Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts
- URL: http://arxiv.org/abs/2402.10958v2
- Date: Mon, 27 May 2024 20:05:03 GMT
- Title: Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts
- Authors: Yueqin Yin, Zhendong Wang, Yi Gu, Hai Huang, Weizhu Chen, Mingyuan Zhou,
- Abstract summary: 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.
- Score: 95.09994361995389
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In the field of large language models (LLMs), aligning models with the diverse preferences of users is a critical challenge. Direct Preference Optimization (DPO) has played a key role in this area. It works by using pairs of preferences derived from the same prompts, and it functions without needing an additional reward model. However, DPO does not fully reflect the complex nature of human learning, which often involves understanding contrasting responses to not only identical but also similar questions. To overcome this shortfall, we propose Relative Preference Optimization (RPO). RPO is designed to discern between more and less preferred responses derived from both identical and related prompts. It introduces a contrastive weighting mechanism, enabling the tuning of LLMs using a broader range of preference data, including both paired and unpaired sets. This approach expands the learning capabilities of the model, allowing it to leverage insights from a more varied set of prompts. Through empirical tests, including dialogue and summarization tasks, and evaluations using the AlpacaEval2.0 leaderboard, RPO has demonstrated a superior ability to align LLMs with user preferences and to improve their adaptability during the training process. Our code can be viewed at https://github.com/yinyueqin/relative-preference-optimization
Related papers
- Adaptive Preference Scaling for Reinforcement Learning with Human Feedback [103.36048042664768]
Reinforcement learning from human feedback (RLHF) is a prevalent approach to align AI systems with human values.
We propose a novel adaptive preference loss, underpinned by distributionally robust optimization (DRO)
Our method is versatile and can be readily adapted to various preference optimization frameworks.
arXiv Detail & Related papers (2024-06-04T20:33:22Z) - 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) - Hybrid Preference Optimization: Augmenting Direct Preference Optimization with Auxiliary Objectives [0.5120567378386615]
We propose a hybrid approach to aligning large language models (LLMs)
With a simple augmentation to the implicit reward decomposition of DPO, we allow for tuning LLMs to maximize a set of arbitrary auxiliary rewards.
The proposed method, Hybrid Preference Optimization (HPO), shows the ability to effectively generalize to both user preferences and auxiliary designer objectives.
arXiv Detail & Related papers (2024-05-28T08:35:48Z) - Self-Play Preference Optimization for Language Model Alignment [75.83359213697854]
Recent advancements suggest that directly working with preference probabilities can yield a more accurate reflection of human preferences.
We propose a self-play-based method for language model alignment, which treats the problem as a constant-sum two-player game.
Our approach, dubbed Self-Play Preference Optimization (SPPO), approximates the Nash equilibrium through iterative policy updates.
arXiv Detail & Related papers (2024-05-01T17:59:20Z) - Token-level Direct Preference Optimization [8.249403373337024]
Fine-tuning pre-trained Large Language Models is essential to align them with human values and intentions.
We introduce Token-level Direct Preference Optimization (TDPO), a novel approach to align LLMs with human preferences by optimizing policy at the token level.
arXiv Detail & Related papers (2024-04-18T08:49:38Z) - Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization [105.3612692153615]
A common technique for aligning large language models (LLMs) relies on acquiring human preferences.
We propose a new axis that is based on eliciting preferences jointly over the instruction-response pairs.
We find that joint preferences over instruction and response pairs can significantly enhance the alignment of LLMs.
arXiv Detail & Related papers (2024-03-31T02:05:40Z) - LiPO: Listwise Preference Optimization through Learning-to-Rank [62.02782819559389]
Policy can learn more effectively from a ranked list of plausible responses given the prompt.
We show that LiPO-$lambda$ can outperform DPO variants and SLiC by a clear margin on several preference alignment tasks.
arXiv Detail & Related papers (2024-02-02T20:08:10Z) - Active Preference Inference using Language Models and Probabilistic Reasoning [13.523369679010685]
We introduce an inference-time algorithm that helps large language models infer user preferences.
Our algorithm uses a probabilistic model whose conditional distributions are defined by prompting an LLM.
Results in a simplified interactive web shopping setting with real product items show that an LLM equipped with our entropy reduction algorithm outperforms baselines.
arXiv Detail & Related papers (2023-12-19T09:58:54Z)
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.