Causal full-duplex speech LLMs improve response quality by recursively feeding soft vocabulary embeddings as latent thoughts during listening, trained by matching a non-causal expert posterior via ELBO.
Distributional reasoning in llms: Parallel reasoning processes in multi- hop reasoning.arXiv preprint arXiv:2406.13858
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
Coconut lets LLMs perform reasoning directly in continuous latent space by recycling hidden states as inputs, outperforming standard chain-of-thought on search-intensive logical tasks with better accuracy-efficiency trade-offs.
SeLaR selectively applies latent soft reasoning in LLMs via entropy gating and contrastive regularization, outperforming standard CoT on five benchmarks without training.
LLMs solve compositional factual recall either by computing intermediates or directly, with mechanism choice correlated to translation geometry in embedding spaces.
ULPS integrates A*-generated symbolic trajectories, fine-tuned BERT priors, MC dropout uncertainty, and entropy-based blending into PPO, reporting over 9% accuracy gains and better sample efficiency on the MiniGridUnlockPickup benchmark.
citing papers explorer
-
The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning
Causal full-duplex speech LLMs improve response quality by recursively feeding soft vocabulary embeddings as latent thoughts during listening, trained by matching a non-causal expert posterior via ELBO.
-
Training Large Language Models to Reason in a Continuous Latent Space
Coconut lets LLMs perform reasoning directly in continuous latent space by recycling hidden states as inputs, outperforming standard chain-of-thought on search-intensive logical tasks with better accuracy-efficiency trade-offs.
-
SeLaR: Selective Latent Reasoning in Large Language Models
SeLaR selectively applies latent soft reasoning in LLMs via entropy gating and contrastive regularization, outperforming standard CoT on five benchmarks without training.
-
How Do Language Models Compose Functions?
LLMs solve compositional factual recall either by computing intermediates or directly, with mechanism choice correlated to translation geometry in embedding spaces.
-
Uncertainty-Aware LLM-Guided Policy Shaping for Sparse-Reward Reinforcement Learning
ULPS integrates A*-generated symbolic trajectories, fine-tuned BERT priors, MC dropout uncertainty, and entropy-based blending into PPO, reporting over 9% accuracy gains and better sample efficiency on the MiniGridUnlockPickup benchmark.