AI News · Models & Methods
Natural language processing news: translation, speech-to-text, language understanding and text analytics.
217 stories · Updated
217 stories
Listwise preference feedback offers richer supervision for large language model (LLMs) alignment than pairwise comparisons, but a full ranking also reveals more sensitive user preferences. Existing privacy-preserving alignment methods focus mainly on pairwise feedback, while listwise alignment under local differential…
Despite their strong performance, large language models remain highly sensitive to prompt formulation. This issue is typically addressed at inference-time through manual prompt optimization, which introduces overhead and lacks scalability. Conversely, we focus on train-time approaches that build prompt robustness into…
Large Language Models (LLMs) have rapidly become important tools for science, education, medicine, and professional work. Despite their apparent simplicity from the user's perspective, effective and responsible use requires an understanding of how these systems work, what their limitations are, and how their outputs…
Language models do not merely memorize facts; they absorb rhetorical strategies from pretraining data, including the human tendency to reason by analogy. We ask: is this absorbed capability geometrically accessible before any instruction tuning, and what determines whether it can be activated at inference time? We…
Deployed classifiers often act on a prediction only when its confidence clears a threshold and pass the rest to a person. We ask whether one threshold serves all languages equally on typed decision interfaces, APIs that return a probability for each option of a fixed multiple-choice question. In a confirmatory study…
Users engage with large language models on tasks that are purely objective ("When was Netflix founded?"), purely subjective ("What should I name my child?") or anywhere in-between. We have rich tools for evaluating model accuracy with respect to objective criteria. However, when it comes to subjective aspects of a…
Block’s AI lab released Dessa, a full-duplex speech-to-speech model trained only on human conversation audio. It runs locally on a MacBook Pro M4 Max, but Block has published no size, benchmarks or weights. The post Block Unveils Dessa, a Full-Duplex Speech Model Trained Only on Speech appeared first on MarkTechPost .
NVIDIA released Nemotron 3.5 Transcribe, an open-weights speech LLM with 4.3B active parameters. It transcribes 40 languages, adds speaker labels and word timestamps, and posts a 4.71% mean WER on the English Open ASR Leaderboard. The post NVIDIA Releases Nemotron 3.5 Transcribe: An Open 30B MoE Model for 40-Language…
Nvidia just released a free speech-to-text model that can transcribe up to 40 languages, but it only works on recordings, not live audio, so it’s a big step for meeting and medical transcription tools while still leaving real-time use to rivals like ElevenLabs.
