Joe Stacey

17 papers A* 3Journal 9Unranked 5
YearRankTypeTitle / Venue / Authors
2026 — conf
Improving the OOD Performance of Closed-Source LLMs on NLI Through Strategic Data Selection.
EACL (Findings)
Joe Stacey, Lisa Alazraki, Aran Ubhi, Beyza Ermis, Aaron Mueller, Marek Rei
2025 J jnl
AgentCoMa: A Compositional Benchmark Mixing Commonsense and Mathematical Reasoning in Real-World Scenarios.
CoRR
Lisa Alazraki, Lihu Chen, Ana Brassard, Joe Stacey, Hossein A. Rahmani, Marek Rei
2025 J jnl
How to Improve the Robustness of Closed-Source Models on NLI.
CoRR
Joe Stacey, Lisa Alazraki, Aran Ubhi, Beyza Ermis, Aaron Mueller, Marek Rei
2025 J jnl
PyTOD: Programmable Task-Oriented Dialogue with Execution Feedback.
CoRR
Alexandru Coca, Bo-Hsiang Tseng, Peter Boothroyd, Jianpeng Cheng, Mark Gaynor, Zhenxing Zhang, Joe Stacey, Tristan Guigue, Héctor Martínez Alonso, Diarmuid Ó Séaghdha, Anders Johannsen
2024 A* conf
Atomic Inference for NLI with Generated Facts as Atoms.
EMNLP
Joe Stacey, Pasquale Minervini, Haim Dubossarsky, Oana-Maria Camburu, Marek Rei
2024 — conf
Distilling Robustness into Natural Language Inference Models with Domain-Targeted Augmentation.
ACL (Findings)
Joe Stacey, Marek Rei
2024 — conf
LUCID: LLM-Generated Utterances for Complex and Interesting Dialogues.
NAACL (Student Research Workshop)
Joe Stacey, Jianpeng Cheng, John Torr, Tristan Guigue, Joris Driesen, Alexandru Coca, Mark Gaynor, Anders Johannsen
2024 J jnl
LUCID: LLM-Generated Utterances for Complex and Interesting Dialogues.
CoRR
Joe Stacey, Jianpeng Cheng, John Torr, Tristan Guigue, Joris Driesen, Alexandru Coca, Mark Gaynor, Anders Johannsen
2023 J jnl
Improving Robustness in Knowledge Distillation Using Domain-Targeted Data Augmentation.
CoRR
Joe Stacey, Marek Rei
2023 J jnl
Logical Reasoning for Natural Language Inference Using Generated Facts as Atoms.
CoRR
Joe Stacey, Pasquale Minervini, Haim Dubossarsky, Oana-Maria Camburu, Marek Rei
2023 — conf
When and Why Does Bias Mitigation Work?
EMNLP (Findings)
Abhilasha Ravichander, Joe Stacey, Marek Rei
2022 J jnl
Logical Reasoning with Span Predictions: Span-level Logical Atoms for Interpretable and Robust NLI Models.
CoRR
Joe Stacey, Pasquale Minervini, Haim Dubossarsky, Marek Rei
2022 A* conf
Logical Reasoning with Span-Level Predictions for Interpretable and Robust NLI Models.
EMNLP
Joe Stacey, Pasquale Minervini, Haim Dubossarsky, Marek Rei
2022 A* conf
Supervising Model Attention with Human Explanations for Robust Natural Language Inference.
AAAI
Joe Stacey, Yonatan Belinkov, Marek Rei
2021 J jnl
Natural Language Inference with a Human Touch: Using Human Explanations to Guide Model Attention.
CoRR
Joe Stacey, Yonatan Belinkov, Marek Rei
2020 — conf
Avoiding the Hypothesis-Only Bias in Natural Language Inference via Ensemble Adversarial Training.
EMNLP (1)
Joe Stacey, Pasquale Minervini, Haim Dubossarsky, Sebastian Riedel, Tim Rocktäschel
2020 J jnl
There is Strength in Numbers: Avoiding the Hypothesis-Only Bias in Natural Language Inference via Ensemble Adversarial Training.
CoRR
Joe Stacey, Pasquale Minervini, Haim Dubossarsky, Sebastian Riedel, Tim Rocktäschel