Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning

• URL: http://arxiv.org/abs/2602.01745v1
• Date: Mon, 02 Feb 2026 07:27:19 GMT
• Title: Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning
• Abstract summary: RankTuner introduces a probability--entropy calibration signal, the Relative Rank Indicator, which compares the rank of the ground-truth token with its expected rank under the prediction distribution.<n>The inverse indicator is used as a token-wise Relative Scale to reweight the fine-tuning objective, focusing updates on truly under-learned tokens.
• Score: 55.2818264614932
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Token-level reweighting is a simple yet effective mechanism for controlling supervised fine-tuning, but common indicators are largely one-dimensional: the ground-truth probability reflects downstream alignment, while token entropy reflects intrinsic uncertainty induced by the pre-training prior. Ignoring entropy can misidentify noisy or easily replaceable tokens as learning-critical, while ignoring probability fails to reflect target-specific alignment. RankTuner introduces a probability--entropy calibration signal, the Relative Rank Indicator, which compares the rank of the ground-truth token with its expected rank under the prediction distribution. The inverse indicator is used as a token-wise Relative Scale to reweight the fine-tuning objective, focusing updates on truly under-learned tokens without over-penalizing intrinsically uncertain positions. Experiments on multiple backbones show consistent improvements on mathematical reasoning benchmarks, transfer gains on out-of-distribution reasoning, and pre code generation performance over probability-only or entropy-only reweighting baselines.

Related papers

• 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)
• Tailoring Strictly Proper Scoring Rules for Downstream Tasks: An Application to Causal Inference [48.78219918881965]
  We propose a principled framework for deriving task-specific strictly proper scoring rules by matching the local curvature of the downstream error metric.<n>We apply this to the Average Treatment Effect (ATE) estimation, deriving a closed-form loss and its corresponding canonical probability mapping.
  arXiv  Detail & Related papers  (2026-06-02T08:41:25Z)
• Proper Scoring Rules for Agentic Uncertainty Quantification [0.038379177968040606]
  Trajectory Proper Score (TPS) is a predictor-agnostic family of strictly proper trajectory-level scoring rules.<n>Trajectory ECE is resolution-blind, while scalarized Trajectory Brier elicits only the collapsed scalar, not the full trace.
  arXiv  Detail & Related papers  (2026-05-23T22:22:00Z)
• Not All Tokens Learn Alike: Attention Entropy Reveals Heterogeneous Signals in RL Reasoning [11.322734738973603]
  Reinforcement-learning-based post-training has become a key approach for improving the reasoning ability of large language models.<n>This work studies their heterogeneity through attention entropy, which measures how concentrated or diffuse the contextual support is for each response token.
  arXiv  Detail & Related papers  (2026-05-08T12:31:28Z)
• Unleashing Implicit Rewards: Prefix-Value Learning for Distribution-Level Optimization [74.91418266859297]
  Implicit process reward models (PRMs) provide fine-grained reward signals along the reasoning process.<n>PRMs suffer from a train-inference mismatch: training only constrains a sequence-level aggregate, whereas inference requires token-level scores to reflect local step quality.<n>We propose a novel Implicit Prefix-Value Reward Model (IPVRM), which directly learns a prefix-conditioned value function estimating the probability of eventual correctness.<n>We also propose Distribution-Level RL (DistRL), which computes TD advantages for both sampled tokens and high-probability candidate tokens.
  arXiv  Detail & Related papers  (2026-04-14T18:19:54Z)
• Taming the Tail: Stable LLM Reinforcement Learning via Dynamic Vocabulary Pruning [35.41241409574854]
  We show that inference engines and numerically-precise training systems produce different probability distributions from the same parameters, creating a training-inference mismatch.<n>By pruning such tokens, we trade large, systematically biased mismatches for a small, bounded optimization bias.
  arXiv  Detail & Related papers  (2025-12-28T21:44:07Z)
• From Uniform to Heterogeneous: Tailoring Policy Optimization to Every Token's Nature [38.46122853450324]
  Existing algorithms apply uniform optimization to all tokens, ignoring their different roles in reasoning process.<n>We introduce Heterogeneous Adaptive Policy Optimization (HAPO), a token-aware algorithm that dynamically adapts optimization based on token entropy.
  arXiv  Detail & Related papers  (2025-09-20T09:30:25Z)
• When Does Confidence-Based Cascade Deferral Suffice? [69.28314307469381]
  Cascades are a classical strategy to enable inference cost to vary adaptively across samples. A deferral rule determines whether to invoke the next classifier in the sequence, or to terminate prediction. Despite being oblivious to the structure of the cascade, confidence-based deferral often works remarkably well in practice.
  arXiv  Detail & Related papers  (2023-07-06T04:13:57Z)
• Regularized Vector Quantization for Tokenized Image Synthesis [126.96880843754066]
  Quantizing images into discrete representations has been a fundamental problem in unified generative modeling. deterministic quantization suffers from severe codebook collapse and misalignment with inference stage while quantization suffers from low codebook utilization and reconstruction objective. This paper presents a regularized vector quantization framework that allows to mitigate perturbed above issues effectively by applying regularization from two perspectives.
  arXiv  Detail & Related papers  (2023-03-11T15:20:54Z)
• Alignment Entropy Regularization [13.904347165738491]
  We use entropy to measure a model's uncertainty. We evaluate the effect of entropy regularization in encouraging the model to distribute the probability mass only on a smaller subset of allowed alignments.
  arXiv  Detail & Related papers  (2022-12-22T18:51:02Z)
• Deconfounding Scores: Feature Representations for Causal Effect Estimation with Weak Overlap [140.98628848491146]
  We introduce deconfounding scores, which induce better overlap without biasing the target of estimation. We show that deconfounding scores satisfy a zero-covariance condition that is identifiable in observed data. In particular, we show that this technique could be an attractive alternative to standard regularizations.
  arXiv  Detail & Related papers  (2021-04-12T18:50:11Z)
• Evaluating probabilistic classifiers: Reliability diagrams and score decompositions revisited [68.8204255655161]
  We introduce the CORP approach, which generates provably statistically Consistent, Optimally binned, and Reproducible reliability diagrams in an automated way. Corpor is based on non-parametric isotonic regression and implemented via the Pool-adjacent-violators (PAV) algorithm.
  arXiv  Detail & Related papers  (2020-08-07T08:22:26Z)
• Optimal Change-Point Detection with Training Sequences in the Large and Moderate Deviations Regimes [72.68201611113673]
  This paper investigates a novel offline change-point detection problem from an information-theoretic perspective. We assume that the knowledge of the underlying pre- and post-change distributions are not known and can only be learned from the training sequences which are available.
  arXiv  Detail & Related papers  (2020-03-13T23:39:40Z)

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.