C. Monz

UvA-DARE (Digital Academic Repository) Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Last Translation Benchmark

The Last Translation Benchmark is introduced, a collection of human-authored and peer-reviewed examples that break leading machine translation models and a new evaluation approach: each example comes with handcrafted verification rules describing concrete failure cases on that example, therefore allowing reliable and a...

Multi-Turn On-Policy Distillation with Prefix Replay

ReOPD turns expensive agent-environment interaction into a reusable offline resource, enabling scalable distillation across tools, tasks, and environments and preserves or improves OPD-level accuracy, uses zero tool calls during student training, and is at least 4$\times faster per rollout than OPD.

Do Language Models Reason Across Languages?

This paper introduces a simple two-hop question answering setting, where answering a question requires making inferences over two multilingual documents, and finds that language models are more sensitive to language variation in answer-span documents than in those providing bridging information, despite the equal impor...

Ladders in Chaos: When, How, (and Perhaps Why) Does Test-Time Scaling Improve LLM Machine Translation

This study shows that sequential sampling has a higher performance ceiling, providing a more diverse and effective pool of samples, particularly under smaller sampling budgets, and suggests an explanation of the mechanism through which sequential scaling improves machine translation.