Causal Analysis Reduces Spurious Speech in AI LLMs
Researchers have developed a method to reduce spurious speech from full-duplex speech language models like Moshi and PersonaPlex. These models can initiate inappropriate speech during periods of silence, with Moshi initiating around 12% and PersonaPlex about 11%. The study identifies two hypotheses: either the model is selecting speech despite low probabilities or it's influenced by its previous…
1 source primary source
Key points
- Reduced spurious speech from full-duplex LLMs
- Method suppresses 13/13 Moshi and 9/9 PersonaPlex onsets
- Real-time, no retraining required
Read the original at arXiv cs.CL · by Kento Nishi primary sourceOpen source ↗
Topics · follow one to build your own front page
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Generative AI & Models
All →- Meta releases Muse Spark Open, an 816B-parameter open-weight multimodal model with 42B active parameters and 1M-token context · 22 src
- Liquid AI releases d1-ultra decision model at $0.042 per million tokens · 1 src
- Google launches Gemini 4 Argon model globally for Pro and Ultra subscribers with introductory API pricing · 32 src
- Microsoft AI chief says in-house model beats OpenAI's using quarter of compute · 1 src
- NVIDIA releases Nemotron 3.5 Super VL and Bolt edge models for enterprise agents · 8 src
Comments
via GitHub Discussions