Direct Multi-Turn Preference Optimization for Language Agents
This work provides an incremental improvement for researchers and practitioners adapting LLMs to multi-turn agent tasks, enhancing optimization techniques.
The paper tackled the challenge of applying Direct Preference Optimization (DPO) to multi-turn language agent tasks by developing DMPO, a novel loss function that addresses partition function and length disparity issues, achieving superior performance on three datasets.
Adapting Large Language Models (LLMs) for agent tasks is critical in developing language agents. Direct Preference Optimization (DPO) is a promising technique for this adaptation with the alleviation of compounding errors, offering a means to directly optimize Reinforcement Learning (RL) objectives. However, applying DPO to multi-turn tasks presents challenges due to the inability to cancel the partition function. Overcoming this obstacle involves making the partition function independent of the current state and addressing length disparities between preferred and dis-preferred trajectories. In this light, we replace the policy constraint with the state-action occupancy measure constraint in the RL objective and add length normalization to the Bradley-Terry model, yielding a novel loss function named DMPO for multi-turn agent tasks with theoretical explanations. Extensive experiments on three multi-turn agent task datasets confirm the effectiveness and superiority of the DMPO loss. The code is available at https://github.com/swt-user/DMPO.