aiqbench analysis
This research addresses the critical challenge of cross-lingual verbosity in Large Language Models, specifically for time-sensitive applications like subtitling and dubbing. By introducing a reinforcement learning framework called Homura, the authors successfully optimize the trade-off between semantic fidelity and strict temporal constraints without sacrificing meaning. The work establishes a new benchmark, Sand-Glass, to rigorously evaluate performance under syllable-level duration limits, offering a practical solution for real-world deployment of LLMs in media production.
HOMURA: Taming the Sand-Glass for Time-Constrained LLM Translation via Reinforcement Learning
arXiv:2601.10187v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have achieved remarkable strides in multilingual translation but are hindered by a systemic cross-lingual verbosity bias, rendering them unsuitable for strict time-constrained tasks like subtitling and dubbing. Current prompt-engineering approaches struggle to resolve this conflict between semantic fidelity and rigid temporal feasibility. To bridge this gap, we first introduce Sand-Glass, a benchmark specifically designed to evaluate translation under syllable-level duration constraints. Furthermore, we propose Homura, a reinforcement learning framework that explicitly optimizes the trade-off between semantic preservation and temporal compliance. By employing a constrained reinforcement learning objective featuring a novel dynamic syllable-ratio reward, Homura effectively "tames" the output length. Experimental results demonstrate that Homura significantly outperforms strong baselines, achieving precise length control that respects linguistic density hierarchies without compromising semantic adequacy.
Abstract:Large Language Models (LLMs) have achieved remarkable strides in multilingual translation but are hindered by a systemic cross-lingual verbosity bias, rendering them unsuitable for strict time-constrained tasks like subtitling and dubbing. Current prompt-engineering approaches struggle to resolve this conflict between semantic fidelity and rigid temporal feasibility. To bridge this gap, we first introduce Sand-Glass, a benchmark specifically designed to evaluate translation under syllable-level duration constraints. Furthermore, we propose Homura, a reinforcement learning framework that explicitly optimizes the trade-off between semantic preservation and temporal compliance. By employing a constrained reinforcement learning objective featuring a novel dynamic syllable-ratio reward, Homura effectively "tames" the output length. Experimental results demonstrate that Homura significantly outperforms strong baselines, achieving precise length control that respects linguistic density hierarchies without compromising semantic adequacy.
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
arXiv:2601.10187 [cs.CL]
(or arXiv:2601.10187v3 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2601.10187 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 221 words
Related coverage
Game Design Creativity evals
LessWrong · Oct 12, 2026
[AINews] Reality Checks on AI News (Yegge shuts down Gas Town, Databricks’ +60% Astra cost)
Latent Space · Sep 17, 2026
Latent reasoning architectures would likely undermine CoT, our strongest oversight tool
AI Alignment Forum · Sep 23, 2026
The Machines that Make the Machines
NVIDIA · Oct 7, 2026