# Align-SLM: Textless Spoken Language Models with Reinforcement Learning from AI Feedback

arXiv: https://arxiv.org/abs/2411.01834 · HTML: https://mlsanity.com/paper/2411.01834/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 41 of its 53 references that are in the map.
- First posted on arXiv 4 Nov 2024.

## Placed in

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

## Builds on (most cited first, 30 of 41)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [AudioLM: a Language Modeling Approach to Audio Generation](https://mlsanity.com/paper/2209.03143/) (2022)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities](https://mlsanity.com/paper/2305.11000/) (2023)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [Generative Spoken Language Modeling from Raw Audio](https://mlsanity.com/paper/2102.01192/) (2021)
- [Speech Resynthesis from Discrete Disentangled Self-Supervised Representations](https://mlsanity.com/paper/2104.00355/) (2021)
- [Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming](https://mlsanity.com/paper/2408.16725/) (2024)
- [Spirit LM: Interleaved Spoken and Written Language Model](https://mlsanity.com/paper/2402.05755/) (2024)
- [Text-Free Prosody-Aware Generative Spoken Language Modeling](https://mlsanity.com/paper/2109.03264/) (2021)
- [The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling](https://mlsanity.com/paper/2011.11588/) (2020)
- [Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization](https://mlsanity.com/paper/2404.09956/) (2024)
- [Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM](https://mlsanity.com/paper/2305.15255/) (2023)
- [Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks](https://mlsanity.com/paper/2309.07937/) (2023)
- [Generalization Ability of MOS Prediction Networks](https://mlsanity.com/paper/2110.02635/) (2021)
- [Advancing Large Language Models to Capture Varied Speaking Styles and Respond Properly in Spoken Conversations](https://mlsanity.com/paper/2402.12786/) (2024)
- [On the Utility of Self-supervised Models for Prosody-related Tasks](https://mlsanity.com/paper/2210.07185/) (2022)

## Built on by (most cited first, 23 of 23)

- [On The Landscape of Spoken Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2504.08528/) (2025)
- [Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities](https://mlsanity.com/paper/2503.04721/) (2025)
- [Recent Advances in Discrete Speech Tokens: A Review](https://mlsanity.com/paper/2502.06490/) (2025)
- [TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling](https://mlsanity.com/paper/2504.07053/) (2025)
- [Scaling Analysis of Interleaved Speech-Text Language Models](https://mlsanity.com/paper/2504.02398/) (2025)
- [Understanding the Modality Gap: An Empirical Study on the Speech-Text Alignment Mechanism of Large Speech Language Models](https://mlsanity.com/paper/2510.12116/) (2025)
- [Slamming: Training a Speech Language Model on One GPU in a Day](https://mlsanity.com/paper/2502.15814/) (2025)
- [Aligning Spoken Dialogue Models from User Interactions](https://mlsanity.com/paper/2506.21463/) (2025)
- [Multi-Faceted Interactivity Alignment in Full-Duplex Speech Models](https://mlsanity.com/paper/2606.11167/) (2026)
- [Why Do Speech Language Models Fail to Generate Semantically Coherent Outputs? A Modality Evolving Perspective](https://mlsanity.com/paper/2412.17048/) (2024)
- [Covo-Audio Technical Report](https://mlsanity.com/paper/2602.09823/) (2026)
- [SAKE: Towards Editing Auditory Attribute Knowledge of Large Audio-Language Models](https://mlsanity.com/paper/2510.16917/) (2025)
- [Optimizing Conversational Quality in Spoken Dialogue Systems with Reinforcement Learning from AI Feedback](https://mlsanity.com/paper/2601.19063/) (2026)
- [Robust and Efficient Autoregressive Speech Synthesis with Dynamic Chunk-wise Prediction Policy](https://mlsanity.com/paper/2506.22023/) (2025)
- [ASPIRin: Action Space Projection for Interactivity-Optimized Reinforcement Learning in Full-Duplex Speech Language Models](https://mlsanity.com/paper/2604.10065/) (2026)
- [EMO-Reasoning: Benchmarking Emotional Reasoning Capabilities in Spoken Dialogue Systems](https://mlsanity.com/paper/2508.17623/) (2025)
- [RLAIF-SPA: Structured AI Feedback for Semantic-Prosodic Alignment in Speech Synthesis](https://mlsanity.com/paper/2510.14628/) (2025)
- [Dual-Axis Generative Reward Model Toward Semantic and Turn-taking Robustness in Interactive Spoken Dialogue Models](https://mlsanity.com/paper/2604.14920/) (2026)
- [GmSLM : Generative Marmoset Spoken Language Modeling](https://mlsanity.com/paper/2509.09198/) (2025)
- [Cross-Lingual Interleaving for Speech Language Models](https://mlsanity.com/paper/2512.01865/) (2025)
- [AP-GRPO: Anchor-Gated Phonetic Alignment with Policy Optimization for Pathological Speech Reconstruction](https://mlsanity.com/paper/2606.15540/) (2026)
- [On the Effect of Segmentation Width and Cluster Size on Speech Resynthesis and Continuation in Generative Spoken Language Models](https://mlsanity.com/paper/2606.23285/) (2026)
- [Distilling Text LMs into Speech-to-Speech LMs by Matching Internal Text Predictions](https://mlsanity.com/paper/2610.17461/) (2026)

## Abstract (arXiv)

While textless Spoken Language Models (SLMs) have shown potential in end-to-end speech-to-speech modeling, they still lag behind text-based Large Language Models (LLMs) in terms of semantic coherence and relevance. This work introduces the Align-SLM framework, which leverages preference optimization inspired by Reinforcement Learning with AI Feedback (RLAIF) to enhance the semantic understanding of SLMs. Our approach generates multiple speech continuations from a given prompt and uses semantic metrics to create preference data for Direct Preference Optimization (DPO). We evaluate the framework using ZeroSpeech 2021 benchmarks for lexical and syntactic modeling, the spoken version of the StoryCloze dataset for semantic coherence, and other speech generation metrics, including the GPT4-o score and human evaluation. Experimental results show that our method achieves state-of-the-art performance for SLMs on most benchmarks, highlighting the importance of preference optimization to improve the semantics of SLMs.