# DPO-Tuned Large Language Models for Segmentation in Simultaneous Speech Translation

arXiv: https://arxiv.org/abs/2510.12195 · HTML: https://mlsanity.com/paper/2510.12195/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 8 of its 16 references that are in the map.
- First posted on arXiv 14 Oct 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 8 of 8)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Unified Speech-Text Pre-training for Speech Translation and Recognition](https://mlsanity.com/paper/2204.05409/) (2022)
- [Efficient Wait-k Models for Simultaneous Machine Translation](https://mlsanity.com/paper/2005.08595/) (2020)
- [Re-translation versus Streaming for Simultaneous Translation](https://mlsanity.com/paper/2004.03643/) (2020)
- [SHAS: Approaching optimal Segmentation for End-to-End Speech Translation](https://mlsanity.com/paper/2202.04774/) (2022)
- [End-to-End Simultaneous Speech Translation with Differentiable Segmentation](https://mlsanity.com/paper/2305.16093/) (2023)
- [Speech Segmentation Optimization using Segmented Bilingual Speech Corpus for End-to-end Speech Translation](https://mlsanity.com/paper/2203.15479/) (2022)

## Abstract (arXiv)

Simultaneous speech translation requires accurate segmentation to balance translation quality and latency. Recent studies such as SHAS have introduced pretrained segmentation models, achieving stronger performance than heuristic rules. However, segmentation models such as SHAS, though pretrained and more robust than heuristic methods, are still constrained by supervised learning objectives and do not incorporate human preference alignment, which is crucial for natural real-time interpretation. In this work, we propose a segmentation framework based on large language models (LLMs) trained with Direct Preference Optimization (DPO). By leveraging preference alignment, our method enables LLMs to predict natural segmentation points that better meet the demands of real-time translation. We evaluate the system on the ACL 60/60 corpus across three language pairs (English-Japanese, Chinese, German), using SeamlessM4T v2 as the translation backbone. Experimental results show that our DPO-tuned LLM achieves higher segmentation accuracy than SHAS and yields consistent improvements in translation quality (BLEU, COMET) as well as latency (Average Lagging). Furthermore, our system benefits from IWSLT baselines for direct comparison. These findings highlight the potential of preference-tuned LLMs to surpass existing pretrained segmentation models and advance adaptive, human-aligned simultaneous interpretation.