DiPT: Enhancing LLM reasoning through diversified perspective-taking
This addresses reasoning limitations in large language models for AI applications, though it appears incremental as it complements existing methods rather than introducing a paradigm shift.
The paper tackles the problem of language model reasoning errors from single-solution approaches by introducing DiPT, which incorporates diversified viewpoints to enhance reasoning performance and stability, showing improved context understanding and safety against jailbreaking prompts.
Existing work on improving language model reasoning typically explores a single solution path, which can be prone to errors. Inspired by perspective-taking in social studies, this paper introduces DiPT, a novel approach that complements current reasoning methods by explicitly incorporating diversified viewpoints. This approach allows the model to gain a deeper understanding of the problem's context and identify the most effective solution path during the inference stage. Additionally, it provides a general data-centric AI recipe for augmenting existing data to improve their quality for fine-tuning. Our empirical results demonstrate that DiPT can be flexibly integrated into existing methods that focus on a single reasoning approach, enhancing their reasoning performance and stability when presented with paraphrased problems. Furthermore, we illustrate improved context understanding by maintaining the model's safe outputs against "jailbreaking" prompts intentionally designed to bypass safeguards built into deployed models. Lastly, we show that fine-tuning with data enriched with diverse perspectives can boost the reasoning capabilities of the model compared to fine-tuning with raw data alone.