Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:Z6ELNVS6record.jsonopen to challenge →
read the original abstract
Large language models (LLMs) have achieved significant performance gains via scaling up model sizes and/or data. However, recent evidence suggests diminishing returns from such approaches, motivating scaling the computation spent at inference time. Existing inference-time scaling methods, usually with reward models, cast the task as a search problem, which tends to be vulnerable to reward hacking as a consequence of approximation errors in reward models. In this paper, we instead cast inference-time scaling as a probabilistic inference task and leverage sampling-based techniques to explore the typical set of the state distribution of a state-space model with an approximate likelihood, rather than optimize for its mode directly. We propose a novel inference-time scaling approach by adapting particle-based Monte Carlo methods to this task. Our empirical evaluation demonstrates that our methods have a 4-16x better scaling rate over our deterministic search counterparts on various challenging mathematical reasoning tasks. Using our approach, we show that Qwen2.5-Math-1.5B-Instruct can surpass GPT-4o accuracy in only 4 rollouts, while Qwen2.5-Math-7B-Instruct scales to o1 level accuracy in only 32 rollouts. Our work not only presents an effective method to inference-time scaling, but also connects the rich literature in probabilistic inference with inference-time scaling of LLMs to develop more robust algorithms in future work. Code, videos, and further information available at https://probabilistic-inference-scaling.github.io.
This paper has not been read by Pith yet.
Forward citations
Cited by 5 Pith papers
-
The Power of Test-Time Training for Approximate Sampling
Establishes a quadratic lower bound on query complexity for sampling from large classes of distributions given approximate density oracles, answers an open question on optimality of random walks, and shows circumventi...
-
ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling
ToolPRM provides fine-grained intra-call process supervision via a new dataset and reward model, outperforming outcome and coarse-grained alternatives on function-calling benchmarks.
-
Inference-Time Scaling of Diffusion Language Models via Trajectory Refinement
PG-DLM applies particle Gibbs sampling over full trajectories in diffusion language models to enable iterative refinement, yielding higher accuracy on reward-guided generation with theoretical convergence guarantees.
-
TreeCoder: Systematic Exploration and Optimisation of Decoding and Constraints for LLM Code Generation
TreeCoder improves LLM code generation accuracy by representing decoding as an optimizable tree search over programs with first-class constraints for syntax, style, and execution, outperforming baselines on MBPP and S...
-
TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning
TokUR estimates token-level uncertainty via low-rank weight perturbations in LLMs, aggregates signals to correlate with correctness, and uses them to improve reasoning performance on math tasks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.