Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

• URL: http://arxiv.org/abs/2408.03314v1
• Date: Tue, 6 Aug 2024 17:35:05 GMT
• Title: Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
• Authors: Charlie Snell, Jaehoon Lee, Kelvin Xu, Aviral Kumar,
• Abstract summary: We study the scaling of inference-time computation in LLMs. We find that in both cases, the effectiveness of different approaches to scaling test-time compute critically varies depending on the difficulty of the prompt.
• Score: 27.656263126925815
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Enabling LLMs to improve their outputs by using more test-time computation is a critical step towards building generally self-improving agents that can operate on open-ended natural language. In this paper, we study the scaling of inference-time computation in LLMs, with a focus on answering the question: if an LLM is allowed to use a fixed but non-trivial amount of inference-time compute, how much can it improve its performance on a challenging prompt? Answering this question has implications not only on the achievable performance of LLMs, but also on the future of LLM pretraining and how one should tradeoff inference-time and pre-training compute. Despite its importance, little research attempted to understand the scaling behaviors of various test-time inference methods. Moreover, current work largely provides negative results for a number of these strategies. In this work, we analyze two primary mechanisms to scale test-time computation: (1) searching against dense, process-based verifier reward models; and (2) updating the model's distribution over a response adaptively, given the prompt at test time. We find that in both cases, the effectiveness of different approaches to scaling test-time compute critically varies depending on the difficulty of the prompt. This observation motivates applying a "compute-optimal" scaling strategy, which acts to most effectively allocate test-time compute adaptively per prompt. Using this compute-optimal strategy, we can improve the efficiency of test-time compute scaling by more than 4x compared to a best-of-N baseline. Additionally, in a FLOPs-matched evaluation, we find that on problems where a smaller base model attains somewhat non-trivial success rates, test-time compute can be used to outperform a 14x larger model.

Related papers

• Rational Metareasoning for Large Language Models [5.5539136805232205]
  Being prompted to engage in reasoning has emerged as a core technique for using large language models (LLMs) This work introduces a novel approach based on computational models of metareasoning used in cognitive science. We develop a reward function that incorporates the Value of Computation by penalizing unnecessary reasoning.
  arXiv  Detail & Related papers  (2024-10-07T23:48:52Z)
• Inference Scaling for Long-Context Retrieval Augmented Generation [37.15479223789199]
  In this work, we investigate inference scaling for retrieval augmented generation (RAG) We focus on two inference scaling strategies: in-context learning and iterative prompting. We demonstrate that scaling inference compute on long-context large language models achieves up to 58.9% gains on benchmark datasets.
  arXiv  Detail & Related papers  (2024-10-06T03:42:15Z)
• MindStar: Enhancing Math Reasoning in Pre-trained LLMs at Inference Time [51.5039731721706]
  MindStar is a purely inference-based searching method for large language models. It formulates reasoning tasks as searching problems and proposes two search ideas to identify the optimal reasoning paths. It significantly enhances the reasoning abilities of open-source models, such as Llama-2-13B and Mistral-7B, and achieves comparable performance to GPT-3.5 and Grok-1.
  arXiv  Detail & Related papers  (2024-05-25T15:07:33Z)
• Online Cascade Learning for Efficient Inference over Streams [9.516197133796437]
  Large Language Models (LLMs) have a natural role in answering complex queries about data streams. We propose online cascade learning, the first approach to address this challenge. We formulate the task of learning cascades online as an imitation-learning problem.
  arXiv  Detail & Related papers  (2024-02-07T01:46:50Z)
• Benchmarking Causal Study to Interpret Large Language Models for Source Code [6.301373791541809]
  This paper introduces a benchmarking strategy named Galeras comprised of curated testbeds for three SE tasks. We illustrate the insights of our benchmarking strategy by conducting a case study on the performance of ChatGPT under distinct prompt engineering methods.
  arXiv  Detail & Related papers  (2023-08-23T20:32:12Z)
• Leaving the Nest: Going Beyond Local Loss Functions for Predict-Then-Optimize [57.22851616806617]
  We show that our method achieves state-of-the-art results in four domains from the literature. Our approach outperforms the best existing method by nearly 200% when the localness assumption is broken.
  arXiv  Detail & Related papers  (2023-05-26T11:17:45Z)
• SatLM: Satisfiability-Aided Language Models Using Declarative Prompting [68.40726892904286]
  We propose a new satisfiability-aided language modeling (SatLM) approach for improving the reasoning capabilities of large language models (LLMs) We use an LLM to generate a declarative task specification rather than an imperative program and leverage an off-the-shelf automated theorem prover to derive the final answer. We evaluate SATLM on 8 different datasets and show that it consistently outperforms program-aided LMs in the imperative paradigm.
  arXiv  Detail & Related papers  (2023-05-16T17:55:51Z)
• Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL [106.82295532402335]
  Existing reinforcement learning algorithms suffer from computational intractability, strong statistical assumptions, and suboptimal sample complexity. We provide the first computationally efficient algorithm that attains rate-optimal sample complexity with respect to the desired accuracy level. Our algorithm, MusIK, combines systematic exploration with representation learning based on multi-step inverse kinematics.
  arXiv  Detail & Related papers  (2023-04-12T14:51:47Z)
• M-L2O: Towards Generalizable Learning-to-Optimize by Test-Time Fast Self-Adaptation [145.7321032755538]
  Learning to Optimize (L2O) has drawn increasing attention as it often remarkably accelerates the optimization procedure of complex tasks. This paper investigates a potential solution to this open challenge by meta-training an L2O that can perform fast test-time self-adaptation to an out-of-distribution task.
  arXiv  Detail & Related papers  (2023-02-28T19:23:20Z)
• Confident Adaptive Language Modeling [95.45272377648773]
  CALM is a framework for dynamically allocating different amounts of compute per input and generation timestep. We demonstrate the efficacy of our framework in reducing compute -- potential speedup of up to $times 3$ -- while provably maintaining high performance.
  arXiv  Detail & Related papers  (2022-07-14T17:00:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.