Spectral Logit Sculpting: Adaptive Low-Rank Logit Transformation for Controlled Text Generation

• URL: http://arxiv.org/abs/2509.25204v1
• Date: Fri, 19 Sep 2025 04:17:46 GMT
• Title: Spectral Logit Sculpting: Adaptive Low-Rank Logit Transformation for Controlled Text Generation
• Authors: Jin Li, Zhebo Wang, Tianliang Lu, Mohan Li, Wenpeng Xing, Meng Han,
• Abstract summary: Entropy-based inference methods have gained traction for improving the reliability of Large Language Models (LLMs)<n>We propose Spectral Logit Sculpting (SLS), a lightweight inference-time optimization method that dynamically modulates token distributions using spectral and entropic properties of recent logits.<n>SLS consistently outperforms existing baseline methods, achieving superior accuracy in mathematical, coding, and scientific reasoning tasks.
• Score: 21.76979685109612
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Entropy-based inference methods have gained traction for improving the reliability of Large Language Models (LLMs). However, many existing approaches, such as entropy minimization techniques, suffer from high computational overhead and fail to leverage historical token context effectively. To address these limitations, we propose Spectral Logit Sculpting (SLS), a lightweight inference-time optimization method that dynamically modulates token distributions using spectral and entropic properties of recent logits. SLS maintains a sliding buffer of top-K logits, performs on-the-fly Singular Value Decomposition (SVD) to identify dominant spectral directions, and adaptively rescales logits based on both entropy and logit gap statistics--only activating when uncertainty is high. Without updating any model parameters, SLS effectively sharpens the output distribution while preserving contextual consistency. Experimental results on multiple public benchmarks demonstrate that SLS consistently outperforms existing baseline methods, achieving superior accuracy in mathematical, coding, and scientific reasoning tasks.

Related papers

• Benchmarking Few-shot Transferability of Pre-trained Models with Improved Evaluation Protocols [123.73663884421272]
  Few-shot transfer has been revolutionized by stronger pre-trained models and improved adaptation algorithms.<n>We establish FEWTRANS, a comprehensive benchmark containing 10 diverse datasets.<n>By releasing FEWTRANS, we aim to provide a rigorous "ruler" to streamline reproducible advances in few-shot transfer learning research.
  arXiv  Detail & Related papers  (2026-02-28T05:41:57Z)
• SPRINT: Stochastic Performative Prediction With Variance Reduction [18.735898645810405]
  Performative prediction (PP) is an algorithmic framework for machine learning (ML) models where the model's deployment affects the distribution of the data it is trained on.<n>We propose a new algorithm called performative prediction with gradient reduction (SSPS) Experiments.
  arXiv  Detail & Related papers  (2025-09-22T00:56:17Z)
• Inference-Time Scaling of Diffusion Language Models with Particle Gibbs Sampling [70.8832906871441]
  We study how to steer generation toward desired rewards without retraining the models.<n>Prior methods typically resample or filter within a single denoising trajectory, optimizing rewards step-by-step without trajectory-level refinement.<n>We introduce particle Gibbs sampling for diffusion language models (PG-DLM), a novel inference-time algorithm enabling trajectory-level refinement while preserving generation perplexity.
  arXiv  Detail & Related papers  (2025-07-11T08:00:47Z)
• 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)
• Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space [92.6187727249868]
  We introduce LatentSeek, a framework that enhances reasoning through Test-Time Instance-level Adaptation (TTIA) within the model's latent space.<n>LatentSeek is evaluated on a range of reasoning benchmarks, including GSM8K, MATH-500, and AIME2024.<n>Results show that LatentSeek consistently outperforms strong baselines.
  arXiv  Detail & Related papers  (2025-05-19T16:26:02Z)
• RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models [53.571195477043496]
  We propose an algorithm named Rotated Straight-Through-Estimator (RoSTE)<n>RoSTE combines quantization-aware supervised fine-tuning (QA-SFT) with an adaptive rotation strategy to reduce activation outliers.<n>Our findings reveal that the prediction error is directly proportional to the quantization error of the converged weights, which can be effectively managed through an optimized rotation configuration.
  arXiv  Detail & Related papers  (2025-02-13T06:44:33Z)
• Transformer-Driven Active Transfer Learning for Cross-Hyperspectral Image Classification [3.087068801861429]
  Hyperspectral image (HSI) classification presents inherent challenges due to high spectral dimensionality, significant domain shifts, and limited availability of labeled data.<n>We propose a novel Active Transfer Learning (ATL) framework built upon a Spatial-Spectral Transformer (SST) backbone.<n>The framework integrates multistage transfer learning with an uncertainty-diversity-driven active learning mechanism.
  arXiv  Detail & Related papers  (2024-11-27T07:53:39Z)
• Zeroth-Order Fine-Tuning of LLMs in Random Subspaces [63.10833446782114]
  As language models grow in size, memory demands for backpropagation increase.<n>Zeroth-order (ZO) optimization methods offer a memory-efficient alternative.<n>In this paper, we propose Subspace Zero-order optimization to address the challenges posed by posed by high dimensionality perturbations.
  arXiv  Detail & Related papers  (2024-10-11T17:01:43Z)
• Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures [21.18741772731095]
  Zeroth-order (ZO) algorithms offer a promising alternative by approximating gradients using finite differences of function values. Existing ZO methods struggle to capture the low-rank gradient structure common in LLM fine-tuning, leading to suboptimal performance. This paper proposes a low-rank ZO algorithm (LOZO) that effectively captures this structure in LLMs.
  arXiv  Detail & Related papers  (2024-10-10T08:10:53Z)
• Sparse is Enough in Fine-tuning Pre-trained Large Language Models [98.46493578509039]
  We propose a gradient-based sparse fine-tuning algorithm, named Sparse Increment Fine-Tuning (SIFT) We validate its effectiveness on a range of tasks including the GLUE Benchmark and Instruction-tuning.
  arXiv  Detail & Related papers  (2023-12-19T06:06:30Z)
• Locally Interpretable Model Agnostic Explanations using Gaussian Processes [2.9189409618561966]
  Local Interpretable Model-Agnostic Explanations (LIME) is a popular technique for explaining the prediction of a single instance. We propose a Gaussian Process (GP) based variation of locally interpretable models. We demonstrate that the proposed technique is able to generate faithful explanations using much fewer samples as compared to LIME.
  arXiv  Detail & Related papers  (2021-08-16T05:49:01Z)
• Fast Distributionally Robust Learning with Variance Reduced Min-Max Optimization [85.84019017587477]
  Distributionally robust supervised learning is emerging as a key paradigm for building reliable machine learning systems for real-world applications. Existing algorithms for solving Wasserstein DRSL involve solving complex subproblems or fail to make use of gradients. We revisit Wasserstein DRSL through the lens of min-max optimization and derive scalable and efficiently implementable extra-gradient algorithms.
  arXiv  Detail & Related papers  (2021-04-27T16:56:09Z)

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.