Publications
2025
Explain then Rank: Scale Calibration of Neural Rankers Using Natural Language Explanations from LLMs Puxuan Yu, Daniel Cohen, Hemank Lamba, Joel Tetreault, Alejandro Jaimes, ACL (Findings) 2025
2024
In-Context Example Ordering Guided by Label Distributions Zhichao Xu, Daniel Cohen, Bei Wang, Vivek Srikumar, NAACL (Findings) 2024
2023
Predictive Uncertainty-based Bias Mitigation in Ranking Maria Heuss, Daniel Cohen, Masoud Mansoury, Maarten de Rijke, Carsten Eickhoff, CIKM 2023
A Lightweight Constrained Generation Alternative for Query-Focused Summarization Zhichao Xu, Daniel Cohen, SIGIR 2023
2022
CODER: An efficient framework for improving retrieval through COntextualized Document Embedding Reranking George Zerveas, Navid Rekabsaz, Daniel Cohen, Carsten Eickhoff, EMNLP 2022 pdf
Mitigating Bias in Search Results through Set-based Document Reranking and Neutrality Regularization George Zerveas, Navid Rekabsaz, Daniel Cohen, Carsten Eickhoff, SIGIR 2022 pdf
Inconsistent Ranking Assumptions in Medical Search and Their Downstream Consequences Daniel Cohen, Kevin Du, Bhaskar Mitra, Laura Mercurio, Navid Rekabsaz, Carsten Eickhoff, SIGIR 2022 pdf
2021
A Modern Perspective on Query Likelihood with Deep Generative Retrieval Models Oleg Lesota, Navid Rekabsaz, Daniel Cohen, Klaus Antonius Grasserbauer, Carsten Eickhoff, Markus Schedl, ICTIR 2021 pdf
Not All Relevance Scores are Equal: Efficient Uncertainty and Calibration Modeling for Deep Retrieval Models Daniel Cohen, Bhaskar Mitra, Navid Rekabsaz, Carsten Eickhoff, SIGIR 2021 pdf
Allowing for the Grounded Use of Temporal Difference Learning in Large Ranking Models via Substate Updates Daniel Cohen, SIGIR 2021 pdf
2020
Evaluating the Performance of Reinforcement Learning Algorithms Scott M. Jordan, Yash Chandak, Daniel Cohen, Mengxue Zhang, Philip S. Thomas, ICML 2020 pdf
2019
Learning a Better Negative Sampling Policy with Deep Neural Networks for Search Daniel Cohen, Scott M. Jordan, W. Bruce Croft, ICTIR 2019 — Best Full Paper pdf, bibtex
An Assumption-Free Approach to the Dynamic Truncation of Ranked Lists Yen-Chieh Lien, Daniel Cohen, W. Bruce Croft, ICTIR 2019 pdf, bibtex
The Challenges of Optimizing Machine Translation for Low Resource Cross-Language Information Retrieval Constantine Lignos, Daniel Cohen, Yen-Chieh Lien, Pratik Mehta, W. Bruce Croft, Scott Miller, EMNLP 2019 pdf/bibtex
2018
Cross Domain Regularization for Neural Ranking Models using Adversarial Learning Daniel Cohen, Bhaskar Mitra, Katja Hofmann, W. Bruce Croft, SIGIR 2018 — Best Short Paper pdf, bibtex
Universal Approximation Functions for Fast Learning to Rank: Replacing Expensive Regression Forests with Simple Feed-Forward Networks John Foley*, Daniel Cohen*, Hamed Zamani, James Allan, W. Bruce Croft, SIGIR 2018 pdf, bibtex
WikiPassageQA: A Benchmark Collection for Research on Non-factoid Answer Passage Retrieval Daniel Cohen, Liu Yang, W. Bruce Croft, SIGIR 2018 pdf, bibtex
A Hybrid Embedding Approach to Noisy Answer Passage Retrieval Daniel Cohen, W. Bruce Croft, ECIR 2018 pdf, bibtex
Understanding the Representational Power of Neural Retrieval Models Using NLP Tasks Daniel Cohen, Brendan O’Connor, W. Bruce Croft, ICTIR 2018 pdf, bibtex
Distributed Evaluations: Ending Neural Point Metrics Daniel Cohen, Scott M. Jordan, W. Bruce Croft, SIGIR 2018 Workshop on Learning from Limited or Noisy Data pdf/bibtex
Using Cumulative Distribution Based Performance Analysis to Benchmark Models Scott M. Jordan, Daniel Cohen, Philip S. Thomas, NeurIPS 2018 Workshop on Critiquing and Correcting Trends in Machine Learning pdf