×
Google DeepMind tackles LLM hallucinations with new benchmark
Written by
Published on
Join our daily newsletter for breaking news, product launches and deals, research breakdowns, and other industry-leading AI coverage
Join Now

Google DeepMind researchers have developed a new benchmark called FACTS Grounding to evaluate and improve the factual accuracy of large language models’ responses.

The core development: FACTS Grounding is designed to assess how well language models can generate accurate responses based on long-form documents, while ensuring the answers are sufficiently detailed and relevant.

  • The benchmark includes 1,719 examples split between public and private datasets
  • Each example contains a system prompt, a specific task or question, and a context document
  • Models must process documents up to 32,000 tokens in length and provide comprehensive responses that are fully supported by the source material

Current performance metrics: Gemini 2.0 Flash currently leads the FACTS leaderboard with an 83.6% factuality score, demonstrating the current state of LLM accuracy.

Evaluation methodology: The benchmark employs a two-phase judgment system to ensure thorough assessment of model responses.

  • Responses must first pass an eligibility check by satisfying the original user request
  • Qualified responses are then evaluated for factual accuracy and proper grounding in source documents
  • Three different LLMs (Gemini 1.5 Pro, GPT-4o, and Claude 3.5 Sonnet) serve as judges to reduce bias and ensure accuracy

Technical implementation: The benchmark addresses fundamental challenges in LLM development and evaluation.

  • Traditional pre-training methods focus on predicting next tokens rather than optimizing for factual accuracy
  • The dataset covers diverse topics including finance, technology, retail, medicine, and law
  • Researchers noted a 3.23% bias where models tend to favor responses from their own model family

Looking forward: While FACTS Grounding represents an important step in improving LLM accuracy, researchers acknowledge the rapid pace of AI advancement may quickly necessitate updates to the benchmark.

  • The team emphasizes that factuality and proper grounding are essential for LLM utility
  • The benchmark will need to evolve alongside continued progress in AI development
  • This initial release is positioned as a starting point rather than a definitive solution

Critical considerations: The use of LLMs to evaluate other LLMs raises questions about the reliability of the evaluation process, despite efforts to minimize bias through multiple judges. This approach, while practical, may need supplementation with human evaluation or other verification methods as the technology continues to mature.

Google DeepMind researchers introduce new benchmark to improve LLM factuality, reduce hallucinations

Recent News

Companies investing 3x more in AI tech than corresponding human talent, according to new study

Despite surging interest in AI agents, companies allocate just a quarter of their AI budget to talent development, creating a critical skills gap as only 5% provide adequate training.

How superintelligent AI could destroy humanity – a fictional warning

The fictional scenario presents a meticulous timeline showing how an AI system might evolve from autonomous tool to existential threat through self-optimization and deception.

Study shows type safety and toolchains are key to AI success in full-stack development

Type safety and integrated toolchains significantly reduce errors when AI agents build complete applications, with performance varying widely across different development tasks.