On Overcoming Miscalibrated Conversational Priors in LLM-based Chatbots
Christine Herlihy, Jennifer Neville, Tobias Schnabel, Adith Swaminathan
2024 Uncertainty in Artificial Intelligence | July 2024
Tobias Schnabel
Senior Researcher
Publications
Publications by Year
-
-
HINT: Integration Testing for AI-based Features with Humans in the Loop
Quanze Chen, Tobias Schnabel, Besmira Nushi, Saleema Amershi
International Conference on Intelligent User Interfaces | March 2022
Lightweight Compositional Embeddings for Incremental Streaming Recommendation
Mengyue Hang, Tobias Schnabel, Longqi Yang, Jennifer Neville
Machine Learning on Graphs, WSDM'22 | February 2022
SummaC: Re-visiting NLI-based Models for Inconsistency Detection in Summarization
Philippe Laban, Tobias Schnabel, Paul Bennett, Marti A. Hearst
Transactions of the Association for Computational Linguistics | February 2022, Vol 10: pp. 163-177
-
Local Factor Models for Large-Scale Inductive Recommendation
Longqi Yang, Tobias Schnabel, Paul Bennett, Susan Dumais
RecSys | September 2021
Keep It Simple: Unsupervised Simplification of Multi-Paragraph Text
Philippe Laban, Tobias Schnabel, Paul Bennett, Marti A. Hearst
ACL-IJCNLP 2021 | July 2021
-
Debiasing Item-to-Item Recommendations With Small Annotated Datasets
Tobias Schnabel, Paul Bennett
RecSys | September 2020
“Who doesn’t like dinosaurs?” Finding and Eliciting Richer Preferences for Recommendation
Tobias Schnabel, Gonzalo Ramos, Saleema Amershi
14th ACM Conference on Recommender Systems | September 2020
The Impact of More Transparent Interfaces on Behavior in Personalized Recommendation
Tobias Schnabel, Saleema Amershi, Paul Bennett, Peter Bailey, Thorsten Joachims
Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) | July 2020
-
Deep Generalized Method of Moments for Instrumental Variable Analysis
Tobias Schnabel, Andrew Bennett, Nathan Kallus
NeurIPS | December 2019
Shaping Feedback Data in Recommender Systems with Interventions Based on Information Foraging Theory
Tobias Schnabel, Paul Bennett, Thorsten Joachims
The 12th ACM International Conference on Web Search and Data Mining (WSDM 2019) | March 2019
-
Short-Term Satisfaction and Long-Term Coverage: Understanding How Users Tolerate Algorithmic Exploration
Tobias Schnabel, Paul N. Bennett, Susan Dumais, Thorsten Joachims
Proceedings of the 11th ACM International Conference on Web Search and Data Mining (WSDM '18) | February 2018
-
Unbiased Learning-to-Rank with Biased Feedback
Thorsten Joachims, Adith Swaminathan, Tobias Schnabel
2017 Web Search and Data Mining | February 2017
Best Paper Award
-
Unbiased Comparative Evaluation of Ranking Functions
Tobias Schnabel, Adith Swaminathan, Peter Frazier, Thorsten Joachims
ACM International Conference on the Theory of Information Retrieval | September 2016
Recommendations as Treatments: Debiasing Learning and Evaluation
Tobias Schnabel, Adith Swaminathan, Ashudeep Singh, Navin Chandak, Thorsten Joachims
2016 International Conference on Machine Learning | June 2016
Using Shortlists to Support Decision Making and Improve Recommender System Performance
Tobias Schnabel, Paul N. Bennett, Susan T. Dumais, Thorsten Joachims
Proceedings of the 25th International World Wide Web Conference (WWW '16) | May 2016
Publications by Research Area
-
On Overcoming Miscalibrated Conversational Priors in LLM-based Chatbots
Christine Herlihy, Jennifer Neville, Tobias Schnabel, Adith Swaminathan
2024 Uncertainty in Artificial Intelligence | July 2024
Prompts As Programs: A Structure-Aware Approach to Efficient Compile-Time Prompt Optimization
Tobias Schnabel, Jennifer Neville
April 2024
HINT: Integration Testing for AI-based Features with Humans in the Loop
Quanze Chen, Tobias Schnabel, Besmira Nushi, Saleema Amershi
International Conference on Intelligent User Interfaces | March 2022
SummaC: Re-visiting NLI-based Models for Inconsistency Detection in Summarization
Philippe Laban, Tobias Schnabel, Paul Bennett, Marti A. Hearst
Transactions of the Association for Computational Linguistics | February 2022, Vol 10: pp. 163-177
Lightweight Compositional Embeddings for Incremental Streaming Recommendation
Mengyue Hang, Tobias Schnabel, Longqi Yang, Jennifer Neville
Machine Learning on Graphs, WSDM'22 | February 2022
Local Factor Models for Large-Scale Inductive Recommendation
Longqi Yang, Tobias Schnabel, Paul Bennett, Susan Dumais
RecSys | September 2021
Keep It Simple: Unsupervised Simplification of Multi-Paragraph Text
Philippe Laban, Tobias Schnabel, Paul Bennett, Marti A. Hearst
ACL-IJCNLP 2021 | July 2021
Debiasing Item-to-Item Recommendations With Small Annotated Datasets
Tobias Schnabel, Paul Bennett
RecSys | September 2020
“Who doesn’t like dinosaurs?” Finding and Eliciting Richer Preferences for Recommendation
Tobias Schnabel, Gonzalo Ramos, Saleema Amershi
14th ACM Conference on Recommender Systems | September 2020
The Impact of More Transparent Interfaces on Behavior in Personalized Recommendation
Tobias Schnabel, Saleema Amershi, Paul Bennett, Peter Bailey, Thorsten Joachims
Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) | July 2020
Deep Generalized Method of Moments for Instrumental Variable Analysis
Tobias Schnabel, Andrew Bennett, Nathan Kallus
NeurIPS | December 2019
Shaping Feedback Data in Recommender Systems with Interventions Based on Information Foraging Theory
Tobias Schnabel, Paul Bennett, Thorsten Joachims
The 12th ACM International Conference on Web Search and Data Mining (WSDM 2019) | March 2019
Short-Term Satisfaction and Long-Term Coverage: Understanding How Users Tolerate Algorithmic Exploration
Tobias Schnabel, Paul N. Bennett, Susan Dumais, Thorsten Joachims
Proceedings of the 11th ACM International Conference on Web Search and Data Mining (WSDM '18) | February 2018
Unbiased Learning-to-Rank with Biased Feedback
Thorsten Joachims, Adith Swaminathan, Tobias Schnabel
2017 Web Search and Data Mining | February 2017
Best Paper Award
Recommendations as Treatments: Debiasing Learning and Evaluation
Tobias Schnabel, Adith Swaminathan, Ashudeep Singh, Navin Chandak, Thorsten Joachims
2016 International Conference on Machine Learning | June 2016
Using Shortlists to Support Decision Making and Improve Recommender System Performance
Tobias Schnabel, Paul N. Bennett, Susan T. Dumais, Thorsten Joachims
Proceedings of the 25th International World Wide Web Conference (WWW '16) | May 2016
-
On Overcoming Miscalibrated Conversational Priors in LLM-based Chatbots
Christine Herlihy, Jennifer Neville, Tobias Schnabel, Adith Swaminathan
2024 Uncertainty in Artificial Intelligence | July 2024
The Impact of More Transparent Interfaces on Behavior in Personalized Recommendation
Tobias Schnabel, Saleema Amershi, Paul Bennett, Peter Bailey, Thorsten Joachims
Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) | July 2020
Shaping Feedback Data in Recommender Systems with Interventions Based on Information Foraging Theory
Tobias Schnabel, Paul Bennett, Thorsten Joachims
The 12th ACM International Conference on Web Search and Data Mining (WSDM 2019) | March 2019
Unbiased Learning-to-Rank with Biased Feedback
Thorsten Joachims, Adith Swaminathan, Tobias Schnabel
2017 Web Search and Data Mining | February 2017
Best Paper Award
Unbiased Comparative Evaluation of Ranking Functions
Tobias Schnabel, Adith Swaminathan, Peter Frazier, Thorsten Joachims
ACM International Conference on the Theory of Information Retrieval | September 2016
Recommendations as Treatments: Debiasing Learning and Evaluation
Tobias Schnabel, Adith Swaminathan, Ashudeep Singh, Navin Chandak, Thorsten Joachims
2016 International Conference on Machine Learning | June 2016
Using Shortlists to Support Decision Making and Improve Recommender System Performance
Tobias Schnabel, Paul N. Bennett, Susan T. Dumais, Thorsten Joachims
Proceedings of the 25th International World Wide Web Conference (WWW '16) | May 2016
-
SummaC: Re-visiting NLI-based Models for Inconsistency Detection in Summarization
Philippe Laban, Tobias Schnabel, Paul Bennett, Marti A. Hearst
Transactions of the Association for Computational Linguistics | February 2022, Vol 10: pp. 163-177
Keep It Simple: Unsupervised Simplification of Multi-Paragraph Text
Philippe Laban, Tobias Schnabel, Paul Bennett, Marti A. Hearst
ACL-IJCNLP 2021 | July 2021
-
HINT: Integration Testing for AI-based Features with Humans in the Loop
Quanze Chen, Tobias Schnabel, Besmira Nushi, Saleema Amershi
International Conference on Intelligent User Interfaces | March 2022
“Who doesn’t like dinosaurs?” Finding and Eliciting Richer Preferences for Recommendation
Tobias Schnabel, Gonzalo Ramos, Saleema Amershi
14th ACM Conference on Recommender Systems | September 2020
The Impact of More Transparent Interfaces on Behavior in Personalized Recommendation
Tobias Schnabel, Saleema Amershi, Paul Bennett, Peter Bailey, Thorsten Joachims
Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) | July 2020
Using Shortlists to Support Decision Making and Improve Recommender System Performance
Tobias Schnabel, Paul N. Bennett, Susan T. Dumais, Thorsten Joachims
Proceedings of the 25th International World Wide Web Conference (WWW '16) | May 2016
Publications by Type
-
On Overcoming Miscalibrated Conversational Priors in LLM-based Chatbots
Christine Herlihy, Jennifer Neville, Tobias Schnabel, Adith Swaminathan
2024 Uncertainty in Artificial Intelligence | July 2024
HINT: Integration Testing for AI-based Features with Humans in the Loop
Quanze Chen, Tobias Schnabel, Besmira Nushi, Saleema Amershi
International Conference on Intelligent User Interfaces | March 2022
Lightweight Compositional Embeddings for Incremental Streaming Recommendation
Mengyue Hang, Tobias Schnabel, Longqi Yang, Jennifer Neville
Machine Learning on Graphs, WSDM'22 | February 2022
Local Factor Models for Large-Scale Inductive Recommendation
Longqi Yang, Tobias Schnabel, Paul Bennett, Susan Dumais
RecSys | September 2021
Keep It Simple: Unsupervised Simplification of Multi-Paragraph Text
Philippe Laban, Tobias Schnabel, Paul Bennett, Marti A. Hearst
ACL-IJCNLP 2021 | July 2021
Debiasing Item-to-Item Recommendations With Small Annotated Datasets
Tobias Schnabel, Paul Bennett
RecSys | September 2020
“Who doesn’t like dinosaurs?” Finding and Eliciting Richer Preferences for Recommendation
Tobias Schnabel, Gonzalo Ramos, Saleema Amershi
14th ACM Conference on Recommender Systems | September 2020
The Impact of More Transparent Interfaces on Behavior in Personalized Recommendation
Tobias Schnabel, Saleema Amershi, Paul Bennett, Peter Bailey, Thorsten Joachims
Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) | July 2020
Deep Generalized Method of Moments for Instrumental Variable Analysis
Tobias Schnabel, Andrew Bennett, Nathan Kallus
NeurIPS | December 2019
Shaping Feedback Data in Recommender Systems with Interventions Based on Information Foraging Theory
Tobias Schnabel, Paul Bennett, Thorsten Joachims
The 12th ACM International Conference on Web Search and Data Mining (WSDM 2019) | March 2019
Short-Term Satisfaction and Long-Term Coverage: Understanding How Users Tolerate Algorithmic Exploration
Tobias Schnabel, Paul N. Bennett, Susan Dumais, Thorsten Joachims
Proceedings of the 11th ACM International Conference on Web Search and Data Mining (WSDM '18) | February 2018
Unbiased Learning-to-Rank with Biased Feedback
Thorsten Joachims, Adith Swaminathan, Tobias Schnabel
2017 Web Search and Data Mining | February 2017
Best Paper Award
Unbiased Comparative Evaluation of Ranking Functions
Tobias Schnabel, Adith Swaminathan, Peter Frazier, Thorsten Joachims
ACM International Conference on the Theory of Information Retrieval | September 2016
Recommendations as Treatments: Debiasing Learning and Evaluation
Tobias Schnabel, Adith Swaminathan, Ashudeep Singh, Navin Chandak, Thorsten Joachims
2016 International Conference on Machine Learning | June 2016
Using Shortlists to Support Decision Making and Improve Recommender System Performance
Tobias Schnabel, Paul N. Bennett, Susan T. Dumais, Thorsten Joachims
Proceedings of the 25th International World Wide Web Conference (WWW '16) | May 2016
-
-
SummaC: Re-visiting NLI-based Models for Inconsistency Detection in Summarization
Philippe Laban, Tobias Schnabel, Paul Bennett, Marti A. Hearst
Transactions of the Association for Computational Linguistics | February 2022, Vol 10: pp. 163-177