Recent advancements in large-scale models, such as GPT-4, have showcased remarkable capabilities in addressing standard queries. However, when facing complex problems that require multi-step logical reasoning, their accuracy dramatically decreases. Current research has explored the realm of prompting engineering to bolster the inferential capacities of these models. Our paper unveils a pioneering prompting technique, dubbed Graph of Thoughts (GoT). Through testing ona trio of escalating challenges: the 24-point game, resolution of high-degree polynomial equations, and derivation offormulas for recursive sequences, our method outperformedGPT-4, achieving accuracy improvements of 89.7%, 86%,and 56% for each respective task. Moreover, when juxtaposedwith the state-of-the-art (SOTA) prompting method, Tree ofThought (ToT), our approach registered an average accuracy boost of 23%, 24%, and 15%.
Latest posts by Ryan Watkins (see all)
- Risks and Opportunities of Open-Source Generative AI - May 15, 2024
- Is that a Guideline? Addressing Learning in Ethics Guidelines - May 10, 2024
- The Hazards of Putting Ethics on Autopilot - May 9, 2024