Efficiently Scaling LLM Reasoning with Certaindex

• URL: http://arxiv.org/abs/2412.20993v2
• Date: Tue, 27 May 2025 16:41:53 GMT
• Title: Efficiently Scaling LLM Reasoning with Certaindex
• Authors: Yichao Fu, Junda Chen, Siqi Zhu, Zheyu Fu, Zhongdongming Dai, Yonghao Zhuang, Yian Ma, Aurick Qiao, Tajana Rosing, Ion Stoica, Hao Zhang,
• Abstract summary: Test-time reasoning algorithms can wastefully generate many tokens without improving accuracy.<n>We introduce Certaindex, an algorithm-agnostic metric measuring when further computation is unlikely to alter the final result.<n>Certaindex is lightweight, can accelerate reasoning program inference via early exit, and enables dynamic token allocation.
• Score: 25.549811985276488
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Test-time reasoning algorithms such as chain-of-thought, self-consistency, and MCTS enhance LLM problem-solving but can wastefully generate many tokens without improving accuracy. At the same time, we observe that these algorithms exhibit answer stabilization: their intermediate solutions often cease to change after a certain point, and further investment of compute does not change their final answer. To quantify this phenomenon, we introduce Certaindex, an algorithm-agnostic metric measuring this evolving stability, signaling when further computation is unlikely to alter the final result. Certaindex is lightweight, can accelerate reasoning program inference via early exit, and further enables dynamic token allocation, gang scheduling, and many opportunities when integrated with real-world LLM serving systems. To quantify real-world benefits, we built Certaindex as a scheduler into Dynasor, our reasoning-aware LLM serving system, and demonstrate up to 50% compute savings and 3.3x higher throughput in real workloads with no accuracy drop. Our code is available at https://github.com/hao-ai-lab/Dynasor.git

Related papers

• Optimizing LLM Inference: Fluid-Guided Online Scheduling with Memory Constraints [14.341123057506827]
  Large Language Models (LLMs) are indispensable in today's applications, but their inference procedure demands significant computational resources. This paper formulates LLM inference optimization as a multi-stage online scheduling problem. We develop a fluid dynamics approximation to provide a tractable benchmark that guides algorithm design.
  arXiv  Detail & Related papers  (2025-04-15T16:00:21Z)
• Uncertainty-Guided Chain-of-Thought for Code Generation with LLMs [45.33160999781074]
  Chain-of-Thought (CoT) reasoning has been demonstrated as an effective technique for improving the problem-solving capabilities of large language models (LLMs)<n>We introduce UnCert-CoT, an approach designed to enhance code generation by incorporating an uncertainty-aware CoT reasoning mechanism.
  arXiv  Detail & Related papers  (2025-03-19T15:40:45Z)
• DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal [55.13854171147104]
  Large Language Models (LLMs) have revolutionized various domains, including natural language processing, data analysis, and software development. We present Dynamic Action Re-Sampling (DARS), a novel inference time compute scaling approach for coding agents. We evaluate our approach on SWE-Bench Lite benchmark, demonstrating that this scaling strategy achieves a pass@k score of 55% with Claude 3.5 Sonnet V2.
  arXiv  Detail & Related papers  (2025-03-18T14:02:59Z)
• Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning [60.67176246634741]
  We formalize the problem of optimizing test-time compute as a meta-reinforcement learning (RL) problem.<n>We show that state-of-the-art models do not minimize regret, but one can do so by maximizing a dense reward bonus in conjunction with the outcome 0/1 reward RL.
  arXiv  Detail & Related papers  (2025-03-10T17:40:43Z)
• Smart Routing: Cost-Effective Multi-LLM Serving for Multi-Core AIOS [31.60019342381251]
  Existing scheduling frameworks mainly target at latency optimization. This paper proposes an efficient capability-cost coordinated scheduling framework, ECCOS, for multi-LLM serving.
  arXiv  Detail & Related papers  (2025-02-27T22:35:31Z)
• Inference-Time Computations for LLM Reasoning and Planning: A Benchmark and Insights [49.42133807824413]
  We examine the reasoning and planning capabilities of large language models (LLMs) in solving complex tasks. Recent advances in inference-time techniques demonstrate the potential to enhance LLM reasoning without additional training. OpenAI's o1 model shows promising performance through its novel use of multi-step reasoning and verification.
  arXiv  Detail & Related papers  (2025-02-18T04:11:29Z)
• Predicting Emergent Capabilities by Finetuning [98.9684114851891]
  We find that finetuning language models can shift the point in scaling at which emergence occurs towards less capable models. We validate this approach using four standard NLP benchmarks. We find that, in some cases, we can accurately predict whether models trained with up to 4x more compute have emerged.
  arXiv  Detail & Related papers  (2024-11-25T01:48:09Z)
• The Effect of Scheduling and Preemption on the Efficiency of LLM Inference Serving [8.552242818726347]
  INFERMAX is an analytical framework that uses inference cost models to compare various schedulers. Our findings indicate that preempting requests can reduce GPU costs by 30% compared to avoiding preemptions at all.
  arXiv  Detail & Related papers  (2024-11-12T00:10:34Z)
• Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization [50.485788083202124]
  Reinforcement Learning (RL) plays a crucial role in aligning large language models with human preferences and improving their ability to perform complex tasks. We introduce Direct Q-function Optimization (DQO), which formulates the response generation process as a Markov Decision Process (MDP) and utilizes the soft actor-critic (SAC) framework to optimize a Q-function directly parameterized by the language model. Experimental results on two math problem-solving datasets, GSM8K and MATH, demonstrate that DQO outperforms previous methods, establishing it as a promising offline reinforcement learning approach for aligning language models.
  arXiv  Detail & Related papers  (2024-10-11T23:29:20Z)
• Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification [52.095460362197336]
  Large language models (LLMs) struggle with consistent and accurate reasoning. LLMs are trained primarily on correct solutions, reducing their ability to detect and learn from errors. We propose a novel collaborative method integrating Chain-of-Thought (CoT) and Program-of-Thought (PoT) solutions for verification.
  arXiv  Detail & Related papers  (2024-10-05T05:21:48Z)
• Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters [27.656263126925815]
  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.
  arXiv  Detail & Related papers  (2024-08-06T17:35:05Z)
• I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models [20.070306492164427]
  Post-training quantization serves as a potent technique to accelerate the inference of large language models. Existing works still necessitate a considerable number of floating-point (FP) operations during inference. This limitation hinders the deployment of large language models on the edge and cloud devices. We propose I-LLM, a novel integer-only fully-quantized PTQ framework tailored for large language models.
  arXiv  Detail & Related papers  (2024-05-28T05:56:11Z)
• Edge Intelligence Optimization for Large Language Model Inference with Batching and Quantization [20.631476379056892]
  Large Language Models (LLMs) are at the forefront of this movement. LLMs require cloud hosting, which raises issues regarding privacy, latency, and usage limitations. We present an edge intelligence optimization problem tailored for LLM inference.
  arXiv  Detail & Related papers  (2024-05-12T02:38:58Z)
• Switchable Decision: Dynamic Neural Generation Networks [98.61113699324429]
  We propose a switchable decision to accelerate inference by dynamically assigning resources for each data instance. Our method benefits from less cost during inference while keeping the same accuracy.
  arXiv  Detail & Related papers  (2024-05-07T17:44:54Z)
• Can Large Language Models Play Games? A Case Study of A Self-Play Approach [61.15761840203145]
  Large Language Models (LLMs) harness extensive data from the Internet, storing a broad spectrum of prior knowledge. Monte-Carlo Tree Search (MCTS) is a search algorithm that provides reliable decision-making solutions. This work introduces an innovative approach that bolsters LLMs with MCTS self-play to efficiently resolve turn-based zero-sum games.
  arXiv  Detail & Related papers  (2024-03-08T19:16:29Z)
• The Fine-Grained Complexity of Gradient Computation for Training Large Language Models [12.853829771559916]
  Large language models (LLMs) have made fundamental contributions over the last a few years. We show nearly identical results for the harder-seeming problem of computing the gradient of loss function of one layer attention network.
  arXiv  Detail & Related papers  (2024-02-07T00:45:31Z)
• Accelerating Exact Combinatorial Optimization via RL-based Initialization -- A Case Study in Scheduling [1.3053649021965603]
  This research aims to develop an innovative approach that employs machine learning (ML) for addressing optimization problems. We introduce a novel two-phase RL-to-ILP scheduling framework, which includes three steps: 1) solver as coarse-grain scheduler, 2) solution relaxation and 3) exact solving via ILP. Our framework demonstrates the same scheduling performance compared with using exact scheduling methods while achieving up to 128 $times$ speed improvements.
  arXiv  Detail & Related papers  (2023-08-19T15:52:43Z)
• Tree-of-Mixed-Thought: Combining Fast and Slow Thinking for Multi-hop Visual Reasoning [16.495754104540605]
  Large language models (LLMs) can generate code-like plans for complex inference tasks such as visual reasoning. We propose a hierarchical plan-searching algorithm that integrates the one-stop reasoning (fast) and the Tree-of-thought (slow)
  arXiv  Detail & Related papers  (2023-08-18T16:21:40Z)
• GRACE: Discriminator-Guided Chain-of-Thought Reasoning [75.35436025709049]
  We propose Guiding chain-of-thought ReAsoning with a CorrectnEss Discriminator (GRACE) to steer the decoding process towards producing correct reasoning steps. GRACE employs a discriminator trained with a contrastive loss over correct and incorrect steps, which is used during decoding to score next-step candidates.
  arXiv  Detail & Related papers  (2023-05-24T09:16:51Z)
• Learning to Optimize Permutation Flow Shop Scheduling via Graph-based Imitation Learning [70.65666982566655]
  Permutation flow shop scheduling (PFSS) is widely used in manufacturing systems. We propose to train the model via expert-driven imitation learning, which accelerates convergence more stably and accurately. Our model's network parameters are reduced to only 37% of theirs, and the solution gap of our model towards the expert solutions decreases from 6.8% to 1.3% on average.
  arXiv  Detail & Related papers  (2022-10-31T09:46:26Z)
• 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)
• AsySQN: Faster Vertical Federated Learning Algorithms with Better Computation Resource Utilization [159.75564904944707]
  We propose an asynchronous quasi-Newton (AsySQN) framework for vertical federated learning (VFL) The proposed algorithms make descent steps scaled by approximate without calculating the inverse Hessian matrix explicitly. We show that the adopted asynchronous computation can make better use of the computation resource.
  arXiv  Detail & Related papers  (2021-09-26T07:56:10Z)
• Combining Deep Learning and Optimization for Security-Constrained Optimal Power Flow [94.24763814458686]
  Security-constrained optimal power flow (SCOPF) is fundamental in power systems. Modeling of APR within the SCOPF problem results in complex large-scale mixed-integer programs. This paper proposes a novel approach that combines deep learning and robust optimization techniques.
  arXiv  Detail & Related papers  (2020-07-14T12:38:21Z)

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.