← Back to all news
arXiv Machine Learning By Jiajun He, Zongyu Guo, Jos\'e Miguel Hern\'andez-Lobato, Yuanqi Du

Recipes for Steering and Scaling LLMs via Sampling

Read the original on arXiv Machine Learning →

The paper introduces a flexible, theoretically grounded framework for steering and scaling autoregressive large language models (LLMs) through sampling. It presents two algorithms—Sequential Monte Carlo (SMC) and Replica Exchange (RE)—that guide generation toward desired distributions such as powering, product, or tilting of the base model. Experiments show these methods outperform Best‑of‑N and standard MCMC baselines, offering a systematic recipe for probabilistic inference with LLMs via sampling.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Aug 4

The Illusion of Stochasticity in LLMs

arXiv:2604. 06543v2 Announce Type: replace-cross Abstract: In this work, we demonstrate that reliable stochastic sampling is a fundamental yet unfulfilled requirement for Large Language Models (LLMs) operating as agents.

By Xiangming Gu, Soham De, Michalis Titsias, Larisa Markeeva, Petar Veli\v{c}kovi\'c, Razvan Pascanu
llmsagentsreinforcement-learning
More like this →
arXiv Machine Learning
Jun 18

Structured Inference with Large Language Gibbs

arXiv:2606. 19264v1 Announce Type: new Abstract: The knowledge encoded in large language models (LLMs) can serve as a substrate for structured reasoning over variables describing a complex world, but accessing this knowledge in a probabilistically coherent manner poses a difficult inference problem.

By Sanghyeok Choi, Henry Gouk, Esmeralda S. Whitammer
llms
More like this →
arXiv AI
Sep 2

Efficiently Estimating Optimal Hyperparameter Scaling Laws through Power-Law Entropy Search

The paper introduces Power‑Law Entropy Search (PLES), a computational‑cost‑aware acquisition function that uses multi‑fidelity Bayesian optimization to efficiently estimate optimal hyperparameter scaling laws for large language model training. PLES focuses on reducing the overall uncertainty of scaling law estimates rather than optimizing a single objective, selecting configurations that maximize uncertainty reduction per unit computational cost. Experiments on synthetic benchmarks, surrogate models, and real LLM pre‑training runs show that PLES converges to accurate scaling laws using less than one‑tenth of the computational budget required by conventional grid search and other baselines.

By Zhiliang Chen, Sebastian Ament, David Eriksson, Maximilian Balandat, Eytan Bakshy, Jihao Andreas Lin
llmsbenchmarks
More like this →
arXiv Machine Learning
Aug 11

On the Effect of Sampling Diversity in Scaling LLM Inference

arXiv:2502. 11027v5 Announce Type: replace Abstract: Large language model (LLM) scaling inference is key to unlocking greater performance, and leveraging diversity has proven an effective way to enhance it.

By Tianchun Wang, Zichuan Liu, Yuanzhou Chen, Jonathan Light, Weiyang Liu, Haifeng Chen, Xiang Zhang, Wei Cheng
llms
More like this →