Guided by Gut: Efficient Test-Time Scaling with Reinforced Intrinsic Confidence

• URL: http://arxiv.org/abs/2505.20325v1
• Date: Fri, 23 May 2025 18:19:09 GMT
• Title: Guided by Gut: Efficient Test-Time Scaling with Reinforced Intrinsic Confidence
• Authors: Amirhosein Ghasemabadi, Keith G. Mills, Baochun Li, Di Niu,
• Abstract summary: Test-Time Scaling (TTS) methods for enhancing Large Language Model (LLM) reasoning often incur substantial computational costs.<n>This paper introduces Guided by Gut (GG), an efficient self-guided TTS framework that achieves PRM-level performance without costly external verifier models.
• Score: 38.30075427255948
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Test-Time Scaling (TTS) methods for enhancing Large Language Model (LLM) reasoning often incur substantial computational costs, primarily due to extensive reliance on external Process Reward Models (PRMs) or sampling methods like Best-of-N (BoN). This paper introduces Guided by Gut (GG), an efficient self-guided TTS framework that achieves PRM-level performance without costly external verifier models. Our method employs a lightweight tree search guided solely by intrinsic LLM signals, token-level confidence and step novelty. One critical innovation is improving the reliability of internal confidence estimates via a targeted reinforcement learning fine-tuning phase. Empirical evaluations on challenging mathematical reasoning benchmarks demonstrate that GG enables smaller models (e.g., 1.5B parameters) to achieve accuracy matching or surpassing significantly larger models (e.g., 32B-70B parameters), while reducing GPU memory usage by up to 10x. Compared to PRM-based methods, GG achieves comparable accuracy with 8x faster inference speeds and 4-5x lower memory usage. Additionally, GG reduces KV cache memory usage by approximately 50% compared to the BoN strategy, facilitating more efficient and practical deployment of TTS techniques.

Related papers

• Beyond First-Order: Training LLMs with Stochastic Conjugate Subgradients and AdamW [2.028622227373579]
  gradient-based descent (SGD) have long been central to training large language models (LLMs)<n>This paper proposes a conjugate subgradient method together with adaptive sampling specifically for training LLMs.
  arXiv  Detail & Related papers  (2025-07-01T23:30:15Z)
• Kinetics: Rethinking Test-Time Scaling Laws [18.325591438335007]
  Kinetics Scaling Law suggests that test-time compute is more effective when used on models above a threshold than smaller ones.<n>Motivated by this, we propose a new scaling paradigm centered on sparse attention, which lowers per-token cost and enables longer generations and more parallel samples.
  arXiv  Detail & Related papers  (2025-06-05T17:59:24Z)
• Accelerated Test-Time Scaling with Model-Free Speculative Sampling [58.69141724095398]
  We introduce STAND (STochastic Adaptive N-gram Drafting), a novel model-free speculative decoding approach.<n>We show that STAND reduces inference latency by 60-65% compared to standard autoregressive decoding.<n>As a model-free approach, STAND can be applied to any existing language model without additional training.
  arXiv  Detail & Related papers  (2025-06-05T07:31:18Z)
• Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement [22.801244105119025]
  We propose new algorithms to improve token-efficient reasoning with small-scale models by effectively trading off accuracy and computation.<n>We first show that the post-SFT model fails to determine the optimal stopping point of the reasoning process, resulting in verbose and repetitive outputs.<n>Experiments on four reasoning benchmarks, MATH500, AMC, AIME24 and OlympiadBench, demonstrate that TS is highly effective compared to s1's budget forcing approach.
  arXiv  Detail & Related papers  (2025-05-12T18:04:39Z)
• Optimizing Deep Neural Networks using Safety-Guided Self Compression [0.0]
  This study introduces a novel safety-driven quantization framework that prunes and quantizes neural network weights.<n>The proposed methodology is rigorously evaluated on both a convolutional neural network (CNN) and an attention-based language model.<n> Experimental results reveal that our framework achieves up to a 2.5% enhancement in test accuracy relative to the original unquantized models.
  arXiv  Detail & Related papers  (2025-05-01T06:50:30Z)
• START: Self-taught Reasoner with Tools [51.38785489790888]
  We introduce START (Self-Taught Reasoner with Tools), a tool-integrated long Chain-of-thought (CoT) reasoning LLM.<n> START is capable of performing complex computations, self-checking, exploring diverse methods, and self-ging.<n>It significantly outperforms the base QwQ-32B and achieves performance comparable to the state-of-the-art open-weight model R1-Distill-Qwen-32B.
  arXiv  Detail & Related papers  (2025-03-06T17:11:51Z)
• Reward-Guided Speculative Decoding for Efficient LLM Reasoning [80.55186052123196]
  We introduce Reward-Guided Speculative Decoding (RSD), a novel framework aimed at improving the efficiency of inference in large language models (LLMs)<n>RSD incorporates a controlled bias to prioritize high-reward outputs, in contrast to existing speculative decoding methods that enforce strict unbiasedness.<n>RSD delivers significant efficiency gains against decoding with the target model only, while achieving significant better accuracy than parallel decoding method on average.
  arXiv  Detail & Related papers  (2025-01-31T17:19:57Z)
• The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit [46.37267466656765]
  This paper presents an optimization framework that combines Retrieval-Augmented Generation (RAG) with an innovative multi-head early exit architecture.<n>Our experiments demonstrate how this architecture effectively decreases time without sacrificing the accuracy needed for reliable recommendation delivery.
  arXiv  Detail & Related papers  (2025-01-04T03:26:46Z)
• UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation [93.38604803625294]
  We present UncertaintyRAG, a novel approach for long-context Retrieval-Augmented Generation (RAG) We use Signal-to-Noise Ratio (SNR)-based span uncertainty to estimate similarity between text chunks. UncertaintyRAG outperforms baselines by 2.03% on LLaMA-2-7B, achieving state-of-the-art results.
  arXiv  Detail & Related papers  (2024-10-03T17:39:38Z)
• LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning [56.88751562302793]
  Low-rank adaption (LoRA) has emerged to fine-tune large language models (LLMs) LoRAPrune is a new framework that delivers an accurate structured pruned model in a highly memory-efficient manner. LoRAPrune achieves a reduction in perplexity by 4.81 on WikiText2 and 3.46 on PTB, while also decreasing memory usage by 52.6%.
  arXiv  Detail & Related papers  (2023-05-28T15:15:48Z)
• A Simple Fine-tuning Is All You Need: Towards Robust Deep Learning Via Adversarial Fine-tuning [90.44219200633286]
  We propose a simple yet very effective adversarial fine-tuning approach based on a $textitslow start, fast decay$ learning rate scheduling strategy. Experimental results show that the proposed adversarial fine-tuning approach outperforms the state-of-the-art methods on CIFAR-10, CIFAR-100 and ImageNet datasets.
  arXiv  Detail & Related papers  (2020-12-25T20:50:15Z)

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.