Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

• URL: http://arxiv.org/abs/2502.06703v1
• Date: Mon, 10 Feb 2025 17:30:23 GMT
• Title: Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
• Authors: Runze Liu, Junqi Gao, Jian Zhao, Kaiyan Zhang, Xiu Li, Biqing Qi, Wanli Ouyang, Bowen Zhou,
• Abstract summary: Test-Time Scaling is an important method for improving the performance of Large Language Models. This paper focuses on two core questions: What is the optimal approach to scale test-time computation across different policy models, PRMs, and problem difficulty levels? We show that with our compute-optimal TTS strategy, extremely small policy models can outperform larger models.
• Score: 69.57918638435491
• License:
• Abstract: Test-Time Scaling (TTS) is an important method for improving the performance of Large Language Models (LLMs) by using additional computation during the inference phase. However, current studies do not systematically analyze how policy models, Process Reward Models (PRMs), and problem difficulty influence TTS. This lack of analysis limits the understanding and practical use of TTS methods. In this paper, we focus on two core questions: (1) What is the optimal approach to scale test-time computation across different policy models, PRMs, and problem difficulty levels? (2) To what extent can extended computation improve the performance of LLMs on complex tasks, and can smaller language models outperform larger ones through this approach? Through comprehensive experiments on MATH-500 and challenging AIME24 tasks, we have the following observations: (1) The compute-optimal TTS strategy is highly dependent on the choice of policy model, PRM, and problem difficulty. (2) With our compute-optimal TTS strategy, extremely small policy models can outperform larger models. For example, a 1B LLM can exceed a 405B LLM on MATH-500. Moreover, on both MATH-500 and AIME24, a 0.5B LLM outperforms GPT-4o, a 3B LLM surpasses a 405B LLM, and a 7B LLM beats o1 and DeepSeek-R1, while with higher inference efficiency. These findings show the significance of adapting TTS strategies to the specific characteristics of each task and model and indicate that TTS is a promising approach for enhancing the reasoning abilities of LLMs.

Related papers

• Teaching LLMs According to Their Aptitude: Adaptive Reasoning for Mathematical Problem Solving [55.895917967408586]
  Existing approaches to mathematical reasoning with large language models rely on Chain-of-Thought (CoT) for generalizability or Tool-Integrated Reasoning (TIR) for precise computation. We propose TATA (Teaching LLMs According to Their Aptitude), an adaptive framework that enables LLMs to personalize their reasoning strategy spontaneously.
  arXiv  Detail & Related papers  (2025-02-17T16:56:23Z)
• Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling [52.34735382627312]
  Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. Existing approaches mainly rely on imitation learning and struggle to achieve effective test-time scaling. We present T1 to scale reinforcement learning by encouraging exploration and understand inference scaling.
  arXiv  Detail & Related papers  (2025-01-20T18:33:33Z)
• A Comprehensive Evaluation of Quantized Instruction-Tuned Large Language Models: An Experimental Analysis up to 405B [11.832907585157638]
  This paper evaluates the performance of instruction-tuned LLMs on models ranging from 7B to 405B. We assess performance across six task types: commonsense Q&A, knowledge and language understanding, instruction following, hallucination detection, mathematics, and dialogue.
  arXiv  Detail & Related papers  (2024-09-17T10:31:37Z)
• 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)
• TAT-LLM: A Specialized Language Model for Discrete Reasoning over Tabular and Textual Data [73.29220562541204]
  We consider harnessing the amazing power of language models (LLMs) to solve our task. We develop a TAT-LLM language model by fine-tuning LLaMA 2 with the training data generated automatically from existing expert-annotated datasets.
  arXiv  Detail & Related papers  (2024-01-24T04:28:50Z)
• Scaling Sentence Embeddings with Large Language Models [43.19994568210206]
  In this work, we propose an in-context learning-based method aimed at improving sentence embeddings performance. Our approach involves adapting the previous prompt-based representation method for autoregressive models. By scaling model size, we find scaling to more than tens of billion parameters harms the performance on semantic textual similarity tasks.
  arXiv  Detail & Related papers  (2023-07-31T13:26:03Z)
• TART: A plug-and-play Transformer module for task-agnostic reasoning [38.84903599406189]
  Large language models (LLMs) exhibit in-context learning abilities which enable the same model to perform several tasks without any task-specific training. Traditional adaptation approaches, such as fine-tuning, modify the underlying models for each specific task. We propose TART which generically improves an LLM's reasoning abilities using a synthetically trained Transformer-based reasoning module.
  arXiv  Detail & Related papers  (2023-06-13T04:37:00Z)
• 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)

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.