Humans outperform AI in Alibaba math competition
Although artificial intelligence has demonstrated capabilities surpassing humans in many fields, it still faces significant limitations in the realm of mathematics.
During the preliminary round of the 2024 Alibaba Global Mathematics Competition, 563 teams used AI to answer questions. Much to the surprise of AI advocates, none of the teams scored high enough to advance to the finals.
During the 48-hour preliminary round, AI and human participants were given the same exam questions, including multiple-choice, problem-solving and proof questions. AI teams were asked to submit their models in advance to avoid cheating.
According to the competition's organizing committee, the average score of the participating AI teams was 18, which was on par with the average level of human competitors. However, the highest score achieved by AI was only 34, which was far behind the highest human score of 113.
Chen Tianchu, who researches large models at the Computer Architecture Laboratory of Zhejiang University, said that the current working method of LLMs (large language models) is still to predict the next word at a fixed rate based on context and output the results all at once. For tasks that require repeated, multiple trials and thoughtful thinking, like math competitions, LLMs still have limitations in completing complex reasoning and rigorous thinking, The Economic Observer reported. He added that AI cannot yet replace professionally trained humans in math.
About half of the AI team members were born after 2000 and represented institutions such as Peking University, Tsinghua University, the University of Oxford, Amazon Web Services and ByteDance.
Some adjusted open-source large models, enabling AI to advance from elementary mathematics to advanced mathematics; some built AI agents, combining prompt engineering to access closed-source models like GPT-4, upgrading GPT-4's mathematical problem-solving abilities.
Tu Jinhao from Jianping High School in Shanghai achieved the highest score by using AI. Drawing inspiration from the concept of self-debate, Tu applied multiple large models to several rounds of "self-questioning, self-answering, self-verification" to seek the optimal solution to problems.
The top three AI teams earned prizes of $10,000, $5,000 and $2,000.
According to the organizing committee, the annual event will continue to open to AI to encourage exploration of its potential limits and drive research and innovation in its application in mathematics.
Yin Wotao, a member of the committee, said in an interview with Shanghai Securities News that it is a positive attempt to break through the limits of AI capabilities and bring more possibilities.