arXiv AI
Semantic Flow Regularization: Teaching LLMs to Generate Diverse Yet Coherent Responses
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 25
ConvergeFlow: Language Flow with Provable Convergence to Token Embeddings
arXiv:2608.23551v1 Announce Type: cross Abstract: Recent advances in continuous diffusion and flow-based language models (LMs) have achieved performance competitive with discrete LMs. However, existi...
arXiv Machine Learning
Jun 19
The Significance of Style Diversity in Annotation-Free Synthetic Data Generation
arXiv:2606. 20400v1 Announce Type: new Abstract: Generating high-utility synthetic data for intent classification typically requires human-annotated seed data, which is often unavailable in fast-paced industrial settings.
arXiv Machine Learning
Jul 7
LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure
arXiv:2607. 04733v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) is the standard approach for adapting pretrained language models to downstream domains, yet it often improves target-domain behavior at the cost of degrading pre-existing capabilities.
Hugging Face Trending Papers
Jul 6
LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure
Supervised fine-tuning (SFT) is the standard approach for adapting pretrained language models to downstream domains, yet it often improves target-domain behavior at the cost of degrading pre-existing capabilities. Standard cross-entropy fine-tuning promotes only the observed label token and leaves unconstrained how probability mass is redistributed over other plausible alternatives, potentially distorting the rich local preference structure learned during pretraining.
arXiv AI
Jun 18
Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors
arXiv:2606. 19325v1 Announce Type: cross Abstract: Existing multi-speaker dialogue systems bind speakers to utterances through structured supervision: per-turn tags, multi-stream transcriptions, or learnable speaker embeddings.
arXiv Machine Learning
Aug 3
PTP: Previous-Token Prediction based LLM Inversion for Near-Exact Prompt Reconstruction
arXiv:2607. 29378v1 Announce Type: cross Abstract: Large language models (LLMs) generate text by auto-regressively sampling the next token.