Profiles2021-2025
Trevor Cohn
The University of Melbourne
14Papers
13Last author
21Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers14
- Planning in the Dark: LLM-Symbolic Planning Pipeline Without ExpertsAuthor 3 of 3AAAI 2025 · 19 citations
- TUBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction TuningAuthor 7 of 7ACL Findings 2025 · 6 citations
- Zero-Shot Performance Prediction for Probabilistic Scaling LawsAuthor 4 of 4NeurIPS 2025 · 2 citations
- Pre-training Cross-lingual Open Domain Question Answering with Large-scale Synthetic SupervisionAuthor 3 of 3EMNLP 2024 · 1 citation
- Mitigating Backdoor Poisoning Attacks through the Lens of Spurious CorrelationAuthor 5 of 5EMNLP 2023 · 9 citations
- Rethinking Round-Trip Translation for Machine Translation EvaluationAuthor 4 of 4ACL Findings 2023 · 9 citations
- Cost-effective Distillation of Large Language ModelsAuthor 2 of 3ACL Findings 2023 · 7 citations
- Boot and Switch: Alternating Distillation for Zero-Shot Dense RetrievalAuthor 4 of 4EMNLP Findings 2023
- Noisy Self-Training with Synthetic Queries for Dense RetrievalAuthor 3 of 3EMNLP Findings 2023
- Measuring and Mitigating Name Biases in Neural Machine TranslationAuthor 3 of 3ACL 2022 · 31 citations
- Foiling Training-Time Attacks on Neural Machine Translation SystemsAuthor 4 of 4EMNLP Findings 2022 · 1 citation
- A Targeted Attack on Black-Box Neural Machine Translation with Parallel Data PoisoningAuthor 5 of 5WWW 2021 · 37 citations
- Putting words into the system's mouth: A targeted attack on neural machine translation using monolingual data poisoningAuthor 7 of 7ACL Findings 2021 · 20 citations
- As Easy as 1, 2, 3: Behavioural Testing of NMT Systems for Numerical TranslationAuthor 6 of 6ACL Findings 2021 · 5 citations
