New Desiderata for Direct Preference Optimization
- URL: http://arxiv.org/abs/2407.09072v1
- Date: Fri, 12 Jul 2024 07:52:32 GMT
- Title: New Desiderata for Direct Preference Optimization
- Authors: Xiangkun Hu, Tong He, David Wipf,
- Abstract summary: We introduce new evaluation criteria that highlight unresolved shortcomings in the ability of existing DPO methods to interpolate between a pre-trained reference model and empirical measures of human preferences.
Our insights motivate an alternative DPO-like loss that provably mitigates these limitations.
- Score: 19.324743346476417
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large language models in the past have typically relied on some form of reinforcement learning with human feedback (RLHF) to better align model responses with human preferences. However, because of oft-observed instabilities when implementing these RLHF pipelines, various reparameterization techniques have recently been introduced to sidestep the need for separately learning an RL reward model. Instead, directly fine-tuning for human preferences is achieved via the minimization of a single closed-form training objective, a process originally referred to as direct preference optimization (DPO) and followed by several notable descendants. Although effective in certain real-world settings, we introduce new evaluation criteria that serve to highlight unresolved shortcomings in the ability of existing DPO methods to interpolate between a pre-trained reference model and empirical measures of human preferences, as well as unavoidable trade-offs in how low- and high-quality responses are regularized and constraints are handled. Our insights then motivate an alternative DPO-like loss that provably mitigates these limitations. Empirical results serve to corroborate notable aspects of our analyses.
Related papers
- The Hitchhiker's Guide to Human Alignment with *PO [43.4130314879284]
We focus on identifying the algorithm that, while being performant, is simultaneously more robust to varying hyper parameters.
Our analysis reveals that the widely adopted DPO method consistently produces lengthy responses of inferior quality.
Motivated by these findings, we propose an embarrassingly simple extension to the DPO algorithm, LN-DPO, resulting in more concise responses without sacrificing quality.
arXiv Detail & Related papers (2024-07-21T17:35:20Z) - Joint Demonstration and Preference Learning Improves Policy Alignment with Human Feedback [58.049113055986375]
We develop a single stage approach named Alignment with Integrated Human Feedback (AIHF) to train reward models and the policy.
The proposed approach admits a suite of efficient algorithms, which can easily reduce to, and leverage, popular alignment algorithms.
We demonstrate the efficiency of the proposed solutions with extensive experiments involving alignment problems in LLMs and robotic control problems in MuJoCo.
arXiv Detail & Related papers (2024-06-11T01:20:53Z) - Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF [82.7679132059169]
Reinforcement learning from human feedback has emerged as a central tool for language model alignment.
We propose a new algorithm for online exploration in RLHF, Exploratory Preference Optimization (XPO)
XPO enjoys the strongest known provable guarantees and promising empirical performance.
arXiv Detail & Related papers (2024-05-31T17:39:06Z) - 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.
To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model.
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) - 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) - LIRE: listwise reward enhancement for preference alignment [27.50204023448716]
We propose a gradient-based reward optimization approach that incorporates the offline rewards of multiple responses into a streamlined listwise framework.
LIRE is straightforward to implement, requiring minimal parameter tuning, and seamlessly aligns with the pairwise paradigm.
Our experiments demonstrate that LIRE consistently outperforms existing methods across several benchmarks on dialogue and summarization tasks.
arXiv Detail & Related papers (2024-05-22T10:21:50Z) - RS-DPO: A Hybrid Rejection Sampling and Direct Preference Optimization Method for Alignment of Large Language Models [7.676477609461592]
Reinforcement learning from human feedback (RLHF) has been extensively employed to align large language models with user intent.
DPO relies on contrastive responses generated from human annotator and alternative LLM, instead of the policy model.
In this paper, we address both challenges by systematically combining sampling rejection (RS) and DPO.
Our proposed method effectively fine-tunes LLMs with limited resource environments, leading to improved alignment with user intent.
arXiv Detail & Related papers (2024-02-15T16:00:58Z) - Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint [56.74058752955209]
This paper studies the alignment process of generative models with Reinforcement Learning from Human Feedback (RLHF)
We first identify the primary challenges of existing popular methods like offline PPO and offline DPO as lacking in strategical exploration of the environment.
We propose efficient algorithms with finite-sample theoretical guarantees.
arXiv Detail & Related papers (2023-12-18T18:58:42Z) - Statistical Rejection Sampling Improves Preference Optimization [42.57245965632205]
We introduce a novel approach to source preference data from the target optimal policy using rejection sampling.
We also propose a unified framework that enhances the loss functions used in both Sequence Likelihood (SLiC) and Direct Preference Optimization (DPO) from a preference modeling standpoint.
arXiv Detail & Related papers (2023-09-13T01:07:25Z) - Direct Preference Optimization: Your Language Model is Secretly a Reward
Model [126.78737228677025]
We introduce a new parameterization of the reward model in RLHF that enables extraction of the corresponding optimal policy in closed form.
The resulting algorithm, which we call Direct Preference Optimization (DPO), is stable, performant, and computationally lightweight.
Our experiments show that DPO can fine-tune LMs to align with human preferences as well as or better than existing methods.
arXiv Detail & Related papers (2023-05-29T17:57:46Z)
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.