The Missing Piece in Pre-trained Model Evaluation: Reward-Guided Decoding Unlocks Task-Oriented Behavior Without Parameter Updates

• URL: http://arxiv.org/abs/2605.28020v1
• Date: Wed, 27 May 2026 06:25:00 GMT
• Title: The Missing Piece in Pre-trained Model Evaluation: Reward-Guided Decoding Unlocks Task-Oriented Behavior Without Parameter Updates
• Abstract summary: Energy-Based Decoding is a training-free, reward-guided framework for activating task-oriented behaviors from frozen pre-trained models.<n>We show that EBD shifts base-model outputs toward more instructionfollowing behavior, increasing behavioral similarity to post-trained counterparts.
• Score: 31.50160357699629
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the rapid progress of large language models (LLMs), reliably evaluating the capabilities of pre-trained LLMs has become increasingly important. The challenge is that base pre-trained models are optimized for next-token prediction and often fail to follow instructions or produce well-formed answers under standard prompting and direct decoding. As a result, benchmark performance can conflate model capability with decoding-induced failures to produce task-oriented outputs, while exposing such behavior often relies on costly post-training. Recent decodingonly approaches attempt to reshape output distributions, but such methods can be inefficient and brittle across open-ended tasks. To address these limitations, we propose Energy-Based Decoding (EBD), a training-free, reward-guided framework for activating task-oriented behaviors from frozen pre-trained LLMs across both open-ended and objective tasks. EBD augments decoding with an external lightweight reward model, steering generations toward high-utility responses while anchoring them to the pre-trained model prior through a reward-tilted target distribution. We show that EBD shifts base-model outputs toward more instructionfollowing behavior, increasing behavioral similarity to post-trained counterparts and enabling a fairer inference-time evaluation of accessible pre-trained-model behavior. Empirically, EBD outperforms baselines across five models and six benchmarks, improving Qwen3-8B-Base on AlpacaEval2.0 from 8.8 to 44.5, reducing Mistral-7B Math500 latency by 18.9x relative to prior decoding work, and remaining robust to reward-model size.

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)
• On Predicting the Post-training Potential of Pre-trained LLMs [60.07459271263409]
  We introduce a new task of predicting post-training potential - forecasting a base model's performance before post-training.<n>We propose RuDE, a unified framework that bypasses the generation gap of base models by leveraging response discrimination.<n>Experiments demonstrate a correlation greater than 90% with post-training performance.
  arXiv  Detail & Related papers  (2026-05-12T11:33:49Z)
• Pioneer Agent: Continual Improvement of Small Language Models in Production [6.452260317191361]
  Small language models are attractive for production deployment due to their low cost, fast inference, and ease of specialization.<n>We present Pioneer Agent, a closed-loop system that automates the process of adapting small language models to a specific task.
  arXiv  Detail & Related papers  (2026-04-10T18:13:09Z)
• RADAR: Revealing Asymmetric Development of Abilities in MLLM Pre-training [59.493415006017635]
  Pre-trained Multi-modal Large Language Models (MLLMs) provide a knowledge-rich foundation for post-training.<n>Current evaluation relies on testing after supervised fine-tuning, which introduces laborious additional training and autoregressive decoding costs.<n>We propose RADAR, an efficient ability-centric evaluation framework for Revealing Asymmetric Development of Abilities in MLLM pRe-training.
  arXiv  Detail & Related papers  (2026-02-13T12:56:31Z)
• AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering [52.67783579040657]
  AceGRPO is a machine learning system that prioritizes tasks at the agent's learning frontier to maximize learning efficiency.<n>Our trained Ace-30B model achieves a 100% valid submission rate on MLE-Bench-Lite, approaches the performance of proprietary frontier models, and outperforms larger open-source baselines.
  arXiv  Detail & Related papers  (2026-02-08T10:55:03Z)
• 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)
• ACECODER: Acing Coder RL via Automated Test-Case Synthesis [36.740393665032954]
  We design a pipeline that generates extensive (question, test-cases) pairs from existing code data.<n>We construct preference pairs based on pass rates over sampled programs to train reward models with Bradley-Terry loss.<n>We show that our RL training can improve model on HumanEval-plus by over 25% and MBPP-plus by 6% for merely 80 optimization steps.
  arXiv  Detail & Related papers  (2025-02-03T18:46:04Z)
• What Do Learning Dynamics Reveal About Generalization in LLM Reasoning? [83.83230167222852]
  We find that a model's generalization behavior can be effectively characterized by a training metric we call pre-memorization train accuracy. By connecting a model's learning behavior to its generalization, pre-memorization train accuracy can guide targeted improvements to training strategies.
  arXiv  Detail & Related papers  (2024-11-12T09:52:40Z)
• Learning to Modulate pre-trained Models in RL [22.812215561012874]
  Fine-tuning a pre-trained model often suffers from catastrophic forgetting. Our study shows that with most fine-tuning approaches, the performance on pre-training tasks deteriorates significantly. We propose a novel method, Learning-to-Modulate (L2M), that avoids the degradation of learned skills by modulating the information flow of the frozen pre-trained model.
  arXiv  Detail & Related papers  (2023-06-26T17:53:05Z)
• CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning [92.36705236706678]
  "CodeRL" is a new framework for program synthesis tasks through pretrained LMs and deep reinforcement learning. During inference, we introduce a new generation procedure with a critical sampling strategy. For the model backbones, we extended the encoder-decoder architecture of CodeT5 with enhanced learning objectives.
  arXiv  Detail & Related papers  (2022-07-05T02:42:15Z)

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.