Eliciting Fine-Tuned Transformer Capabilities via Inference-Time Techniques

• URL: http://arxiv.org/abs/2506.08060v1
• Date: Mon, 09 Jun 2025 08:37:19 GMT
• Title: Eliciting Fine-Tuned Transformer Capabilities via Inference-Time Techniques
• Authors: Asankhaya Sharma,
• Abstract summary: Large language models have transformed natural language processing, yet supervised fine-tuning (SFT) remains computationally intensive.<n>This paper formally proves that capabilities acquired through SFT can be approximated by a base transformer model.<n>We extend these results to practical scenarios with finite context lengths and partial dataset access.
• Score: 1.14219428942199
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models have transformed natural language processing, yet supervised fine-tuning (SFT) remains computationally intensive. This paper formally proves that capabilities acquired through SFT can be approximated by a base transformer model using inference-time techniques, specifically in-context learning (ICL), without altering model parameters, under idealized assumptions including unbounded computational resources and access to the fine-tuning dataset. We extend these results to practical scenarios with finite context lengths and partial dataset access. For text generation tasks with fixed output length $l$, datasets of size $\mathrm{O}\left( \frac{m V}{\varepsilon^2} \log \frac{m}{\delta} \right)$ or, with bounded context, $\mathrm{O}\left( \frac{l \log V}{\varepsilon^2} \log \frac{1}{\delta} \right)$ suffice to approximate fine-tuned behavior across $m$ contexts within error $\varepsilon$, where $V$ is the vocabulary size and $\delta$ is the failure probability. For linear classification, datasets of size $\mathrm{O}\left( \frac{d}{\varepsilon} \right)$ or, with fixed context, $\mathrm{O}\left( \frac{1}{\varepsilon^2} \log \frac{1}{\delta} \right)$ are sufficient, where $d$ is the input dimension. Grounded in the Turing completeness of transformers, these results provide a theoretical foundation for resource-efficient deployment of large language models, with practical techniques like retrieval-augmented generation bridging theory to real-world applications.

Related papers

• Robust learning of halfspaces under log-concave marginals [6.852292115526837]
  We give an algorithm that learns linear threshold functions and returns a classifier with boundary volume $O(r+varepsilon)$ at radius perturbation $r$.<n>The time and sample complexity of $dtildeO (1/varepsilon2)$ matches the complexity of Boolean regression.
  arXiv  Detail & Related papers  (2025-05-19T20:12:16Z)
• Sign Operator for Coping with Heavy-Tailed Noise in Non-Convex Optimization: High Probability Bounds Under $(L_0, L_1)$-Smoothness [74.18546828528298]
  We show that SignSGD with Majority Voting can robustly work on the whole range of complexity with $kappakappakappakappa-1right, kappakappakappa-1right, kappakappakappa-1right, kappakappakappa-1right, kappakappakappa-1right, kappakappakappa-1right, kappakappakappa-1right, kappa
  arXiv  Detail & Related papers  (2025-02-11T19:54:11Z)
• Learning Networks from Wide-Sense Stationary Stochastic Processes [7.59499154221528]
  A key inference problem here is to learn edge connectivity from node outputs (potentials)<n>We use a Whittle's maximum likelihood estimator (MLE) to learn the support of $Last$ from temporally correlated samples.<n>We show that the MLE problem is strictly convex, admitting a unique solution.
  arXiv  Detail & Related papers  (2024-12-04T23:14:00Z)
• Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximization [65.8915778873691]
  conditional distributions is a central problem in machine learning.<n>We propose a new paradigm that integrates both paired and unpaired data.<n>We show that our approach can theoretically recover true conditional distributions with arbitrarily small error.
  arXiv  Detail & Related papers  (2024-10-03T16:12:59Z)
• Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit [75.4661041626338]
  We study the problem of gradient descent learning of a single-index target function $f_*(boldsymbolx) = textstylesigma_*left(langleboldsymbolx,boldsymbolthetarangleright)$<n>We prove that a two-layer neural network optimized by an SGD-based algorithm learns $f_*$ with a complexity that is not governed by information exponents.
  arXiv  Detail & Related papers  (2024-06-03T17:56:58Z)
• Policy Zooming: Adaptive Discretization-based Infinite-Horizon Average-Reward Reinforcement Learning [2.2984209387877628]
  We study Lipschitz MDPs in the infinite-horizon average-reward reinforcement learning (RL) setup.<n>We upper bound their regret as $tildemathcalObig(T1 - d_texteff.-1big)$, where $d_texteff. = dPhi_z+2$ for model-free algorithmtextitPZRL-MF and $d_texteff. = 2d_mathcalS + dPhi_z + 3$ for
  arXiv  Detail & Related papers  (2024-05-29T06:18:09Z)
• On Understanding Attention-Based In-Context Learning for Categorical Data [49.40350941996942]
  We develop a network composed of attention blocks, with each block employing a self-attention layer followed by a cross-attention layer, with associated skip connections.<n>This model can exactly perform multi-step functional GD inference for in-context inference with categorical observations.
  arXiv  Detail & Related papers  (2024-05-27T15:03:21Z)
• Overview of Physics-Informed Machine Learning Inversion of Geophysical Data [1.5108390071719444]
  We review four types of algorithms for physics-informed machine learning (PIML) inversion of geophysical data. The selection of weights $lambda_i$ and the NN operations determine one of four different PIML algorithms.
  arXiv  Detail & Related papers  (2023-10-12T08:10:31Z)
• Regret-Optimal Federated Transfer Learning for Kernel Regression with Applications in American Option Pricing [8.723136784230906]
  We propose an optimal iterative scheme for federated transfer learning, where a central planner has access to datasets. Our objective is to minimize the cumulative deviation of the generated parameters $thetai(t)_t=0T$ across all $T$ iterations. By leveraging symmetries within the regret-optimal algorithm, we develop a nearly regret $_optimal that runs with $mathcalO(Np2)$ fewer elementary operations.
  arXiv  Detail & Related papers  (2023-09-08T19:17:03Z)
• Near-Optimal Regret Bounds for Multi-batch Reinforcement Learning [54.806166861456035]
  We study the episodic reinforcement learning (RL) problem modeled by finite-horizon Markov Decision Processes (MDPs) with constraint on the number of batches. We design a computational efficient algorithm to achieve near-optimal regret of $tildeO(sqrtSAH3Kln (1/delta))$tildeO(cdot) hides logarithmic terms of $(S,A,H,K)$ in $K$ episodes. Our technical contribution are two-fold: 1) a near-optimal design scheme to explore
  arXiv  Detail & Related papers  (2022-10-15T09:22:22Z)
• Supervised Training of Conditional Monge Maps [107.78770597815242]
  Optimal transport (OT) theory describes general principles to define and select, among many possible choices, the most efficient way to map a probability measure onto another. We introduce CondOT, a multi-task approach to estimate a family of OT maps conditioned on a context variable. We demonstrate the ability of CondOT to infer the effect of an arbitrary combination of genetic or therapeutic perturbations on single cells.
  arXiv  Detail & Related papers  (2022-06-28T19:34:44Z)
• A Law of Robustness beyond Isoperimetry [84.33752026418045]
  We prove a Lipschitzness lower bound $Omega(sqrtn/p)$ of robustness of interpolating neural network parameters on arbitrary distributions. We then show the potential benefit of overparametrization for smooth data when $n=mathrmpoly(d)$. We disprove the potential existence of an $O(1)$-Lipschitz robust interpolating function when $n=exp(omega(d))$.
  arXiv  Detail & Related papers  (2022-02-23T16:10:23Z)
• An Algorithm for Learning Smaller Representations of Models With Scarce Data [0.0]
  We present a greedy algorithm for solving binary classification problems in situations where the dataset is too small or not fully representative. It relies on a trained model with loose accuracy constraints, an iterative hyperparameter pruning procedure, and a function used to generate new data.
  arXiv  Detail & Related papers  (2020-10-15T19:17:51Z)
• Hybrid Stochastic-Deterministic Minibatch Proximal Gradient: Less-Than-Single-Pass Optimization with Nearly Optimal Generalization [83.80460802169999]
  We show that HSDMPG can attain an $mathcalObig (1/sttnbig)$ which is at the order of excess error on a learning model. For loss factors, we prove that HSDMPG can attain an $mathcalObig (1/sttnbig)$ which is at the order of excess error on a learning model.
  arXiv  Detail & Related papers  (2020-09-18T02:18:44Z)
• Convergence of Sparse Variational Inference in Gaussian Processes Regression [29.636483122130027]
  We show that a method with an overall computational cost of $mathcalO(log N)2D(loglog N)2)$ can be used to perform inference.
  arXiv  Detail & Related papers  (2020-08-01T19:23:34Z)
• Few-Shot Learning via Learning the Representation, Provably [115.7367053639605]
  This paper studies few-shot learning via representation learning. One uses $T$ source tasks with $n_1$ data per task to learn a representation in order to reduce the sample complexity of a target task.
  arXiv  Detail & Related papers  (2020-02-21T17:30:00Z)

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.