# Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation

arXiv: https://arxiv.org/abs/2501.00868 · HTML: https://mlsanity.com/paper/2501.00868/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 30 references that are in the map.
- First posted on arXiv 1 Jan 2025.

## Builds on (most cited first, 23 of 23)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [Learning to Translate in Real-time with Neural Machine Translation](https://mlsanity.com/paper/1610.00388/) (2016)
- [Monotonic Multihead Attention](https://mlsanity.com/paper/1909.12406/) (2019)
- [SimulMT to SimulST: Adapting Simultaneous Text Translation to End-to-End Simultaneous Speech Translation](https://mlsanity.com/paper/2011.02048/) (2020)
- [Streaming automatic speech recognition with the transformer model](https://mlsanity.com/paper/2001.02674/) (2020)
- [Transformer-Transducer: End-to-End Speech Recognition with Self-Attention](https://mlsanity.com/paper/1910.12977/) (2019)
- [Efficient Wait-k Models for Simultaneous Machine Translation](https://mlsanity.com/paper/2005.08595/) (2020)
- [Towards Fast and Accurate Streaming End-to-End ASR](https://mlsanity.com/paper/2004.11544/) (2020)
- [RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer](https://mlsanity.com/paper/2106.04833/) (2021)
- [Information-Transport-based Policy for Simultaneous Translation](https://mlsanity.com/paper/2210.12357/) (2022)
- [TransLLaMa: LLM-based Simultaneous Translation System](https://mlsanity.com/paper/2402.04636/) (2024)
- [Attention as a Guide for Simultaneous Speech Translation](https://mlsanity.com/paper/2212.07850/) (2022)
- [Learning When to Translate for Streaming Speech](https://mlsanity.com/paper/2109.07368/) (2021)
- [Learning Optimal Policy for Simultaneous Machine Translation via Binary Search](https://mlsanity.com/paper/2305.12774/) (2023)
- [An Online Attention-based Model for Speech Recognition](https://mlsanity.com/paper/1811.05247/) (2018)
- [Decoder-only Streaming Transformer for Simultaneous Translation](https://mlsanity.com/paper/2406.03878/) (2024)
- [Glancing Future for Simultaneous Machine Translation](https://mlsanity.com/paper/2309.06179/) (2023)
- [Simultaneous Machine Translation with Tailored Reference](https://mlsanity.com/paper/2310.13588/) (2023)
- [Self-Modifying State Modeling for Simultaneous Machine Translation](https://mlsanity.com/paper/2406.02237/) (2024)

## Built on by (most cited first, 5 of 5)

- [Asynchronous Reasoning: Training-Free Interactive Thinking LLMs](https://mlsanity.com/paper/2512.10931/) (2025)
- [StreamUni: Achieving Streaming Speech Translation with a Unified Large Speech-Language Model](https://mlsanity.com/paper/2507.07803/) (2025)
- [SimulMEGA: MoE Routers are Advanced Policy Makers for Simultaneous Speech Translation](https://mlsanity.com/paper/2509.01200/) (2025)
- [DOA: Training-Free Decoder-Only Attention Policy for Long-Form Simultaneous Translation with SpeechLLMs](https://mlsanity.com/paper/2605.31432/) (2026)
- [Towards Efficient Simultaneous Inverse Text Normalization with Pretrained Text-to-Text Language Model and Read-Tag-Write Policy](https://mlsanity.com/paper/2610.19492/) (2026)

## Abstract (arXiv)

Simultaneous generation models write generation results while reading streaming inputs, necessitating a policy-maker to determine the appropriate output timing. Existing simultaneous generation methods generally adopt the traditional encoder-decoder architecture and learn the generation and policy-making capabilities through complex dynamic programming techniques. Although LLMs excel at text generation, they face challenges in taking on the role of policy-makers through traditional training methods, limiting their exploration in simultaneous generation. To overcome these limitations, we propose a novel LLM-driven Simultaneous Generation (LSG) framework, which allows the off-the-shelf LLM to decide the generation timing and produce output concurrently. Specifically, LSG selects the generation policy that minimizes latency as the baseline policy. Referring to the baseline policy, LSG enables the LLM to devise an improved generation policy that better balances latency and generation quality, and writes generation results accordingly. Experiments on simultaneous translation and streaming automatic speech recognition tasks show that our method can achieve state-of-the-art performance utilizing the open-source LLMs and demonstrate practicality in real-world scenarios.