LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure

• URL: http://arxiv.org/abs/2607.04733v1
• Date: Mon, 06 Jul 2026 07:14:22 GMT
• Title: LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure
• Abstract summary: Supervised fine-tuning (SFT) is the standard approach for adapting pretrained language models to downstream domains.<n>We propose LP-SFT, a Local-Preserving Supervised Fine-Tuning objective designed to explicitly protect this inherent entropy structure.
• Score: 16.743783987674842
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Supervised fine-tuning (SFT) is the standard approach for adapting pretrained language models to downstream domains, yet it often improves target-domain behavior at the cost of degrading pre-existing capabilities. Standard cross-entropy fine-tuning promotes only the observed label token and leaves unconstrained how probability mass is redistributed over other plausible alternatives, potentially distorting the rich local preference structure learned during pretraining. We first analyze next-token predictions using Shannon and Renyi entropies, revealing that pretrained models exhibit a regular multimodal entropy structure. These entropy peaks correspond to varying numbers of plausible alternatives, indicating that the base model intrinsically encodes rich distributional knowledge beyond the single supervised token. Motivated by this observation, we propose LP-SFT, a Local-Preserving Supervised Fine-Tuning objective designed to explicitly protect this inherent entropy structure. At each step, LP-SFT constructs an adaptive support of alternative tokens and applies a locally normalized preservation loss to maintain the base model's relative structure among them, while standard cross-entropy independently optimizes the supervised token. Across mixed-domain and single-domain fine-tuning experiments, LP-SFT improves overall performance over vanilla SFT and recent SFT-enhancement baselines, achieving the best balance between pass@1 accuracy and pass@k performance. These results suggest that local preservation helps mitigate capability degradation without collapsing sampling-accessible diversity.

Related papers

• Beyond Static Interpretability: Anticipating Post-SFT Mechanisms from Pre-SFT Parameters for Better Tuning [28.24632224083753]
  Mechanistic localization bridges mechanistic interpretability and post-training optimization.<n>We propose a forward-looking framework that accurately estimates the post-SFT interpretability state.
  arXiv  Detail & Related papers  (2026-08-25T12:28:55Z)
• One Step Closer to Ground Truth: A Multi-Scale Residual-Aware Representation Learning Pipeline for Predicting Time Series Data [6.704099492625706]
  We introduce a two-stage, model-agnostic framework that explicitly decouples forecasting and residual learning into distinct stages of representation learning.<n>By formalizing this pipeline as a hypothesis space expansion, our framework addresses approximation limitations inherent in single-stage architectures.
  arXiv  Detail & Related papers  (2026-06-09T10:31:54Z)
• PriFT: Prior-Support Guided Supervised Fine-Tuning [74.65198014829393]
  Supervised fine-tuning (SFT) is an efficient approach for downstream task adaptation.<n>SFT fits fixed demonstrations token by token, including targets poorly aligned with the model's pretrained distribution.<n>We propose PriFT, which derives token weights from a frozen pretrained reference to obtain a stable reweighting signal unaffected by fine-tuning.
  arXiv  Detail & Related papers  (2026-06-08T12:14:06Z)
• Time Series as Language: A Universal Tokenizer for General-Purpose Time Series Foundation Models [58.73838451441261]
  We introduce UniTok, a universal tokenizer that transforms continuous time series (TS) into discrete tokens, and UniTok-FM, a foundation model pretrained via NTP on these tokens.<n>UniTok-FM is a general-purpose foundation model that supports zero-shot and prompt-boosted forecasting, as well as few-shot generation and classification via training-free in-context inference.
  arXiv  Detail & Related papers  (2026-05-31T16:04:11Z)
• Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models [65.89572755202245]
  Diffusion Language Models (DLMs) offer stronger global awareness and highly parallel generation.<n>Post-training DLMs with standard Negative Evidence Lower Bound (NELBO)-based supervised fine-tuning remains inefficient.<n>We propose a self-distilled trajectory-based post-training framework that aligns training with the easy-to-hard structure of inference.
  arXiv  Detail & Related papers  (2026-05-12T09:39:06Z)
• Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models [102.20309135516186]
  Cross-entropy (CE) training provides dense and scalable supervision for language models.<n>We introduce a feature-matching objective for language-model fine-tuning.<n>To optimize this objective efficiently, we propose energy-based fine-tuning.
  arXiv  Detail & Related papers  (2026-03-12T17:57:50Z)
• Support Tokens, Stability Margins, and a New Foundation for Robust LLMs [1.429795922604976]
  We re-interpret causal self-attention transformers, the backbone of modern foundation models.<n>A barrier constraint emerges on the self-attention parameters.<n>This reveals a boundary where attention becomes ill-conditioned.
  arXiv  Detail & Related papers  (2026-02-25T08:44:44Z)
• Gradients Must Earn Their Influence: Unifying SFT with Generalized Entropic Objectives [22.29000001610794]
  Standard negative log-likelihood for Supervised Fine-Tuning (SFT) applies uniform token-level weighting.<n>This rigidity creates a two-fold failure mode: (i) overemphasizing low-probability targets can amplify gradients on noisy supervision and disrupt robust priors, and (ii) uniform weighting provides weak sharpening when the model is already confident.<n>Existing methods fail to resolve the resulting plasticity--stability dilemma, often suppressing necessary learning signals alongside harmful ones.<n>We introduce Dynamic Entropy Fine-Tuning (DEFT), a parameter-free objective that modulates the
  arXiv  Detail & Related papers  (2026-02-11T22:56:43Z)
• Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting [44.23640219583819]
  Reinforced Fine-Tuning (SFT) is the standard paradigm for domain adaptation, yet it frequently incurs the cost of catastrophic forgetting.<n>We propose Entropy-Adaptive Fine-Tuning (EAFT) to solve this problem.<n>EAFT consistently matches the downstream performance of standard SFT while significantly mitigating the degradation of general capabilities.
  arXiv  Detail & Related papers  (2026-01-05T14:28:17Z)
• Steering Vision-Language Pre-trained Models for Incremental Face Presentation Attack Detection [62.89126207012712]
  Face Presentation Attack Detection (PAD) demands incremental learning to combat spoofing tactics and domains.<n>Privacy regulations forbid retaining past data, necessitating rehearsal-free learning (RF-IL)
  arXiv  Detail & Related papers  (2025-12-22T04:30:11Z)
• 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)

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.