Plug-and-Play Training Framework for Preference Optimization

• URL: http://arxiv.org/abs/2412.20996v1
• Date: Mon, 30 Dec 2024 15:01:48 GMT
• Title: Plug-and-Play Training Framework for Preference Optimization
• Authors: Jingyuan Ma, Rui Li, Zheng Li, Lei Sha, Zhifang Sui,
• Abstract summary: We propose a novel training framework for large language models (LLMs) This framework employs multiple sampling to analyze output distributions, assign different weights to samples, and incorporate these weights into the preference optimization process. Experimental results demonstrate that our framework integrates seamlessly with various preference optimization methods and achieves consistent improvements in mathematical reasoning tasks.
• Score: 25.53286104242179
• License:
• Abstract: Recently, preference optimization methods such as DPO have significantly enhanced large language models (LLMs) in wide tasks including dialogue and question-answering. However, current methods fail to account for the varying difficulty levels of training samples during preference optimization, leading to mediocre performance in tasks with high accuracy requirements, particularly in mathematical reasoning. To address this limitation, we propose a novel training framework, which employs multiple sampling to analyze output distributions, assign different weights to samples, and incorporate these weights into the preference optimization process. This plug-and-play approach enables LLMs to prioritize challenging examples during training, improving learning efficiency. Experimental results demonstrate that our framework integrates seamlessly with various preference optimization methods and achieves consistent improvements in mathematical reasoning tasks.

Related papers

• Multi-Response Preference Optimization with Augmented Ranking Dataset [2.8973004951877357]
  Preference optimization has played a significant role in improving the performance of Large Language Models. We propose a novel approach to augment Preference Optimization datasets. We also introduce a Multi-response-based Preference Optimization training method.
  arXiv  Detail & Related papers  (2024-12-10T05:45:36Z)
• Adaptive Optimization for Enhanced Efficiency in Large-Scale Language Model Training [3.668740611399284]
  Large-scale language models (LLM) have achieved remarkable results in a variety of tasks. This paper proposes an improved method based on adaptive optimization algorithm.
  arXiv  Detail & Related papers  (2024-12-06T02:17:30Z)
• Evolutionary Pre-Prompt Optimization for Mathematical Reasoning [45.461506988071534]
  This paper explores the optimization of example selection for designing effective chain-of-thought pre-prompts. It shows that the choice of the algorithm, typically in favor of comparison-based methods such as evolutionary computation, significantly enhances efficacy and feasibility.
  arXiv  Detail & Related papers  (2024-12-05T16:12:06Z)
• AIPO: Improving Training Objective for Iterative Preference Optimization [34.24211649396053]
  We study iterative preference optimization with synthetic data. We propose our training objective for iterative preference optimization, namely Agreement-aware Iterative Preference Optimization (AIPO)
  arXiv  Detail & Related papers  (2024-09-13T14:03:49Z)
• Learning Joint Models of Prediction and Optimization [56.04498536842065]
  Predict-Then-Then framework uses machine learning models to predict unknown parameters of an optimization problem from features before solving. This paper proposes an alternative method, in which optimal solutions are learned directly from the observable features by joint predictive models.
  arXiv  Detail & Related papers  (2024-09-07T19:52:14Z)
• Large Language Models Prompting With Episodic Memory [53.8690170372303]
  We propose PrOmpting with Episodic Memory (POEM), a novel prompt optimization technique that is simple, efficient, and demonstrates strong generalization capabilities. In the testing phase, we optimize the sequence of examples for each test query by selecting the sequence that yields the highest total rewards from the top-k most similar training examples in the episodic memory. Our results show that POEM outperforms recent techniques like TEMPERA and RLPrompt by over 5.3% in various text classification tasks.
  arXiv  Detail & Related papers  (2024-08-14T11:19:28Z)
• LLM as a Complementary Optimizer to Gradient Descent: A Case Study in Prompt Tuning [69.95292905263393]
  We show that gradient-based and high-level LLMs can effectively collaborate a combined optimization framework. In this paper, we show that these complementary to each other and can effectively collaborate a combined optimization framework.
  arXiv  Detail & Related papers  (2024-05-30T06:24:14Z)
• Federated Conditional Stochastic Optimization [110.513884892319]
  Conditional optimization has found in a wide range of machine learning tasks, such as in-variant learning tasks, AUPRC, andAML. This paper proposes algorithms for distributed federated learning.
  arXiv  Detail & Related papers  (2023-10-04T01:47:37Z)
• Consolidated learning -- a domain-specific model-free optimization strategy with examples for XGBoost and MIMIC-IV [4.370097023410272]
  This paper proposes a new formulation of the tuning problem, called consolidated learning. In such settings, we are interested in the total optimization time rather than tuning for a single task. We demonstrate the effectiveness of this approach through an empirical study for XGBoost algorithm and the collection of predictive tasks extracted from the MIMIC-IV medical database.
  arXiv  Detail & Related papers  (2022-01-27T21:38:53Z)
• Bayesian Optimization for Selecting Efficient Machine Learning Models [53.202224677485525]
  We present a unified Bayesian Optimization framework for jointly optimizing models for both prediction effectiveness and training efficiency. Experiments on model selection for recommendation tasks indicate models selected this way significantly improves model training efficiency.
  arXiv  Detail & Related papers  (2020-08-02T02:56:30Z)
• Automatically Learning Compact Quality-aware Surrogates for Optimization Problems [55.94450542785096]
  Solving optimization problems with unknown parameters requires learning a predictive model to predict the values of the unknown parameters and then solving the problem using these values. Recent work has shown that including the optimization problem as a layer in a complex training model pipeline results in predictions of iteration of unobserved decision making. We show that we can improve solution quality by learning a low-dimensional surrogate model of a large optimization problem.
  arXiv  Detail & Related papers  (2020-06-18T19:11:54Z)

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.