring advanced infrastructure for knowledge-intensive tasks in NLP. Specifically, I am invested in the pushing the existing boundaries of LLMs, particularly in ensuring their factual accuracy and enhancing their capabilities to perform tasks requiring complex reasoning. My work also extends into deep representation learning and into AI explainability and interpretability, which are crucial for building transparent and trustworthy AI systems.

In addition to my current pursuits, I have a strong foundation in information and coding theory, and I remain intrigued by its applications in modern AI. I've also conducted research on recommender systems, a field that continues to fascinate me due to its profound impact on user experience and decision-making.

I am always open to discussions and potential collaborations on these topics. If you have insights, questions, or are interested in exploring these areas together, please feel free to reach out.


Recent News

    Sept. 2024 One paper accepted to NeurIPS 🙌
    August 2024 A new preprint on a benchmark for complex claim verification.
    June 2024 A new preprint on a complex aggregative reasoning dataset.
    May 2024 Our technical report on LLMs for education is out
    May 2024 One paper accepted to ICML 🙌

Résumé




Education

2019-2023
Bar-Ilan University

PhD in Computer Science

2017-2019
Tel Aviv University

MSc in Electrical and Electronics Engineering

2014-2018
Tel Aviv University

BSc in Computer Science and Electrical Engineering

ML Professional Experience

2023-Now
Google Research

Research Scientist

2022-2023
Google Research

Research Intern

2022
Meta AI Research (FAIR)

Research Intern

2020-2022
AI2 (Semantic Scholar Team)

Research Intern

2018-2020
Microsoft

Research Intern

Publications




Jump to publications in:
'24 '23 '22 '21 '20 '18

2024

TACT: Advancing Complex Aggregative Reasoning with Information Extraction Tools
Avi Caciularu, Alon Jacovi, Eyal Ben-David, Sasha Goldshtein, Tal Schuster, Jonathan Herzig, Gal Elidan, and Amir Globerson
The Annual Conference on Neural Information Processing Systems (NeurIPS, Datasets and Benchmarks)
Towards Responsible Development of Generative AI for Education: An Evaluation-Driven Approach
Irina Jurenka, ..., Avi Caciularu, et al.
Technical Report
Unpacking Tokenization: Evaluating Text Compression and its Correlation with Model Performance
Omer Goldman, Avi Caciularu, Matan Eyal, Kris Cao, Idan Szpektor, and Reut Tsarfaty
The Annual Meeting of the Association for Computational Linguistics (ACL Findings)
Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models
Asma Ghandeharioun*, Avi Caciularu*, Adam Pearce, Lucas Dixon, and Mor Geva
The International Conference on Machine Learning (ICML)

2023


Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks
Alon Jacovi, Avi Caciularu, Omer Goldman, and Yoav Goldberg
The Conference on Empirical Methods in Natural Language Processing (EMNLP)
The Curious Case of Hallucinatory Unanswerablity: Finding Truths in the Hidden States of Over-Confident Large Language Models
Aviv Slobodkin, Omer Goldman, Avi Caciularu, Ido Dagan, and Shauli Ravfogel
The Conference on Empirical Methods in Natural Language Processing (EMNLP)
Optimizing Retrieval-augmented Reader Models via Token Elimination
Moshe Berchansky, Peter Izsak, Avi Caciularu, Ido Dagan, and Moshe Wasserblat
The Conference on Empirical Methods in Natural Language Processing (EMNLP)
A Comprehensive Evaluation of Tool-Assisted Generation Strategies
Alon Jacovi, Avi Caciularu, Jonathan Herzig, Roee Aharoni, Bernd Bohnet, and Mor Geva
The Conference on Empirical Methods in Natural Language Processing, Findings (EMNLP Findings)
Don’t Add, don’t Miss: Effective Content Preserving Generation from Pre-Selected Text Spans
Aviv Slobodkin, Avi Caciularu, Eran Hirsch, and Ido Dagan
The Conference on Empirical Methods in Natural Language Processing, Findings (EMNLP Findings)
Peek Across: Improving Multi-Document Modeling via Cross-Document Question-Answering
Avi Caciularu, Matthew E. Peters, Jacob Goldberger, Ido Dagan, and Arman Cohan
The Annual Meeting of the Association for Computational Linguistics (ACL)
Revisiting Sentence Union Generation as a Testbed for Text Consolidation
Eran Hirsch, Valentina Pyatkin, Ruben Wolhandler, Avi Caciularu, Asi Shefer, and Ido Dagan
The Annual Meeting of the Association for Computational Linguistics, Findings (ACL Findings)
An Entangled Mixture of Variational Autoencoders Approach to Deep Clustering
Avi Caciularu and Jacob Goldberger
Neurocomputing
Explaining the decisions of power quality disturbance classifiers using latent space features
Ram Machlev, Michael Perl, Avi Caciularu, Juri Belikov, Kfir Yehuda Levy, and Yoash Levron
The International Journal of Electrical Power and Energy Systems

2022


Cross-document Event Coreference Search: Task, Dataset and Modeling
Alon Eirew, Avi Caciularu, and Ido Dagan
The Conference on Empirical Methods in Natural Language Processing (EMNLP)
QASem Parsing: Text-to-text Modeling of QA-based Semantics
Ayal Klein, Eran Hirsch, Ron Eliav, Valentina Pyatkin, Avi Caciularu, and Ido Dagan
The Conference on Empirical Methods in Natural Language Processing (EMNLP)
Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space
Mor Geva*, Avi Caciularu*, Kevin Ro Wang, and Yoav Goldberg
The Conference on Empirical Methods in Natural Language Processing (EMNLP)
LM-Debugger: An Interactive Tool for Inspection and Intervention in Transformer-Based Language Models
Mor Geva, Avi Caciularu, Guy Dar, Paul Roit, Shoval Sadde, Micah Shlain, Bar Tamir, and Yoav Goldberg
The Conference on Empirical Methods in Natural Language Processing, System demonstrations (EMNLP demo)
Long Context Question Answering via Supervised Contrastive Learning
Avi Caciularu, Ido Dagan, Jacob Goldberger, and Arman Cohan
The Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)
A Proposition-Level Clustering Approach for Multi-Document Summarization
Ori Ernst, Avi Caciularu*, Ori Shapira*, Ramakanth Pasunuru, Mohit Bansal, Jacob Goldberger, and Ido Dagan
The Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)
Interpreting BERT-based Text Similarity via Activation and Saliency Maps
Itzik Malkiel*, Dvir Ginzburg*, Oren Barkan, Avi Caciularu, Jonathan Weill, and Noam Koenigstein
The International World Wide Web Conference (WWW)
MetricBERT: Text Representation Learning via Self-Supervised Triplet Training
Itzik Malkiel*, Dvir Ginzburg*, Oren Barkan, Avi Caciularu, Jonathan Weill, and Noam Koenigstein
The International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

2021


CDLM: Cross-document Language Modeling
Avi Caciularu, Arman Cohan, Iz Beltagy, Matthew E. Peters, Arie Cattan, and Ido Dagan
The Conference on Empirical Methods in Natural Language Processing, Findings (EMNLP Findings)
iFacetSum: Coreference-based Interactive Faceted Summarization for Multi-Document Exploration
Eran Hirsch, Alon Eirew*, Ori Shapira*, Avi Caciularu, Arie Cattan, Ori Ernst, Ramakanth Pasunuru, Hadar Ronen, Mohit Bansal, and Ido Dagan
The Conference on Empirical Methods in Natural Language Processing, System demonstrations (EMNLP demo)
Cold Item Integration in Deep Hybrid Recommenders via Tunable Stochastic Gates
Oren Barkan*, Roy Hirsch*, Ori Katz*, Avi Caciularu, Jonathan Weill, and Noam Koenigstein
The International Conference on Data Mining (ICDM)
Representation Learning via Variational Bayesian Networks
Oren Barkan*, Avi Caciularu*, Idan Rejwan*, Ori Katz, Jonathan Weill, Itzik Malkiel and Noam Koenigstein
The International Conference on Information and Knowledge Management (CIKM)
Grad-SAM: Explaining Transformers via Gradient Self-Attention Maps
Oren Barkan*, Edan Hauon*, Avi Caciularu*, Ori Katz, Itzik Malkiel, Omri Armstrong, and Noam Koenigstein
The International Conference on Information and Knowledge Management (CIKM)
Anchor-based Collaborative Filtering
Oren Barkan*, Roy Hirsch*, Ori Katz*, Avi Caciularu, and Noam Koenigstein
The International Conference on Information and Knowledge Management (CIKM)
GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps
Oren Barkan*, Omri Armstrong*, Amir Hertz*, Avi Caciularu, Ori Katz, Jonathan Weill, Itzik Malkiel, and Noam Koenigstein
The International Conference on Information and Knowledge Management (CIKM)
On the Evolution of Word Order
Idan Rejwan and Avi Caciularu
Recent Advances in Natural Language Processing (RANLP), Student Research Workshop
Denoising Word Embeddings by Averaging in a Shared Space
Avi Caciularu, Ido Dagan, and Jacob Goldberger
The Joint Conference on Lexical and Computational Semantics (*SEM)
Self-Supervised Document Similarity Ranking via Contextualized Language Models and Hierarchical Inference
Dvir Ginzburg*, Itzik Malkiel*, Oren Barkan, Avi Caciularu, and Noam Koenigstein
The Annual Meeting of the Association for Computational Linguistics, Findings (ACL Findings)
Cold Start Revisited: A Deep Hybrid Recommender with Cold-Warm Item Harmonization
Oren Barkan*, Roy Hirsch*, Ori Katz*, Avi Caciularu, Yoni Weill, and Noam Koenigstein
The International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
perm2vec: Attentive Graph Permutation Selection for Decoding of Error Correction Codes
Avi Caciularu*, Nir Raviv*, Tomer Raviv, Jacob Goldberger, and Yair Be’ery
IEEE Transactions on Cognitive Communications and Networking, Special Issue

2020


Within-Between Lexical Relation Classification
Avi Caciularu*, Oren Barkan*, and Ido Dagan
The Conference on Empirical Methods in Natural Language Processing (EMNLP)
Paraphrasing vs Coreferring: Two Sides of the Same Coin
Yehudit Meged, Avi Caciularu, Vered Shwartz, and Ido Dagan
The Conference on Empirical Methods in Natural Language Processing, Findings (EMNLP Findings)
RecoBERT: A Catalog Language Model for Text-Based Recommendations
Itzik Malkiel, Oren Barkan, Avi Caciularu, Noam Razin, Ori Katz, and Noam Koenigstein
The Conference on Empirical Methods in Natural Language Processing, Findings (EMNLP Findings)
Cold Item Recommendations via Hierarchical Item2vec
Oren Barkan*, Avi Caciularu*, Idan Rejwan*, Jonathan Weill, Ori Katz, Itzik Malkiel, and Noam Koenigstein
The International Conference on Data Mining (ICDM)
Explainable Recommendations via Attentive Multi-Persona Collaborative Filtering
Oren Barkan*, Yonatan Fuchs*, Avi Caciularu, and Noam Koenigstein
The ACM Conference on Recommender Systems (RecSys)
Attentive Item2vec: Neural Attentive User Representations
Oren Barkan*, Avi Caciularu*, Ori Katz, and Noam Koenigstein
International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
Bayesian Hierarchical Words Representation Learning
Oren Barkan*, Idan Rejwan*, Avi Caciularu*, and Noam Koenigstein
The Annual Meeting of the Association for Computational Linguistics (ACL)
Unsupervised Linear and Nonlinear Channel Equalization and Decoding using Variational Autoencoders
Avi Caciularu and David Burshtein
IEEE Transactions on Cognitive Communications and Networking (TCCN)
Scalable Attentive Sentence-Pair Modeling via Distilled Sentence Embedding
Oren Barkan*, Noam Razin*, Itzik Malkiel, Ori Katz, Avi Caciularu, and Noam Koenigstein
The AAAI Conference on Artificial Intelligence (AAAI)

2018


ARPM: Additive, Retentive Penalty Method for Multidimensional NILM Algorithms
Mattan Serry, David Sriker, Avi Caciularu, Ram Machlev, Yuval Beck, and David Raz
The International Conference on the Science of Electrical Engineering (ICSEE)
Blind Channel Equalization Using Variational Autoencoders
Avi Caciularu and David Burshtein
The International Conference on Communications (ICC)
Inducing Regular Grammars Using Recurrent Neural Networks
Mor Cohen*, Avi Caciularu*, Idan Rejwan*, and Jonathan Berant
The International Joint Conferences on Artificial Intelligence (IJCAI): Workshop on Learning and Reasoning (L&R)