# Generation-Step-Aware Framework for Cross-Modal Representation and Control in Multilingual Speech-Text Models

arXiv: https://arxiv.org/abs/2601.17387 · HTML: https://mlsanity.com/paper/2601.17387/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 18 references that are in the map.
- First posted on arXiv 24 Jan 2026.

## Builds on (most cited first, 13 of 13)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [SALMONN: Towards Generic Hearing Abilities for Large Language Models](https://mlsanity.com/paper/2310.13289/) (2023)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model](https://mlsanity.com/paper/2406.04904/) (2024)
- [Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models](https://mlsanity.com/paper/2402.16438/) (2024)
- [On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons](https://mlsanity.com/paper/2404.02431/) (2024)
- [Neuron Specialization: Leveraging intrinsic task modularity for multilingual machine translation](https://mlsanity.com/paper/2404.11201/) (2024)
- [Language Arithmetics: Towards Systematic Language Neuron Identification and Manipulation](https://mlsanity.com/paper/2507.22608/) (2025)
- [Self-conditioning pre-trained language models](https://mlsanity.com/paper/2110.02802/) (2021)
- [How do Multimodal Foundation Models Encode Text and Speech? An Analysis of Cross-Lingual and Cross-Modal Representations](https://mlsanity.com/paper/2411.17666/) (2024)
- [What Language(s) Does Aya-23 Think In? How Multilinguality Affects Internal Language Representations](https://mlsanity.com/paper/2507.20279/) (2025)
- [Cross-Attention is Half Explanation in Speech-to-Text Models](https://mlsanity.com/paper/2509.18010/) (2025)

## Abstract (arXiv)

Multilingual speech-text models rely on cross-modal language alignment to transfer knowledge between speech and text, but it remains unclear whether this reflects shared computation for the same language or modality-specific processing. We introduce a generation-step-aware framework for evaluating cross-modal computation that (i) identifies language-selective neurons for each modality at different decoding steps, (ii) decomposes them into language-representation and language-control roles, and (iii) enables cross-modal comparison via overlap measures and causal intervention. Applying our framework to SeamlessM4T, and additionally evaluating its generality on the decoder-only model Qwen2-Audio, we find that cross-modal language-representation alignment is highly model dependent. SeamlessM4T exhibits pronounced generation-step-dependent specialization, where only 5-7% of language-representation neurons are shared across modalities and overlap shifts from same-language to typologically related languages during autoregressive generation, whereas Qwen2-Audio maintains substantially larger cross-modal sharing (45-47%) together with stable, strongly language-specific alignment across decoding steps. In contrast, language-control neurons identified at later decoding steps exhibit progressively stronger cross-modal transfer from speech to text in SeamlessM4T. Together, these results demonstrate that generation-step-aware analysis can reveal both shared and model-specific patterns of cross-modal computation.