Gradients Must Earn Their Influence: Unifying SFT with Generalized Entropic Objectives

• URL: http://arxiv.org/abs/2602.11424v1
• Date: Wed, 11 Feb 2026 22:56:43 GMT
• Title: Gradients Must Earn Their Influence: Unifying SFT with Generalized Entropic Objectives
• Authors: Zecheng Wang, Deyuan Liu, Chunshan Li, Yupeng Zhang, Zhengyun Zhao, Dianhui Chu, Bingning Wang, Dianbo Sui,
• Abstract summary: 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
• Score: 22.29000001610794
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Standard negative log-likelihood (NLL) for Supervised Fine-Tuning (SFT) applies uniform token-level weighting. 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. Existing methods fail to resolve the resulting plasticity--stability dilemma, often suppressing necessary learning signals alongside harmful ones. To address this issue, we unify token-level SFT objectives within a generalized deformed-log family and expose a universal gate $\times$ error gradient structure, where the gate controls how much the model trusts its current prediction. By employing the Cayley transform, we map the model's continuously evolving uncertainty onto a continuous focus trajectory, which enables seamless interpolation between scenarios involving uncertain novel concepts and those involving well-established knowledge. We then introduce Dynamic Entropy Fine-Tuning (DEFT), a parameter-free objective that modulates the trust gate using distribution concentration (Rényi-2 entropy) as a practical proxy for the model's predictive state. Extensive experiments and analyses demonstrate that DEFT achieves a better balance between exploration and exploitation, leading to improved overall performance.

Related papers

• GTS: Inference-Time Scaling of Latent Reasoning with a Learnable Gaussian Thought Sampler [54.10960908347221]
  We model latent thought exploration as conditional sampling from learnable densities and instantiate this idea as a Gaussian Thought Sampler (GTS)<n>GTS predicts context-dependent perturbation distributions over continuous reasoning states and is trained with GRPO-style policy optimization while keeping the backbone frozen.
  arXiv  Detail & Related papers  (2026-02-15T09:57:47Z)
• Binary Flow Matching: Prediction-Loss Space Alignment for Robust Learning [23.616336786063552]
  Flow matching has emerged as a powerful framework for generative modeling.<n>We identify a latent structural mismatch that arises when it is coupled with velocity-based objectives.<n>We prove that re-aligning the objective to the signal space eliminates the singular weighting.
  arXiv  Detail & Related papers  (2026-02-11T02:02:30Z)
• 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)
• Closed-Loop Transformers: Autoregressive Modeling as Iterative Latent Equilibrium [0.6820746164515952]
  We introduce the closed-loop prediction principle, which requires that models iteratively refine latent representations until reaching a self-consistent equilibrium.<n>We instantiate this principle as Equilibrium Transformers, which augment standard transformer layers with an Equilibrium Refinement Module.<n>Preliminary experiments on the binary parity task demonstrate +3.28% average improvement on challenging sequences, with gains reaching +8.07% where standard transformers approach random performance.
  arXiv  Detail & Related papers  (2025-11-26T20:02:59Z)
• SynCast: Synergizing Contradictions in Precipitation Nowcasting via Diffusion Sequential Preference Optimization [62.958457694151384]
  We introduce preference optimization into precipitation nowcasting for the first time, motivated by the success of reinforcement learning from human feedback in large language models.<n>In the first stage, the framework focuses on reducing FAR, training the model to effectively suppress false alarms.
  arXiv  Detail & Related papers  (2025-10-22T16:11:22Z)
• ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving [64.42138266293202]
  ResAD is a Normalized Residual Trajectory Modeling framework.<n>It reframes the learning task to predict the residual deviation from an inertial reference.<n>On the NAVSIM benchmark, ResAD achieves a state-of-the-art PDMS of 88.6 using a vanilla diffusion policy.
  arXiv  Detail & Related papers  (2025-10-09T17:59:36Z)
• A Unified Noise-Curvature View of Loss of Trainability [8.602734307457387]
  Loss of trainability (LoT) in continual learning occurs when steps no longer yield improvement as tasks evolve.<n>We introduce two complementary criteria: a batch-size-aware gradient-noise bound and a curvature volatility-controlled bound.<n>Using this threshold, we build a simple per-layer scheduler that keeps each layers effective step below a safe limit.
  arXiv  Detail & Related papers  (2025-09-24T02:11:13Z)
• Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories [58.988535279557546]
  We introduce textbf sycophancy Mitigation through Adaptive Reasoning Trajectories.<n>We show that SMART significantly reduces sycophantic behavior while preserving strong performance on out-of-distribution inputs.
  arXiv  Detail & Related papers  (2025-09-20T17:09:14Z)
• Selective Learning: Towards Robust Calibration with Dynamic Regularization [79.92633587914659]
  Miscalibration in deep learning refers to there is a discrepancy between the predicted confidence and performance. We introduce Dynamic Regularization (DReg) which aims to learn what should be learned during training thereby circumventing the confidence adjusting trade-off.
  arXiv  Detail & Related papers  (2024-02-13T11:25:20Z)
• Robustness and Accuracy Could Be Reconcilable by (Proper) Definition [109.62614226793833]
  The trade-off between robustness and accuracy has been widely studied in the adversarial literature. We find that it may stem from the improperly defined robust error, which imposes an inductive bias of local invariance. By definition, SCORE facilitates the reconciliation between robustness and accuracy, while still handling the worst-case uncertainty.
  arXiv  Detail & Related papers  (2022-02-21T10:36:09Z)

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.