Learning to Align Human Code Preferences

• URL: http://arxiv.org/abs/2507.20109v1
• Date: Sun, 27 Jul 2025 02:48:26 GMT
• Title: Learning to Align Human Code Preferences
• Authors: Xin Yin, Chao Ni, Liushan Chen, Xiaohu Yang,
• Abstract summary: Large Language Models (LLMs) have demonstrated remarkable potential in automating software development tasks.<n>Recent advances leverage Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) to align models with human preferences.<n>This paper systematically investigates the roles of SFT and DPO in aligning LLMs with different code preferences.<n>We propose Adaptive Preference Optimization (APO), a dynamic integration approach that adaptively amplifies preferred responses, suppresses dispreferred ones, and encourages exploration of potentially superior solutions during training.
• Score: 2.9994722574283443
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) have demonstrated remarkable potential in automating software development tasks. While recent advances leverage Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) to align models with human preferences, the optimal training strategy remains unclear across diverse code preference scenarios. This paper systematically investigates the roles of SFT and DPO in aligning LLMs with different code preferences. Through both theoretical analysis and empirical observation, we hypothesize that SFT excels in scenarios with objectively verifiable optimal solutions, while applying SFT followed by DPO (S&D) enables models to explore superior solutions in scenarios without objectively verifiable optimal solutions. Based on the analysis and experimental evidence, we propose Adaptive Preference Optimization (APO), a dynamic integration approach that adaptively amplifies preferred responses, suppresses dispreferred ones, and encourages exploration of potentially superior solutions during training. Extensive experiments across six representative code preference tasks validate our theoretical hypotheses and demonstrate that APO consistently matches or surpasses the performance of existing SFT and S&D strategies. Our work provides both theoretical foundations and practical guidance for selecting appropriate training strategies in different code preference alignment scenarios.

Related papers

• Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections [65.36449542323277]
  We present a unified theoretical framework bridgingSupervised Fine-Tuning (SFT) and preference learning in Large Language Model (LLM) post-training.<n>We propose a simple yet effective learning rate reduction approach that yields significant performance improvements.
  arXiv  Detail & Related papers  (2025-06-15T05:42:29Z)
• Preference-Guided Diffusion for Multi-Objective Offline Optimization [64.08326521234228]
  We propose a preference-guided diffusion model for offline multi-objective optimization.<n>Our guidance is a preference model trained to predict the probability that one design dominates another.<n>Our results highlight the effectiveness of classifier-guided diffusion models in generating diverse and high-quality solutions.
  arXiv  Detail & Related papers  (2025-03-21T16:49:38Z)
• A Survey on the Optimization of Large Language Model-based Agents [16.733092886211097]
  Large Language Models (LLMs) have been widely adopted in various fields, becoming essential for autonomous decision-making and interactive tasks.<n>However, current work typically relies on prompt design or fine-tuning strategies applied to vanilla LLMs.<n>We provide a comprehensive review of LLM-based agent optimization approaches, categorizing them into parameter-driven and parameter-free methods.
  arXiv  Detail & Related papers  (2025-03-16T10:09:10Z)
• A Survey of Direct Preference Optimization [103.59317151002693]
  Large Language Models (LLMs) have demonstrated unprecedented generative capabilities.<n>Their alignment with human values remains critical for ensuring helpful and harmless deployments.<n>Direct Preference Optimization (DPO) has recently gained prominence as a streamlined alternative.
  arXiv  Detail & Related papers  (2025-03-12T08:45:15Z)
• Reward-aware Preference Optimization: A Unified Mathematical Framework for Model Alignment [45.45508377432791]
  This paper introduces Reward-Aware Preference Optimization (RPO), a mathematical framework that unifies popular preference optimization techniques.<n>RPO provides a structured approach to disentangle and systematically study the impact of various design choices.<n>We propose a new experimental setup that enables the clean and direct ablation of such design choices.
  arXiv  Detail & Related papers  (2025-01-31T22:39:04Z)
• Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment [40.71270945505082]
  Large language models (LLMs) are increasingly integrated into various societal and decision-making processes.<n>Traditional methods, such as reinforcement learning from human feedback (RLHF), achieve alignment by fine-tuning model parameters.<n>In contrast, prompt optimization is a viable alternative to RLHF for LLM alignment.
  arXiv  Detail & Related papers  (2025-01-07T03:14:39Z)
• Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models [54.381650481255235]
  We introduce a new tuning-free approach for self-alignment, Dynamic Rewarding with Prompt Optimization (O) Our approach leverages a search-based optimization framework that allows LLMs to iteratively self-improve and craft the optimal alignment instructions. Empirical evaluations on eight recent LLMs, both open and closed-sourced, demonstrate that DRPO significantly enhances alignment performance.
  arXiv  Detail & Related papers  (2024-11-13T16:15:38Z)
• Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer [52.09480867526656]
  We identify the source of misalignment as a form of distributional shift and uncertainty in learning human preferences.<n>To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model.<n>Using the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines a preference optimization loss and a supervised learning loss.
  arXiv  Detail & Related papers  (2024-05-26T05:38:50Z)
• Towards Efficient Exact Optimization of Language Model Alignment [93.39181634597877]
  Direct preference optimization (DPO) was proposed to directly optimize the policy from preference data. We show that DPO derived based on the optimal solution of problem leads to a compromised mean-seeking approximation of the optimal solution in practice. We propose efficient exact optimization (EXO) of the alignment objective.
  arXiv  Detail & Related papers  (2024-02-01T18:51:54Z)

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.