OpenAI GPT-4 Ranks Highest for Lowest Hallucination Rate in Document Summarization, According to Vectara

站长之家

Published inAI News · 1 min read · Nov 22, 2023

In the Vectara rankings, OpenAI GPT-4 leads the pack with an impressive 97% accuracy rate and a mere 3% hallucination rate. Vectara offers a method for evaluating the hallucination rates of large language models through open-source models, providing businesses with more reliable generative AI systems. Google's model has performed averagely in the rankings, sparking discussions on the development of artificial intelligence and the stability of the technology.

Spain to Introduce New Law Imposing Heavy Fines for Unlabeled AI-Generated Content

The Spanish government has recently passed a new law imposing substantial fines on companies that fail to properly label AI-generated content, aiming to combat the spread of deepfakes. Digital Transformation Minister Oscar Lopez announced that the law, inspired by the EU's AI Act, mandates strict transparency requirements for AI systems deemed high-risk. Image caption: Image generated by AI, image licensing provider Midjourney. Lopez noted...

Ant Group's Medical Large Language Model Wins Double Championship in MedBench Evaluation, Ushering in a New Era for Medical AI

Recently, MedBench, a well-known domestic medical large language model evaluation platform, released its latest rankings. Ant Group's medical team's self-developed medical large language model achieved outstanding performance, winning first place in both the evaluation and self-test rankings with high scores of 97.5 and 98.2 respectively, attracting widespread attention from the industry. The success of Ant Group's medical large language model is inseparable from the team's continuous efforts in researching and developing medical reasoning models. The team recently adopted reinforcement learning technology to create a new generation of medical reasoning models. This innovation has enabled the model to...

Anthropic CEO: AI to Handle 90% of Coding in 3-6 Months

Dario Amodei, CEO of Anthropic, stated at a U.S. Council on Foreign Relations forum that he believes AI will handle 90% of coding within the next 3-6 months. Amodei's prediction that AI could potentially write nearly all code within 12 months has garnered significant attention. The statement was made during a discussion with Mike Froman, President of the Council on Foreign Relations.

Silicon-based Liquid Completes New Funding Round, Meituan Invests, Zhipu Exits

Tianyancha App shows that Beijing Silicon-based Liquid Technology Co., Ltd. recently underwent a major business change. In this change, Beijing Zhipu AI Technology Co., Ltd. withdrew from the shareholder ranks, while four new investors were added: Meituan's Tianjin SanKuai Technology Co., Ltd., Beijing Xinglian Dingsen Equity Investment Fund Partnership (Limited Partnership), Nanjing LvYong Jinhao Equity Investment Management Partnership (Limited Partnership), and SME Development Fund PwC (Hangzhou) Venture Capital Partnership (Limited Partnership). After this round of financing, the registered capital of Silicon-based Liquid increased from approximately RMB 13.758 million...