Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization
This addresses the challenge of aligning language models for complex reasoning tasks, offering a more efficient alternative to resource-intensive methods, though it appears incremental as it builds on existing RL frameworks.
The paper tackled the problem of improving language models' multi-step reasoning abilities by introducing Direct Q-function Optimization (DQO), which outperformed previous methods on math problem-solving datasets GSM8K and MATH.
Reinforcement Learning (RL) plays a crucial role in aligning large language models (LLMs) with human preferences and improving their ability to perform complex tasks. However, current approaches either require significant computational resources due to the use of multiple models and extensive online sampling for training (e.g., PPO) or are framed as bandit problems (e.g., DPO, DRO), which often struggle with multi-step reasoning tasks, such as math problem solving and complex reasoning that involve long chains of thought. To overcome these limitations, we introduce Direct Q-function Optimization (DQO), which formulates the response generation process as a Markov Decision Process (MDP) and utilizes the soft actor-critic (SAC) framework to optimize a Q-function directly parameterized by the language model. The MDP formulation of DQO offers structural advantages over bandit-based methods, enabling more effective process supervision. Experimental results on two math problem-solving datasets, GSM8K and MATH, demonstrate that DQO outperforms previous methods, establishing it as a promising offline reinforcement learning approach for aligning language models.