PPaperPicks

Trevor Cohn

University of Melbourne, School of Computing and Information Systems, Australia

17 papers at tracked venues · 11 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast Asia
  2. SEA-SafeguardBench: Culturally Grounded Safety Benchmark for Southeast Asian Languages
  3. Tokenizer-Aware Cross-Lingual Adaptation of Decoder-Only LLMs through Embedding Relearning and Swapping
  4. Bridging Sign and Spoken Languages: Pseudo Gloss Generation for Sign Language Translation
  5. Chasing Progress, Not Perfection: Revisiting Strategies for End-to-End LLM Plan Generation
  6. Improving Language Model Distillation through Hidden State Matching
  7. LORAXBENCH: A Multitask, Multilingual Benchmark Suite for 20 Indonesian Languages
  8. MuRating: A High Quality Data Selecting Approach to Multilingual Large Language Model Pretraining
  9. Mufu: Multilingual Fused Learning for Low-Resource Translation with LLM
  10. Planning in the Dark: LLM-Symbolic Planning Pipeline Without Experts
  11. TUBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning
  12. Tulun: Transparent and Adaptable Low-resource Machine Translation
  13. Zero-Shot Performance Prediction for Probabilistic Scaling Laws
  14. Backdoor Attacks on Multilingual Machine Translation
  15. Pre-training Cross-lingual Open Domain Question Answering with Large-scale Synthetic Supervision
  16. Revisiting subword tokenization: A case study on affixal negation in large language models
  17. Simpson's Paradox and the Accuracy-Fluency Tradeoff in Translation