Self-Improvement Towards Pareto Optimality: Mitigating Preference Conflicts in Multi-Objective Alignment

• URL: http://arxiv.org/abs/2502.14354v1
• Date: Thu, 20 Feb 2025 08:27:00 GMT
• Title: Self-Improvement Towards Pareto Optimality: Mitigating Preference Conflicts in Multi-Objective Alignment
• Authors: Moxin Li, Yuantao Zhang, Wenjie Wang, Wentao Shi, Zhuo Liu, Fuli Feng, Tat-Seng Chua,
• Abstract summary: Multi-Objective Alignment (MOA) aims to align responses with multiple human preference objectives. We find that DPO-based MOA approaches suffer from widespread preference conflicts in the data.
• Score: 74.25832963097658
• License:
• Abstract: Multi-Objective Alignment (MOA) aims to align LLMs' responses with multiple human preference objectives, with Direct Preference Optimization (DPO) emerging as a prominent approach. However, we find that DPO-based MOA approaches suffer from widespread preference conflicts in the data, where different objectives favor different responses. This results in conflicting optimization directions, hindering the optimization on the Pareto Front. To address this, we propose to construct Pareto-optimal responses to resolve preference conflicts. To efficiently obtain and utilize such responses, we propose a self-improving DPO framework that enables LLMs to self-generate and select Pareto-optimal responses for self-supervised preference alignment. Extensive experiments on two datasets demonstrate the superior Pareto Front achieved by our framework compared to various baselines. Code is available at \url{https://github.com/zyttt-coder/SIPO}.

Related papers

• 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)
• Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization [75.1240295759264]
  We propose an effective framework for Bridging and Modeling Correlations in pairwise data, named BMC. We increase the consistency and informativeness of the pairwise preference signals through targeted modifications. We identify that DPO alone is insufficient to model these correlations and capture nuanced variations.
  arXiv  Detail & Related papers  (2024-08-14T11:29:47Z)
• mDPO: Conditional Preference Optimization for Multimodal Large Language Models [52.607764280030196]
  Direct preference optimization (DPO) has shown to be an effective method for large language model (LLM) alignment. Recent works have attempted to apply DPO to multimodal scenarios but have found it challenging to achieve consistent improvement. We propose mDPO, a multimodal DPO objective that prevents the over-prioritization of language-only preferences by also optimizing image preference.
  arXiv  Detail & Related papers  (2024-06-17T17:59:58Z)
• 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)
• Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization [105.3612692153615]
  We propose a new axis based on eliciting preferences jointly over instruction-response pairs. Joint preferences over instruction and response pairs can significantly enhance the alignment of large language models.
  arXiv  Detail & Related papers  (2024-03-31T02:05:40Z)
• Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment [103.12563033438715]
  Alignment in artificial intelligence pursues consistency between model responses and human preferences as well as values. Existing alignment techniques are mostly unidirectional, leading to suboptimal trade-offs and poor flexibility over various objectives. We introduce controllable preference optimization (CPO), which explicitly specifies preference scores for different objectives.
  arXiv  Detail & Related papers  (2024-02-29T12:12:30Z)
• 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)
• Multi-Objective Bayesian Optimization with Active Preference Learning [18.066263838953223]
  We propose a Bayesian optimization (BO) approach to identifying the most preferred solution in a multi-objective optimization (MOO) problem. To minimize the interaction cost with the decision maker (DM), we also propose an active learning strategy for the preference estimation.
  arXiv  Detail & Related papers  (2023-11-22T15:24:36Z)

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.