Sequential Monte Carlo sampling from a reward-augmented sequence distribution improves LLM performance on HumanEval by up to 54.9% and MATH500 by up to 8.8%, outperforming standard sampling and GRPO.
Fast controlled generation from language models with adaptive weighted rejection sampling
3 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
3
Pith papers citing it
1
external citations · external index
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Humans produce language more like greedy local choices than globally optimal planning when vocabulary is tightly constrained, with skilled speakers showing more revision.
Quantized open-weight LMs on consumer hardware match closed-source API accuracy for LM-enhanced relational operators while delivering 390x lower cost and 3.8x lower latency in the BlendSQL framework.
citing papers explorer
-
Sampling for Quality: Training-Free Reward-Guided LLM Decoding via Sequential Monte Carlo
Sequential Monte Carlo sampling from a reward-augmented sequence distribution improves LLM performance on HumanEval by up to 54.9% and MATH500 by up to 8.8%, outperforming standard sampling and GRPO.
-
Greedy or not, here I come: Language production under vocabulary constraints in humans and resource-rational models
Humans produce language more like greedy local choices than globally optimal planning when vocabulary is tightly constrained, with skilled speakers showing more revision.
-
Large Databases Need Small, Open-Weight Language Models
Quantized open-weight LMs on consumer hardware match closed-source API accuracy for LM-enhanced relational operators while delivering 390x lower cost and 3.8x lower latency in the BlendSQL framework.