Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game
- URL: http://arxiv.org/abs/2311.08045v4
- Date: Mon, 3 Jun 2024 11:34:05 GMT
- Title: Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game
- Authors: Pengyu Cheng, Yifan Yang, Jian Li, Yong Dai, Tianhao Hu, Peixin Cao, Nan Du, Xiaolong Li,
- Abstract summary: We propose an Adversarial Preference Optimization (APO) framework to target more efficient human preference optimization.
We find the proposed adversarial training framework further enhances existing alignment baselines in terms of LLM helpfulness and harmlessness.
- Score: 31.66896160733569
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Human preference alignment is essential to improve the interaction quality of large language models (LLMs). Existing alignment methods depend on manually annotated preference data to guide the LLM optimization directions. However, continuously updating LLMs for alignment raises a distribution gap between model-generated samples and human-annotated responses, hindering training effectiveness. To mitigate this issue, previous methods require additional preference annotation on newly generated samples to adapt to the shifted distribution, which consumes a large amount of annotation resources. Targeting more efficient human preference optimization, we propose an Adversarial Preference Optimization (APO) framework, in which the LLM and the reward model update alternatively via a min-max game. Through adversarial training, the reward model can adapt to the shifted generation distribution of the LLM without any additional annotation. With comprehensive experiments, we find the proposed adversarial training framework further enhances existing alignment baselines in terms of LLM helpfulness and harmlessness. The code is at https://github.com/Linear95/APO.
Related papers
- 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) - RosePO: Aligning LLM-based Recommenders with Human Values [38.029251417802044]
We propose a general framework -- Recommendation with smoothing personalized Preference Optimization (RosePO)
RosePO better aligns with customized human values during the post-training stage.
Evaluation on three real-world datasets demonstrates the effectiveness of our method.
arXiv Detail & Related papers (2024-10-16T12:54:34Z) - Self-supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness [27.43137305486112]
We propose a novel Self-supervised Preference Optimization (SPO) framework, which constructs a self-supervised preference degree loss combined with the alignment loss.
The results demonstrate that SPO can be seamlessly integrated with existing preference optimization methods to achieve state-of-the-art performance.
arXiv Detail & Related papers (2024-09-26T12:37:26Z) - TSO: Self-Training with Scaled Preference Optimization [14.3799656174528]
We propose TSO, a framework for preference optimization that conducts self-training preference learning without training an additional reward model.
TSO enhances the diversity of responses by constructing a model matrix and incorporating human preference responses.
Experimental results demonstrate that TSO outperforms existing mainstream methods on various alignment evaluation benchmarks.
arXiv Detail & Related papers (2024-08-31T05:37:01Z) - Aligning Large Language Models via Fine-grained Supervision [20.35000061196631]
Pre-trained large-scale language models (LLMs) excel at producing coherent articles, yet their outputs may be untruthful, toxic, or fail to align with user expectations.
Current approaches focus on using reinforcement learning with human feedback to improve model alignment.
We propose a method to enhance LLM alignment through fine-grained token-level supervision.
arXiv Detail & Related papers (2024-06-04T20:21:45Z) - Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment [104.18002641195442]
We introduce Self-Augmented Preference Optimization (SAPO), an effective and scalable training paradigm that does not require existing paired data.
Building on the self-play concept, which autonomously generates negative responses, we further incorporate an off-policy learning pipeline to enhance data exploration and exploitation.
arXiv Detail & Related papers (2024-05-31T14:21:04Z) - Self-Exploring Language Models: Active Preference Elicitation for Online Alignment [88.56809269990625]
We propose a bilevel objective optimistically biased towards potentially high-reward responses to actively explore out-of-distribution regions.
Our experimental results demonstrate that when fine-tuned on Zephyr-7B-SFT and Llama-3-8B-Instruct models, Self-Exploring Language Models (SELM) significantly boosts the performance on instruction-following benchmarks.
arXiv Detail & Related papers (2024-05-29T17:59:07Z) - Multi-Reference Preference Optimization for Large Language Models [56.84730239046117]
We introduce a novel closed-form formulation for direct preference optimization using multiple reference models.
The resulting algorithm, Multi-Reference Preference Optimization (MRPO), leverages broader prior knowledge from diverse reference models.
Our experiments demonstrate that LLMs finetuned with MRPO generalize better in various preference data, regardless of data scarcity or abundance.
arXiv Detail & Related papers (2024-05-26T00:29:04Z) - Weak-to-Strong Extrapolation Expedites Alignment [135.12769233630362]
We propose a method called ExPO to boost models' alignment with human preference.
We demonstrate that ExPO consistently improves off-the-shelf DPO/RLHF models.
We shed light on the essence of ExPO amplifying the reward signal learned during alignment training.
arXiv Detail & Related papers (2024-04-25T17:39:50Z) - Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts [95.09994361995389]
Relative Preference Optimization (RPO) is designed to discern between more and less preferred responses derived from both identical and related prompts.
RPO has demonstrated a superior ability to align large language models with user preferences and to improve their adaptability during the training process.
arXiv Detail & Related papers (2024-02-12T22:47:57Z)
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.