Avi Caciularu

95 papers A* 14A 5Misc 3Journal 51Unranked 22
YearRankTypeTitle / Venue / Authors
2026 — conf
ConvApparel: A Benchmark Dataset and Validation Framework for User Simulators in Conversational Recommenders.
EACL (Volume 1: Long Papers)
Ofer Meshi, Krisztian Balog, Sally Goldman, Avi Caciularu, Guy Tennenholtz, Jihwan Jeong, Amir Globerson, Craig Boutilier
2026 J jnl
ConvApparel: A Benchmark Dataset and Validation Framework for User Simulators in Conversational Recommenders.
CoRR
Ofer Meshi, Krisztian Balog, Sally Goldman, Avi Caciularu, Guy Tennenholtz, Jihwan Jeong, Amir Globerson, Craig Boutilier
2026 J jnl
Latent Reasoning with Supervised Thinking States.
CoRR
Ido Amos, Avi Caciularu, Mor Geva, Amir Globerson, Jonathan Herzig, Lior Shani, Idan Szpektor
2025 J jnl
DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs.
CoRR
Arie Cattan, Alon Jacovi, Ori Ram, Jonathan Herzig, Roee Aharoni, Sasha Goldshtein, Eran Ofek, Idan Szpektor, Avi Caciularu
2025 — conf
DoubleDipper: Recycling Contexts for Efficient and Attributed In-Context Learning.
IJCNLP-AACL (Findings)
Arie Cattan, Alon Jacovi, Alex Fabrikant, Jonathan Herzig, Roee Aharoni, Hannah Rashkin, Dror Marcus, Avinatan Hassidim, Yossi Matias, Idan Szpektor, Avi Caciularu
2025 — conf
Identifying User Goals From UI Trajectories.
WWW (Companion Volume)
Omri Berkovitch, Sapir Caduri, Noam Kahlon, Anatoly Efros, Avi Caciularu, Ido Dagan
2025 — conf
MDCure: A Scalable Pipeline for Multi-Document Instruction-Following.
ACL (1)
Gabrielle Kaili-May Liu, Bowen Shi, Avi Caciularu, Idan Szpektor, Arman Cohan
2025 A* conf
MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs.
EMNLP
Gabrielle Kaili-May Liu, Gal Yona, Avi Caciularu, Idan Szpektor, Tim G. J. Rudner, Arman Cohan
2025 J jnl
MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs.
CoRR
Gabrielle Kaili-May Liu, Gal Yona, Avi Caciularu, Idan Szpektor, Tim G. J. Rudner, Arman Cohan
2025 — conf
ReliableEval: A Recipe for Stochastic LLM Evaluation via Method of Moments.
EMNLP (Findings)
Gili Lior, Eliya Habba, Shahar Levy, Avi Caciularu, Gabriel Stanovsky
2025 J jnl
ReliableEval: A Recipe for Stochastic LLM Evaluation via Method of Moments.
CoRR
Gili Lior, Eliya Habba, Shahar Levy, Avi Caciularu, Gabriel Stanovsky
2024 J jnl
Can Few-shot Work in Long-Context? Recycling the Context to Generate Demonstrations.
CoRR
Arie Cattan, Alon Jacovi, Alex Fabrikant, Jonathan Herzig, Roee Aharoni, Hannah Rashkin, Dror Marcus, Avinatan Hassidim, Yossi Matias, Idan Szpektor, Avi Caciularu
2024 J jnl
CoverBench: A Challenging Benchmark for Complex Claim Verification.
CoRR
Alon Jacovi, Moran Ambar, Eyal Ben-David, Uri Shaham, Amir Feder, Mor Geva, Dror Marcus, Avi Caciularu
2024 J jnl
Identifying User Goals from UI Trajectories.
CoRR
Omri Berkovitch, Sapir Caduri, Noam Kahlon, Anatoly Efros, Avi Caciularu, Ido Dagan
2024 J jnl
MDCure: A Scalable Pipeline for Multi-Document Instruction-Following.
CoRR
Gabrielle Kaili-May Liu, Bowen Shi, Avi Caciularu, Idan Szpektor, Arman Cohan
2024 A* conf
Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models.
ICML
Asma Ghandeharioun, Avi Caciularu, Adam Pearce, Lucas Dixon, Mor Geva
2024 J jnl
Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models.
CoRR
Asma Ghandeharioun, Avi Caciularu, Adam Pearce, Lucas Dixon, Mor Geva
2024 J jnl
SEAM: A Stochastic Benchmark for Multi-Document Tasks.
CoRR
Gili Lior, Avi Caciularu, Arie Cattan, Shahar Levy, Ori Shapira, Gabriel Stanovsky
2024 A* conf
TACT: Advancing Complex Aggregative Reasoning with Information Extraction Tools.
NeurIPS
Avi Caciularu, Alon Jacovi, Eyal Ben-David, Sasha Goldshtein, Tal Schuster, Jonathan Herzig, Gal Elidan, Amir Globerson
2024 J jnl
TACT: Advancing Complex Aggregative Reasoning with Information Extraction Tools.
CoRR
Avi Caciularu, Alon Jacovi, Eyal Ben-David, Sasha Goldshtein, Tal Schuster, Jonathan Herzig, Gal Elidan, Amir Globerson
2024 J jnl
Towards Responsible Development of Generative AI for Education: An Evaluation-Driven Approach.
CoRR
Irina Jurenka, Markus Kunesch, Kevin R. McKee, Daniel Gillick, Shaojian Zhu, Sara Wiltberger, Shubham Milind Phal, Katherine L. Hermann, Daniel Kasenberg, Avishkar Bhoopchand, Ankit Anand, Miruna Pîslar, Stephanie Chan, Lisa Wang, Jennifer She, Parsa Mahmoudieh, Aliya Rysbek, Wei-Jen Ko, Andrea Huber, Brett Wiltshire, Gal Elidan, Roni Rabin, Jasmin Rubinovitz, Amit Pitaru, Mac McAllister, Julia Wilkowski, David Choi, Roee Engelberg, Lidan Hackmon, Adva Levin, Rachel Griffin, Michael Sears, Filip Bar, Mia Mesar, Mana Jabbour, Arslan Chaudhry, James Cohan, Sridhar Thiagarajan, Nir Levine, Ben Brown, Dilan Görür, Svetlana Grant, Rachel Hashimshoni, Laura Weidinger, Jieru Hu, Dawn Chen, Kuba Dolecki, Canfer Akbulut, Maxwell L. Bileschi, Laura Culp, Wen-Xin Dong, Nahema Marchal, Kelsie Van Deman, Hema Bajaj Misra, Michael Duah, Moran Ambar, Avi Caciularu, Sandra Lefdal, Christopher Summerfield, James An, Pierre-Alexandre Kamienny, Abhinit Mohdi, Theofilos Strinopoulos, Annie Hale, Wayne Anderson, Luis C. Cobo, Niv Efron, Muktha Ananda, Shakir Mohamed, Maureen Heymans, Zoubin Ghahramani, Yossi Matias, Ben Gomes, Lila Ibrahim
2024 — conf
Unpacking Tokenization: Evaluating Text Compression and its Correlation with Model Performance.
ACL (Findings)
Omer Goldman, Avi Caciularu, Matan Eyal, Kris Cao, Idan Szpektor, Reut Tsarfaty
2024 J jnl
Unpacking Tokenization: Evaluating Text Compression and its Correlation with Model Performance.
CoRR
Omer Goldman, Avi Caciularu, Matan Eyal, Kris Cao, Idan Szpektor, Reut Tsarfaty
2023 — conf
A Comprehensive Evaluation of Tool-Assisted Generation Strategies.
EMNLP (Findings)
Alon Jacovi, Avi Caciularu, Jonathan Herzig, Roee Aharoni, Bernd Bohnet, Mor Geva
2023 J jnl
A Comprehensive Evaluation of Tool-Assisted Generation Strategies.
CoRR
Alon Jacovi, Avi Caciularu, Jonathan Herzig, Roee Aharoni, Bernd Bohnet, Mor Geva
2023 J jnl
An entangled mixture of variational autoencoders approach to deep clustering.
Neurocomputing
Avi Caciularu, Jacob Goldberger
2023 — conf
Don't Add, don't Miss: Effective Content Preserving Generation from Pre-Selected Text Spans.
EMNLP (Findings)
Aviv Slobodkin, Avi Caciularu, Eran Hirsch, Ido Dagan
2023 J jnl
Dont Add, dont Miss: Effective Content Preserving Generation from Pre-Selected Text Spans.
CoRR
Aviv Slobodkin, Avi Caciularu, Eran Hirsch, Ido Dagan
2023 A* conf
Optimizing Retrieval-augmented Reader Models via Token Elimination.
EMNLP
Moshe Berchansky, Peter Izsak, Avi Caciularu, Ido Dagan, Moshe Wasserblat
2023 J jnl
Optimizing Retrieval-augmented Reader Models via Token Elimination.
CoRR
Moshe Berchansky, Peter Izsak, Avi Caciularu, Ido Dagan, Moshe Wasserblat
2023 — conf
Peek Across: Improving Multi-Document Modeling via Cross-Document Question-Answering.
ACL (1)
Avi Caciularu, Matthew E. Peters, Jacob Goldberger, Ido Dagan, Arman Cohan
2023 J jnl
Peek Across: Improving Multi-Document Modeling via Cross-Document Question-Answering.
CoRR
Avi Caciularu, Matthew E. Peters, Jacob Goldberger, Ido Dagan, Arman Cohan
2023 J jnl
Representation Learning via Variational Bayesian Networks.
CoRR
Oren Barkan, Avi Caciularu, Idan Rejwan, Ori Katz, Jonathan Weill, Itzik Malkiel, Noam Koenigstein
2023 — conf
Revisiting Sentence Union Generation as a Testbed for Text Consolidation.
ACL (Findings)
Eran Hirsch, Valentina Pyatkin, Ruben Wolhandler, Avi Caciularu, Asi Shefer, Ido Dagan
2023 J jnl
Revisiting Sentence Union Generation as a Testbed for Text Consolidation.
CoRR
Eran Hirsch, Valentina Pyatkin, Ruben Wolhandler, Avi Caciularu, Asi Shefer, Ido Dagan
2023 A* conf
Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks.
EMNLP
Alon Jacovi, Avi Caciularu, Omer Goldman, Yoav Goldberg
2023 J jnl
Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks.
CoRR
Alon Jacovi, Avi Caciularu, Omer Goldman, Yoav Goldberg
2023 A* conf
The Curious Case of Hallucinatory (Un)answerability: Finding Truths in the Hidden States of Over-Confident Large Language Models.
EMNLP
Aviv Slobodkin, Omer Goldman, Avi Caciularu, Ido Dagan, Shauli Ravfogel
2023 J jnl
The Curious Case of Hallucinatory Unanswerablity: Finding Truths in the Hidden States of Over-Confident Large Language Models.
CoRR
Aviv Slobodkin, Omer Goldman, Avi Caciularu, Ido Dagan, Shauli Ravfogel
2023 — conf
Utilizing Perturbation of Atoms' Positions for Equivariant Pre-Training in 3D Molecular Analysis.
MLSP
Tal Kiani, Avi Caciularu, Shani Zev, Dan Thomas Major, Jacob Goldberger
2022 A* conf
Cross-document Event Coreference Search: Task, Dataset and Modeling.
EMNLP
Alon Eirew, Avi Caciularu, Ido Dagan
2022 J jnl
Cross-document Event Coreference Search: Task, Dataset and Modeling.
CoRR
Alon Eirew, Avi Caciularu, Ido Dagan
2022 J jnl
Grad-SAM: Explaining Transformers via Gradient Self-Attention Maps.
CoRR
Oren Barkan, Edan Hauon, Avi Caciularu, Ori Katz, Itzik Malkiel, Omri Armstrong, Noam Koenigstein
2022 A* conf
Interpreting BERT-based Text Similarity via Activation and Saliency Maps.
WWW
Itzik Malkiel, Dvir Ginzburg, Oren Barkan, Avi Caciularu, Jonathan Weill, Noam Koenigstein
2022 J jnl
Interpreting BERT-based Text Similarity via Activation and Saliency Maps.
CoRR
Itzik Malkiel, Dvir Ginzburg, Oren Barkan, Avi Caciularu, Jonathan Weill, Noam Koenigstein
2022 — conf
LM-Debugger: An Interactive Tool for Inspection and Intervention in Transformer-Based Language Models.
EMNLP (Demos)
Mor Geva, Avi Caciularu, Guy Dar, Paul Roit, Shoval Sadde, Micah Shlain, Bar Tamir, Yoav Goldberg
2022 J jnl
LM-Debugger: An Interactive Tool for Inspection and Intervention in Transformer-Based Language Models.
CoRR
Mor Geva, Avi Caciularu, Guy Dar, Paul Roit, Shoval Sadde, Micah Shlain, Bar Tamir, Yoav Goldberg
2022 — conf
Long Context Question Answering via Supervised Contrastive Learning.
NAACL-HLT
Avi Caciularu, Ido Dagan, Jacob Goldberger, Arman Cohan
2022 J jnl
MetricBERT: Text Representation Learning via Self-Supervised Triplet Training.
CoRR
Itzik Malkiel, Dvir Ginzburg, Oren Barkan, Avi Caciularu, Yoni Weill, Noam Koenigstein
2022 Misc conf
Metricbert: Text Representation Learning Via Self-Supervised Triplet Training.
ICASSP
Itzik Malkiel, Dvir Ginzburg, Oren Barkan, Avi Caciularu, Yoni Weill, Noam Koenigstein
2022 — conf
Proposition-Level Clustering for Multi-Document Summarization.
NAACL-HLT
Ori Ernst, Avi Caciularu, Ori Shapira, Ramakanth Pasunuru, Mohit Bansal, Jacob Goldberger, Ido Dagan
2022 A* conf
QASem Parsing: Text-to-text Modeling of QA-based Semantics.
EMNLP
Ayal Klein, Eran Hirsch, Ron Eliav, Valentina Pyatkin, Avi Caciularu, Ido Dagan
2022 J jnl
QASem Parsing: Text-to-text Modeling of QA-based Semantics.
CoRR
Ayal Klein, Eran Hirsch, Ron Eliav, Valentina Pyatkin, Avi Caciularu, Ido Dagan
2022 A* conf
Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space.
EMNLP
Mor Geva, Avi Caciularu, Kevin Ro Wang, Yoav Goldberg
2022 J jnl
Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space.
CoRR
Mor Geva, Avi Caciularu, Kevin Ro Wang, Yoav Goldberg
2021 J jnl
A Proposition-Level Clustering Approach for Multi-Document Summarization.
CoRR
Ori Ernst, Avi Caciularu, Ori Shapira, Ramakanth Pasunuru, Mohit Bansal, Jacob Goldberger, Ido Dagan
2021 A conf
Anchor-based Collaborative Filtering.
CIKM
Oren Barkan, Roy Hirsch, Ori Katz, Avi Caciularu, Noam Koenigstein
2021 — conf
CDLM: Cross-Document Language Modeling.
EMNLP (Findings)
Avi Caciularu, Arman Cohan, Iz Beltagy, Matthew E. Peters, Arie Cattan, Ido Dagan
2021 A* conf
Cold Item Integration in Deep Hybrid Recommenders via Tunable Stochastic Gates.
ICDM
Oren Barkan, Roy Hirsch, Ori Katz, Avi Caciularu, Jonathan Weill, Noam Koenigstein
2021 J jnl
Cold Item Integration in Deep Hybrid Recommenders via Tunable Stochastic Gates.
CoRR
Oren Barkan, Roy Hirsch, Ori Katz, Avi Caciularu, Jonathan Weill, Noam Koenigstein
2021 Misc conf
Cold Start Revisited: A Deep Hybrid Recommender with Cold-Warm Item Harmonization.
ICASSP
Oren Barkan, Roy Hirsch, Ori Katz, Avi Caciularu, Yoni Weill, Noam Koenigstein
2021 J jnl
Cross-Document Language Modeling.
CoRR
Avi Caciularu, Arman Cohan, Iz Beltagy, Matthew E. Peters, Arie Cattan, Ido Dagan
2021 — conf
Denoising Word Embeddings by Averaging in a Shared Space.
*SEM
Avi Caciularu, Ido Dagan, Jacob Goldberger
2021 J jnl
Denoising Word Embeddings by Averaging in a Shared Space.
CoRR
Avi Caciularu, Ido Dagan, Jacob Goldberger
2021 A conf
GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps.
CIKM
Oren Barkan, Omri Armstrong, Amir Hertz, Avi Caciularu, Ori Katz, Itzik Malkiel, Noam Koenigstein
2021 J jnl
GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps.
CoRR
Oren Barkan, Omri Armstrong, Amir Hertz, Avi Caciularu, Ori Katz, Itzik Malkiel, Noam Koenigstein
2021 A conf
Grad-SAM: Explaining Transformers via Gradient Self-Attention Maps.
CIKM
Oren Barkan, Edan Hauon, Avi Caciularu, Ori Katz, Itzik Malkiel, Omri Armstrong, Noam Koenigstein
2021 J jnl
On the Evolution of Word Order.
CoRR
Idan Rejwan, Avi Caciularu
2021 A conf
Representation Learning via Variational Bayesian Networks.
CIKM
Oren Barkan, Avi Caciularu, Idan Rejwan, Ori Katz, Jonathan Weill, Itzik Malkiel, Noam Koenigstein
2021 — conf
Self-Supervised Document Similarity Ranking via Contextualized Language Models and Hierarchical Inference.
ACL/IJCNLP (Findings)
Dvir Ginzburg, Itzik Malkiel, Oren Barkan, Avi Caciularu, Noam Koenigstein
2021 J jnl
Self-Supervised Document Similarity Ranking via Contextualized Language Models and Hierarchical Inference.
CoRR
Dvir Ginzburg, Itzik Malkiel, Oren Barkan, Avi Caciularu, Noam Koenigstein
2021 J jnl
Utilizing Evidence Spans via Sequence-Level Contrastive Learning for Long-Context Question Answering.
CoRR
Avi Caciularu, Ido Dagan, Jacob Goldberger, Arman Cohan
2021 — conf
iFacetSum: Coreference-based Interactive Faceted Summarization for Multi-Document Exploration.
EMNLP (Demos)
Eran Hirsch, Alon Eirew, Ori Shapira, Avi Caciularu, Arie Cattan, Ori Ernst, Ramakanth Pasunuru, Hadar Ronen, Mohit Bansal, Ido Dagan
2021 J jnl
iFacetSum: Coreference-based Interactive Faceted Summarization for Multi-Document Exploration.
CoRR
Eran Hirsch, Alon Eirew, Ori Shapira, Avi Caciularu, Arie Cattan, Ori Ernst, Ramakanth Pasunuru, Hadar Ronen, Mohit Bansal, Ido Dagan
2021 J jnl
perm2vec: Attentive Graph Permutation Selection for Decoding of Error Correction Codes.
IEEE J. Sel. Areas Commun.
Avi Caciularu, Nir Raviv, Tomer Raviv, Jacob Goldberger, Yair Be'ery
2020 J jnl
Attentive Item2Vec: Neural Attentive User Representations.
CoRR
Oren Barkan, Avi Caciularu, Ori Katz, Noam Koenigstein
2020 Misc conf
Attentive Item2vec: Neural Attentive User Representations.
ICASSP
Oren Barkan, Avi Caciularu, Ori Katz, Noam Koenigstein
2020 A* conf
Bayesian Hierarchical Words Representation Learning.
ACL
Oren Barkan, Idan Rejwan, Avi Caciularu, Noam Koenigstein
2020 J jnl
Bayesian Hierarchical Words Representation Learning.
CoRR
Oren Barkan, Idan Rejwan, Avi Caciularu, Noam Koenigstein
2020 A* conf
Cold Item Recommendations via Hierarchical Item2vec.
ICDM
Oren Barkan, Avi Caciularu, Idan Rejwan, Ori Katz, Jonathan Weill, Itzik Malkiel, Noam Koenigstein
2020 A conf
Explainable Recommendations via Attentive Multi-Persona Collaborative Filtering.
RecSys
Oren Barkan, Yonatan Fuchs, Avi Caciularu, Noam Koenigstein
2020 J jnl
Explainable Recommendations via Attentive Multi-Persona Collaborative Filtering.
CoRR
Oren Barkan, Yonatan Fuchs, Avi Caciularu, Noam Koenigstein
2020 — conf
Optimizing BERT for Unlabeled Text-Based Items Similarity.
EMNLP (Findings)
Itzik Malkiel, Oren Barkan, Avi Caciularu, Noam Razin, Ori Katz, Noam Koenigstein
2020 — conf
Paraphrasing vs Coreferring: Two Sides of the Same Coin.
EMNLP (Findings)
Yehudit Meged, Avi Caciularu, Vered Shwartz, Ido Dagan
2020 J jnl
Paraphrasing vs Coreferring: Two Sides of the Same Coin.
CoRR
Yehudit Meged, Avi Caciularu, Vered Shwartz, Ido Dagan
2020 J jnl
RecoBERT: A Catalog Language Model for Text-Based Recommendations.
CoRR
Itzik Malkiel, Oren Barkan, Avi Caciularu, Noam Razin, Ori Katz, Noam Koenigstein
2020 A* conf
Scalable Attentive Sentence Pair Modeling via Distilled Sentence Embedding.
AAAI
Oren Barkan, Noam Razin, Itzik Malkiel, Ori Katz, Avi Caciularu, Noam Koenigstein
2020 J jnl
Unsupervised Linear and Nonlinear Channel Equalization and Decoding Using Variational Autoencoders.
IEEE Trans. Cogn. Commun. Netw.
Avi Caciularu, David Burshtein
2020 — conf
Within-Between Lexical Relation Classification.
EMNLP (1)
Oren Barkan, Avi Caciularu, Ido Dagan
2020 J jnl
perm2vec: Graph Permutation Selection for Decoding of Error Correction Codes using Self-Attention.
CoRR
Nir Raviv, Avi Caciularu, Tomer Raviv, Jacob Goldberger, Yair Be'ery
2019 J jnl
Scalable Attentive Sentence-Pair Modeling via Distilled Sentence Embedding.
CoRR
Oren Barkan, Noam Razin, Itzik Malkiel, Ori Katz, Avi Caciularu, Noam Koenigstein
2019 J jnl
Unsupervised Linear and Nonlinear Channel Equalization and Decoding using Variational Autoencoders.
CoRR
Avi Caciularu, David Burshtein
2018 — conf
Blind Channel Equalization Using Variational Autoencoders.
ICC Workshops
Avi Caciularu, David Burshtein
2018 J jnl
Blind Channel Equalization using Variational Autoencoders.
CoRR
Avi Caciularu, David Burshtein
2017 J jnl
Inducing Regular Grammars Using Recurrent Neural Networks.
CoRR
Mor Cohen, Avi Caciularu, Idan Rejwan, Jonathan Berant