Step-level Value Preference Optimization for Mathematical Reasoning
- URL: http://arxiv.org/abs/2406.10858v1
- Date: Sun, 16 Jun 2024 09:06:17 GMT
- Title: Step-level Value Preference Optimization for Mathematical Reasoning
- Authors: Guoxin Chen, Minpeng Liao, Chengxi Li, Kai Fan,
- Abstract summary: We introduce a novel algorithm called Step-level Value Preference Optimization (SVPO)
Our approach employs Monte Carlo Tree Search (MCTS) to automatically annotate step-level preferences for multi-step reasoning.
From the perspective of learning-to-rank, we train an explicit value model to replicate the behavior of the implicit reward model.
- Score: 6.318873143509028
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Direct Preference Optimization (DPO) using an implicit reward model has proven to be an effective alternative to reinforcement learning from human feedback (RLHF) for fine-tuning preference aligned large language models (LLMs). However, the overall preference annotations of responses do not fully capture the fine-grained quality of model outputs in complex multi-step reasoning tasks, such as mathematical reasoning. To address this limitation, we introduce a novel algorithm called Step-level Value Preference Optimization (SVPO). Our approach employs Monte Carlo Tree Search (MCTS) to automatically annotate step-level preferences for multi-step reasoning. Furthermore, from the perspective of learning-to-rank, we train an explicit value model to replicate the behavior of the implicit reward model, complementing standard preference optimization. This value model enables the LLM to generate higher reward responses with minimal cost during inference. Experimental results demonstrate that our method achieves state-of-the-art performance on both in-domain and out-of-domain mathematical reasoning benchmarks.
Related papers
- 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-Exploring Language Models: Active Preference Elicitation for Online Alignment [90.4820014819937]
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 finetuned on Zephyr-7B-SFT and Llama-3-8B-Instruct models, SELM significantly boosts the performance on instruction-following benchmarks.
arXiv Detail & Related papers (2024-05-29T17:59:07Z) - 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) - Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning [55.96599486604344]
We introduce an approach aimed at enhancing the reasoning capabilities of Large Language Models (LLMs) through an iterative preference learning process.
We use Monte Carlo Tree Search (MCTS) to iteratively collect preference data, utilizing its look-ahead ability to break down instance-level rewards into more granular step-level signals.
The proposed algorithm employs Direct Preference Optimization (DPO) to update the LLM policy using this newly generated step-level preference data.
arXiv Detail & Related papers (2024-05-01T11:10:24Z) - Soft Preference Optimization: Aligning Language Models to Expert Distributions [40.84391304598521]
SPO is a method for aligning generative models, such as Large Language Models (LLMs), with human preferences.
SPO integrates preference loss with a regularization term across the model's entire output distribution.
We showcase SPO's methodology, its theoretical foundation, and its comparative advantages in simplicity, computational efficiency, and alignment precision.
arXiv Detail & Related papers (2024-04-30T19:48:55Z) - Let's reward step by step: Step-Level reward model as the Navigators for
Reasoning [64.27898739929734]
Process-Supervised Reward Model (PRM) furnishes LLMs with step-by-step feedback during the training phase.
We propose a greedy search algorithm that employs the step-level feedback from PRM to optimize the reasoning pathways explored by LLMs.
To explore the versatility of our approach, we develop a novel method to automatically generate step-level reward dataset for coding tasks and observed similar improved performance in the code generation tasks.
arXiv Detail & Related papers (2023-10-16T05:21:50Z) - When to Update Your Model: Constrained Model-based Reinforcement
Learning [50.74369835934703]
We propose a novel and general theoretical scheme for a non-decreasing performance guarantee of model-based RL (MBRL)
Our follow-up derived bounds reveal the relationship between model shifts and performance improvement.
A further example demonstrates that learning models from a dynamically-varying number of explorations benefit the eventual returns.
arXiv Detail & Related papers (2022-10-15T17:57:43Z) - SimPO: Simultaneous Prediction and Optimization [3.181417685380586]
We propose a formulation for the Simultaneous Prediction and Optimization (SimPO) framework.
This framework introduces the use of a joint weighted loss of a decision-driven predictive ML model and an optimization objective function.
arXiv Detail & Related papers (2022-03-31T20:01:36Z)
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.