Debiasing Large Language Models via Adaptive Causal Prompting with Sketch-of-Thought
This work addresses efficiency and generalizability issues in LLM prompting for diverse reasoning tasks, representing an incremental improvement over methods like Chain-of-Thought.
The paper tackled the problem of excessive token usage and limited generalizability in prompting methods for Large Language Models (LLMs) by proposing the Adaptive Causal Prompting with Sketch-of-Thought (ACPS) framework, which consistently outperformed existing baselines in accuracy, robustness, and computational efficiency across multiple reasoning benchmarks and LLMs.
Despite notable advancements in prompting methods for Large Language Models (LLMs), such as Chain-of-Thought (CoT), existing strategies still suffer from excessive token usage and limited generalisability across diverse reasoning tasks. To address these limitations, we propose an Adaptive Causal Prompting with Sketch-of-Thought (ACPS) framework, which leverages structural causal models to infer the causal effect of a query on its answer and adaptively select an appropriate intervention (i.e., standard front-door and conditional front-door adjustments). This design enables generalisable causal reasoning across heterogeneous tasks without task-specific retraining. By replacing verbose CoT with concise Sketch-of-Thought, ACPS enables efficient reasoning that significantly reduces token usage and inference cost. Extensive experiments on multiple reasoning benchmarks and LLMs demonstrate that ACPS consistently outperforms existing prompting baselines in terms of accuracy, robustness, and computational efficiency.