UniAPL: A Unified Adversarial Preference Learning Framework for Instruct-Following

• URL: http://arxiv.org/abs/2509.25148v1
• Date: Mon, 29 Sep 2025 17:53:09 GMT
• Title: UniAPL: A Unified Adversarial Preference Learning Framework for Instruct-Following
• Authors: FaQiang Qian, WeiKun Zhang, Ziliang Wang, Kang An, Xuhui Zheng, Liangjian Wen, Mengya Gao, Yong Dai, Yichao Wu,
• Abstract summary: We argue that post-training alignment is fundamentally a unified Preference Learning problem.<n>UniAPL implements a single-stage unified training objective, jointly learning from mixed batches of SFT and preference data.
• Score: 12.924923059340395
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Shaping powerful LLMs to be beneficial and safe is central to AI alignment. We argue that post-training alignment is fundamentally a unified Preference Learning problem, involving two modalities: demonstrated preferences (e.g., Supervised Fine-Tuning, SFT) and comparative preferences (e.g., Reinforcement Learning, RL).The standard sequential pipeline-SFT followed by RL-is flawed due to a critical distributional mismatch: SFT uses static expert data, but as the policy evolves, its generation distribution drifts, making SFT knowledge brittle. Subsequent RL then explores without direct access to the rich, ground-truth knowledge in expert demonstrations, leading to inefficient, ungrounded updates. This separation prevents mutual regularization between data sources. To address this, we reframe alignment as a constrained optimization problem and propose Unified Adversarial Preference Learning (UniAPL),a novel framework that dynamically aligns the policy's distribution with the expert's. UniAPL implements a single-stage unified training objective, jointly learning from mixed batches of SFT and preference data. In every gradient step, dense expert demonstrations directly ground and regularize online exploration, inherently resolving distributional mismatch and maximizing data synergy.We evaluate UniAPL on instruction-following tasks using Qwen3-235B-Instruct-2507 as the teacher. Our models match or exceed strong GRPO baselines: +5.77% on Qwen3-0.6B (matching a 32B model) and +3.75% on Qwen3-4B,even outperforming the teacher. Analyses of response length and log-probability distributions confirm that UniAPL outputs closely mimic expert demonstrations, achieving both stronger performance and better behavioral alignment.

Related papers

• Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training [61.1421888242439]
  Supervised fine-tuning (SFT) is computationally efficient but often yields inferior generalization compared to reinforcement learning (RL)<n>We propose a framework to bridge this chasm by enabling On-Policy SFT.
  arXiv  Detail & Related papers  (2026-02-12T17:59:58Z)
• Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only [70.43369087819332]
  Supervised fine-tuning (SFT) has emerged as a crucial method for aligning large language models with human-annotated demonstrations.<n>We propose Self-Rewarding PPO, a novel fine-tuning method that leverages on-policy techniques to enhance generalization performance.
  arXiv  Detail & Related papers  (2025-10-24T02:02:13Z)
• Mind the Gap: Data Rewriting for Stable Off-Policy Supervised Fine-Tuning [33.899779762210976]
  Supervised fine-tuning (SFT) of large language models can be viewed as an off-policy learning problem.<n>Existing methods mitigate this issue with KL penalties or clipping, which passively updates rather than actively reducing the gap.<n>We propose a simple yet effective data rewriting framework that proactively shrinks the policy gap before training.
  arXiv  Detail & Related papers  (2025-09-18T17:02:30Z)
• 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)
• Bridging Supervised Learning and Reinforcement Learning in Math Reasoning [55.889740979706815]
  Reinforcement Learning (RL) has played a central role in the recent surge of math abilities by enabling self-improvement through binary verifier signals.<n>In this work, we propose Negative-aware Fine-Tuning (NFT) -- a supervised approach that enables LLMs to reflect on their failures and improve autonomously with no external teachers.
  arXiv  Detail & Related papers  (2025-05-23T17:17:40Z)
• All Roads Lead to Likelihood: The Value of Reinforcement Learning in Fine-Tuning [40.93098780862429]
  We show that the strongest results in foundation model fine-tuning (FT) are achieved via a relatively complex, two-stage training procedure.<n>One first trains a reward model (RM) on some dataset (e.g. human preferences) before using it to provide online feedback as part of a downstream reinforcement learning procedure.<n>We find the most support for the explanation that on problems with a generation-verification gap, the combination of the ease of learning the relatively simple RM from the preference data, and the ability of the downstream RL procedure to then filter its search space to the subset of policies that are optimal for
  arXiv  Detail & Related papers  (2025-03-03T00:15:19Z)
• SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning [3.4023074295549014]
  Subtask-oriented Reinforced Fine-Tuning (SoRFT) is a novel training approach to enhance the issue resolving capability of LLMs.<n>We evaluate the SoRFT-trained model on SWE-Bench Verified and SWE-Bench Lite, achieving state-of-the-art (SOTA) performance among open-source models.
  arXiv  Detail & Related papers  (2025-02-27T14:19:45Z)
• A Systematic Examination of Preference Learning through the Lens of Instruction-Following [83.71180850955679]
  We use a novel synthetic data generation pipeline to generate 48,000 instruction unique-following prompts.<n>With our synthetic prompts, we use two preference dataset curation methods - rejection sampling (RS) and Monte Carlo Tree Search (MCTS)<n>Experiments reveal that shared prefixes in preference pairs, as generated by MCTS, provide marginal but consistent improvements.<n>High-contrast preference pairs generally outperform low-contrast pairs; however, combining both often yields the best performance.
  arXiv  Detail & Related papers  (2024-12-18T15:38:39Z)
• Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment [105.34140537748546]
  We propose an improved alignment approach named FIGA. Different from prior methods, we incorporate fine-grained quality signals that are derived by contrasting good and bad responses. Our approach has made two major contributions. Firstly, we curate a refined alignment dataset that pairs initial responses and the corresponding revised ones. Secondly, we devise a new loss function can leverage fine-grained quality signals to instruct the learning of LLMs for alignment.
  arXiv  Detail & Related papers  (2023-11-07T15:36:40Z)

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.