Newest papers

Uncovering Audio-Text Alignment in Large Audio-Language Models through Cross-Modal Concept Neurons

Tzu-Quan Lin, Chih-Kai Yang, Yi-Cheng Lin, Hao Tang, Hung-yi Lee · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28189 · cited by 0 works (OpenAlex) · open-access PDF

German

Während das Sprachmodell Rückgrat auf Text allein vorbereitet ist, können große Audio-Sprachmodelle (LALMs) zu einem großen Teil akustische Attribute wie Emotion, Sprecher-Geschlecht und gesprochene Sprache erkennen. Es ist jedoch unklar, wie die Audio-Repräsentation, wenn überhaupt, mit der anderen Text-Repräsentation integriert ist, bevor das Modell Text produziert. Wir gehen davon aus, dass es einen gemeinsamen Unterraum gibt, in dem die Audio- und Textrepräsentationen ausgerichtet sind. Um diese Hypothese zu testen, identifizieren wir cross-modale Neuronen, die für die Repräsentation von Audio und Text verantwortlich sind. Wir finden Ausrichtung zwischen Audio- und Text-Neuronen in verschiedenen Graden über drei LALMs und vier akust

Machine translation (Meta M2M100); the English original follows.

Abstract

While the language model backbone is pretrained on text alone, large audio-language models (LALMs) can, to a great extent, recognize acoustic attributes, such as emotion, speaker gender, and spoken language. However, it is unclear how the audio representation is integrated, if at all, with the other text representation before the model produces text. We hypothesize that there is a shared subspace where the audio and text representations are aligned. To test this hypothesis, we identify cross-modal neurons that are responsible for representing both audio and text. We find alignment between audio and text neurons to various degrees across three LALMs and four acoustic attribute types. Causal interventions, steering and deactivating the neurons, confirm that the cross-modal neurons are not just necessary for prediction but can also be manipulated.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Representation (politics), Speech recognition, Subspace topology, Natural language processing, Artificial intelligence

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange