Mining Intrinsic Rewards from LLM Hidden States for Efficient Best-of-N Sampling

• URL: http://arxiv.org/abs/2505.12225v2
• Date: Tue, 29 Jul 2025 01:42:42 GMT
• Title: Mining Intrinsic Rewards from LLM Hidden States for Efficient Best-of-N Sampling
• Authors: Jizhou Guo, Zhaomin Wu, Hanchen Yang, Philip S. Yu,
• Abstract summary: We introduce SWIFT, a novel, lightweight technique for improving Large Language Model (LLM) performance.<n>We show that SWIFT outperforms baselines with less than 0.005% of the parameters of baselines, requiring only a few samples for training.<n> SWIFT's robustness, applicability to some closed-source models via logits, and ability to be combined with traditional reward models underscore its practical value.
• Score: 34.69646110042311
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Enhancing Large Language Model (LLM)'s performance with best-of-N sampling is effective and has attracted significant attention. However, it is computationally prohibitive due to massive, data-hungry text-based reward models. By changing the data source from text to hidden states, we introduce SWIFT (Simple Weighted Intrinsic Feedback Technique), a novel, lightweight technique that leverages the rich information embedded in LLM hidden states to address these issues, which operates on token-level and consists of only linear layers. Extensive experiments show that SWIFT outperforms baselines with less than 0.005% of the parameters of baselines, requiring only a few samples for training, demonstrating significant efficiency improvement. SWIFT's robust scalability, applicability to some closed-source models via logits, and ability to be combined with traditional reward models to yield further performance gains underscore its practical value.

Related papers

• InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities [27.09178257629886]
  InfiAlign is a scalable and sample-efficient post-training framework for large language models (LLMs)<n>At the core of InfiAlign is a robust data selection pipeline that automatically curates high-quality alignment data from open-source reasoning.<n>Our results highlight the effectiveness of combining principled data selection with full-stage post-training.
  arXiv  Detail & Related papers  (2025-08-07T15:34:06Z)
• SPaRFT: Self-Paced Reinforcement Fine-Tuning for Large Language Models [51.74498855100541]
  Large language models (LLMs) have shown strong reasoning capabilities when fine-tuned with reinforcement learning (RL)<n>We propose textbfSPaRFT, a self-paced learning framework that enables efficient learning based on the capability of the model being trained.
  arXiv  Detail & Related papers  (2025-08-07T03:50:48Z)
• FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain [14.109309236798518]
  Supervised fine-tuning (SFT) is a standard approach to adapting large language models (LLMs) to new domains.<n>In this work, we improve the statistical efficiency of SFT by selecting an informative subset of training examples.
  arXiv  Detail & Related papers  (2025-05-20T18:41:34Z)
• 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)
• Refining Salience-Aware Sparse Fine-Tuning Strategies for Language Models [14.68920095399595]
  sparsity-based PEFT (SPEFT) introduces trainable sparse adaptations to the weight matrices in the model.<n>We conduct the first systematic evaluation of salience metrics for SPEFT, inspired by zero-cost NAS proxies.<n>We compare static and dynamic masking strategies, finding that static masking, which predetermines non-zero entries before training, delivers efficiency without sacrificing performance.
  arXiv  Detail & Related papers  (2024-12-18T04:14:35Z)
• Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models [79.41139393080736]
  Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and. Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting. LLMs to downstream tasks. We propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning.
  arXiv  Detail & Related papers  (2024-09-30T10:48:20Z)
• Efficient Hybrid Inference for LLMs: Reward-Based Token Modelling with Selective Cloud Assistance [0.0]
  Large language models (LLMs) are known for their exceptional performance across a range of natural language processing tasks. Smaller language models (SLMs), which can be deployed on lower-cost edge devices, struggle to match the performance of their larger counterparts. This paper presents a novel hybrid inference approach that leverages the strengths of both model types.
  arXiv  Detail & Related papers  (2024-09-15T15:12:45Z)
• Large Visual-Language Models Are Also Good Classifiers: A Study of In-Context Multimodal Fake News Detection [0.18416014644193068]
  This paper first assesses the FND capabilities of two notable LVLMs, CogVLM and GPT4V, in comparison to a smaller yet adeptly trained CLIP model in a zero-shot context.<n>Next, we integrate standard in-context learning (ICL) with LVLMs, noting improvements in FND performance, though limited in scope and consistency.<n>We introduce the textbfIn-context textbfMultimodal textbfFake textbfNews textbfD
  arXiv  Detail & Related papers  (2024-07-16T09:28:23Z)
• ITERTL: An Iterative Framework for Fine-tuning LLMs for RTL Code Generation [9.409062607311528]
  Large language models (LLMs) have demonstrated excellent performance, inspiring researchers to explore their use in automating register transfer level (RTL) code generation.<n>Existing approaches to fine-tune LLMs for RTL generation typically are conducted on fixed datasets.<n>We introduce an iterative training paradigm named ITERTL to mitigate these issues.<n>Our model outperforms GPT4 and state-of-the-art (SOTA) open-source models, achieving remarkable 53.8% pass@1 rate on VerilogEval-human benchmark.
  arXiv  Detail & Related papers  (2024-06-28T01:44:57Z)
• Self-Exploring Language Models: Active Preference Elicitation for Online Alignment [88.56809269990625]
  We propose a bilevel objective optimistically biased towards potentially high-reward responses to actively explore out-of-distribution regions. Our experimental results demonstrate that when fine-tuned on Zephyr-7B-SFT and Llama-3-8B-Instruct models, Self-Exploring Language Models (SELM) significantly boosts the performance on instruction-following benchmarks.
  arXiv  Detail & Related papers  (2024-05-29T17:59:07Z)
• SLMRec: Distilling Large Language Models into Small for Sequential Recommendation [38.51895517016953]
  Sequential Recommendation task involves predicting the next item a user is likely to interact with, given their past interactions.<n>Recent research demonstrates the great impact of LLMs on sequential recommendation systems.<n>Due to the huge size of LLMs, it is inefficient and impractical to apply a LLM-based model in real-world platforms.
  arXiv  Detail & Related papers  (2024-05-28T07:12:06Z)
• GPTA: Generative Prompt Tuning Assistant for Synergistic Downstream Neural Network Enhancement with LLMs [11.572835837392867]
  This study introduces GPTA, a Large Language Model assistance training framework, that enhances the training of downstream task models via prefix prompt. By minimizing data exposure to LLM, the framework addresses the security and legal challenges of applying LLM in downstream task model training.
  arXiv  Detail & Related papers  (2024-03-29T23:04:04Z)
• SMART: Automatically Scaling Down Language Models with Accuracy Guarantees for Reduced Processing Fees [21.801053526411415]
  Large Language Models (LLMs) have significantly boosted performance in natural language processing (NLP) tasks. The deployment of high-performance LLMs incurs substantial costs, primarily due to the increased number of parameters aimed at enhancing model performance. We introduce SMART, a novel framework designed to minimize the inference costs of NLP tasks while ensuring sufficient result quality.
  arXiv  Detail & Related papers  (2024-03-11T17:45:47Z)
• An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models [55.01592097059969]
  Supervised finetuning on instruction datasets has played a crucial role in achieving the remarkable zero-shot generalization capabilities. Active learning is effective in identifying useful subsets of samples to annotate from an unlabeled pool. We propose using experimental design to circumvent the computational bottlenecks of active learning.
  arXiv  Detail & Related papers  (2024-01-12T16:56:54Z)
• Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models [52.98743860365194]
  We propose a new fine-tuning method called Self-Play fIne-tuNing (SPIN) At the heart of SPIN lies a self-play mechanism, where the LLM refines its capability by playing against instances of itself. This sheds light on the promise of self-play, enabling the achievement of human-level performance in LLMs without the need for expert opponents.
  arXiv  Detail & Related papers  (2024-01-02T18:53:13Z)
• Retrieval-based Knowledge Transfer: An Effective Approach for Extreme Large Language Model Compression [64.07696663255155]
  Large-scale pre-trained language models (LLMs) have demonstrated exceptional performance in various natural language processing (NLP) tasks. However, the massive size of these models poses huge challenges for their deployment in real-world applications. We introduce a novel compression paradigm called Retrieval-based Knowledge Transfer (RetriKT) which effectively transfers the knowledge of LLMs to extremely small-scale models.
  arXiv  Detail & Related papers  (2023-10-24T07:58:20Z)
• Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding [38.11411155621616]
  We study self-training as one of the predominant semi-supervised learning approaches. We present UPET, a novel Uncertainty-aware self-Training framework. We show that UPET achieves a substantial improvement in terms of performance and efficiency.
  arXiv  Detail & Related papers  (2023-10-19T02:18:29Z)
• Simultaneous Machine Translation with Large Language Models [51.470478122113356]
  We investigate the possibility of applying Large Language Models to SimulMT tasks. We conducted experiments using the textttLlama2-7b-chat model on nine different languages from the MUST-C dataset. The results show that LLM outperforms dedicated MT models in terms of BLEU and LAAL metrics.
  arXiv  Detail & Related papers  (2023-09-13T04:06:47Z)
• Scaling Relationship on Learning Mathematical Reasoning with Large Language Models [75.29595679428105]
  We investigate how the pre-training loss, supervised data amount, and augmented data amount influence the reasoning performances of a supervised LLM. We find that rejection samples from multiple models push LLaMA-7B to an accuracy of 49.3% on GSM8K which outperforms the supervised fine-tuning (SFT) accuracy of 35.9% significantly.
  arXiv  Detail & Related papers  (2023-08-03T15:34:01Z)

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.