Kad: A Framework for Proxy-based Test-time Alignment with Knapsack Approximation Deferral

• URL: http://arxiv.org/abs/2510.27017v1
• Date: Thu, 30 Oct 2025 21:38:45 GMT
• Title: Kad: A Framework for Proxy-based Test-time Alignment with Knapsack Approximation Deferral
• Authors: Ayoub Hammal, Pierre Zweigenbaum, Caio Corro,
• Abstract summary: Large language models (LLM) still require further alignment to adhere to downstream task requirements and stylistic preferences.<n>As LLMs continue to scale in terms of size, the computational cost of alignment procedures increase prohibitively.<n>We propose a novel approach to circumvent these costs via proxy-based test-time alignment.
• Score: 6.949966663998242
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Several previous works concluded that the largest part of generation capabilities of large language models (LLM) are learned (early) during pre-training. However, LLMs still require further alignment to adhere to downstream task requirements and stylistic preferences, among other desired properties. As LLMs continue to scale in terms of size, the computational cost of alignment procedures increase prohibitively. In this work, we propose a novel approach to circumvent these costs via proxy-based test-time alignment, i.e. using guidance from a small aligned model. Our approach can be described as token-specific cascading method, where the token-specific deferral rule is reduced to 0-1 knapsack problem. In this setting, we derive primal and dual approximations of the optimal deferral decision. We experimentally show the benefits of our method both in task performance and speculative decoding speed.

Related papers

• $\ abla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space [71.23672814629448]
  $nabla$-Reasoner is an iterative generation framework that integrates differentiable optimization over token logits into the decoding loop.<n>$nabla$-Reasoner achieves over 20% accuracy improvement on a challenging mathematical reasoning benchmark.
  arXiv  Detail & Related papers  (2026-03-05T08:42:54Z)
• Predicting LLM Output Length via Entropy-Guided Representations [13.351384070796747]
  We introduce a lightweight framework that reuses the main model's internal hidden states for efficient length prediction.<n>Our framework features two core components: 1) Entropy-Guided Token Pooling (EGTP), which uses on-the-fly activations and token entropy for highly accurate static prediction.
  arXiv  Detail & Related papers  (2026-02-12T10:49:04Z)
• PITA: Preference-Guided Inference-Time Alignment for LLM Post-Training [9.093854840532062]
  PITA is a novel framework that integrates preference feedback directly into the LLM's token generation.<n> PITA learns a small preference-based guidance policy to modify token probabilities at inference time without fine-tuning.<n>We evaluate PITA across diverse tasks, including mathematical reasoning and sentiment classification.
  arXiv  Detail & Related papers  (2025-07-26T21:46:32Z)
• Can Pre-training Indicators Reliably Predict Fine-tuning Outcomes of LLMs? [42.608899417822656]
  We construct a dataset using 50 1B parameter LLM variants with systematically varied pre-training configurations.<n>We introduce novel unsupervised and supervised proxy metrics derived from pre-training that successfully reduce the relative performance prediction error rate by over 50%.
  arXiv  Detail & Related papers  (2025-04-16T21:19:09Z)
• LESA: Learnable LLM Layer Scaling-Up [57.0510934286449]
  Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive.<n>Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger ones.<n>We propose textbfLESA, a novel learnable method for depth scaling-up.
  arXiv  Detail & Related papers  (2025-02-19T14:58:48Z)
• Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters [27.656263126925815]
  We study the scaling of inference-time computation in LLMs. We find that in both cases, the effectiveness of different approaches to scaling test-time compute critically varies depending on the difficulty of the prompt.
  arXiv  Detail & Related papers  (2024-08-06T17:35:05Z)
• Graph-Structured Speculative Decoding [52.94367724136063]
  Speculative decoding has emerged as a promising technique to accelerate the inference of Large Language Models. We introduce an innovative approach utilizing a directed acyclic graph (DAG) to manage the drafted hypotheses. We observe a remarkable speedup of 1.73$times$ to 1.96$times$, significantly surpassing standard speculative decoding.
  arXiv  Detail & Related papers  (2024-07-23T06:21:24Z)
• Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient [57.9629676017527]
  We propose an optimization-based structural pruning that learns the pruning masks in a probabilistic space directly by optimizing the loss of the pruned model.<n>We achieve this by learning an underlying Bernoulli distribution to sample binary pruning masks.<n>Experiments conducted on LLaMA, LLaMA-2, LLaMA-3, Vicuna, and Mistral models demonstrate the promising performance of our method in efficiency and effectiveness.
  arXiv  Detail & Related papers  (2024-06-15T09:31:03Z)
• An Efficient Rehearsal Scheme for Catastrophic Forgetting Mitigation during Multi-stage Fine-tuning [55.467047686093025]
  A common approach to alleviate such forgetting is to rehearse samples from prior tasks during fine-tuning.<n>We propose a sampling scheme, textttbf mix-cd, that prioritizes rehearsal of collateral damage'' samples.<n>Our approach is computationally efficient, easy to implement, and outperforms several leading continual learning methods in compute-constrained settings.
  arXiv  Detail & Related papers  (2024-02-12T22:32:12Z)
• Amortizing intractable inference in large language models [56.92471123778389]
  We use amortized Bayesian inference to sample from intractable posterior distributions. We empirically demonstrate that this distribution-matching paradigm of LLM fine-tuning can serve as an effective alternative to maximum-likelihood training. As an important application, we interpret chain-of-thought reasoning as a latent variable modeling problem.
  arXiv  Detail & Related papers  (2023-10-06T16:36:08Z)
• Leaving the Nest: Going Beyond Local Loss Functions for Predict-Then-Optimize [57.22851616806617]
  We show that our method achieves state-of-the-art results in four domains from the literature. Our approach outperforms the best existing method by nearly 200% when the localness assumption is broken.
  arXiv  Detail & Related papers  (2023-05-26T11:17:45Z)
• Learning the Step-size Policy for the Limited-Memory Broyden-Fletcher-Goldfarb-Shanno Algorithm [3.7470451129384825]
  We consider the problem of how to learn a step-size policy for the Limited-Memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS) algorithm. We propose a neural network architecture with local information of the current gradient as the input. The step-length policy is learned from data of similar optimization problems, avoids additional evaluations of the objective function, and guarantees that the output step remains inside a pre-defined interval.
  arXiv  Detail & Related papers  (2020-10-03T09:34:03Z)

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.