DAWN-ICL: Strategic Planning of Problem-solving Trajectories for Zero-Shot In-Context Learning
Tang, Xinyu, Wang, Xiaolei, Zhao, Wayne Xin, Wen, Ji-Rong
–arXiv.org Artificial Intelligence
Zero-shot in-context learning (ZS-ICL) aims to conduct in-context learning (ICL) without using human-annotated demonstrations. Most ZS-ICL methods use large language models (LLMs) to generate (input, label) pairs as pseudo-demonstrations and leverage historical pseudo-demonstrations to help solve the current problem. They assume that problems are from the same task and traverse them in a random order. However, in real-world scenarios, problems usually come from diverse tasks, and only a few belong to the same task. The random traversing order may generate unreliable pseudo-demonstrations and lead to error accumulation. To address this problem, we reformulate ZS-ICL as a planning problem and propose a Demonstration-aware Monte Carlo Tree Search (MCTS) approach (DAWN-ICL), which leverages MCTS to strategically plan the problem-solving trajectories for ZS-ICL. In addition, to achieve effective and efficient Q value estimation, we propose a novel demonstration-aware Q-value function and use it to enhance the selection phase and accelerate the expansion and simulation phases in MCTS. Extensive experiments demonstrate the effectiveness and efficiency of DAWN-ICL on in-domain and cross-domain scenarios, and it even outperforms ICL using human-annotated labels. The code is available at https://github.com/RUCAIBox/MCTS4ZSICL.
arXiv.org Artificial Intelligence
Oct-26-2024
- Country:
- North America > United States (0.04)
- Asia
- British Indian Ocean Territory > Diego Garcia (0.04)
- China > Beijing
- Beijing (0.04)
- Genre:
- Research Report (0.64)
- Industry:
- Education > Curriculum > Subject-Specific Education (1.00)
- Technology: