Soft Reasoning improves LLM accuracy on reasoning benchmarks by perturbing the embedding of the first generated token and searching the perturbation space with Bayesian optimization guided by the model's own verifier.
There are 1000 ml in 1 liter, so 0.4 liters is 0.4×1000 =⟨⟨0.4×1000 = 400⟩⟩400ml
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration
Soft Reasoning improves LLM accuracy on reasoning benchmarks by perturbing the embedding of the first generated token and searching the perturbation space with Bayesian optimization guided by the model's own verifier.