Loading...
Market
Which type of data will STaRK primarily utilize by end of 2024?
4
Resolution / Starting Odds
Textual Data • 25%
Structured Data • 25%
Semi-Structured Data • 25%
Unstructured Data • 25%
Technical reviews, usage reports, or Amazon's detailed use-case studies
Story
STaRK: New LLM Benchmark for Semi-Structured Data Released by Amazon, Researchers
Apr 29, 2024, 04:11 PM
In a collaborative effort with Amazon, researchers have developed and released STaRK, a new large-scale Language Model (LLM) retrieval benchmark designed to address the challenges of semi-structured knowledge bases. STaRK aims to reduce LLM hallucinations by utilizing Retrieval-Augmented Generation (RAG) over both textual and structured knowledge bases, enhancing the model's ability to handle complex real-world data. The benchmark includes datasets from diverse fields such as e-commerce, biomedicine, and academic research, facilitating advancements in semantic retrieval and reasoning while tackling more intricate user queries.
View original story
Similar markets
Movie recommendations • 33%
TV show recommendations • 33%
Content search by genre • 33%
Increase in usage • 33%
Decrease in usage • 33%
No significant change • 34%
Less than 10% • 25%
10% to 20% • 25%
20% to 30% • 25%
More than 30% • 25%
StarkWare • 33%
Ethereum Foundation • 33%
Other • 33%
Increase in investment • 25%
Stable investment levels • 25%
Decrease in investment • 25%
Significant new partnerships • 25%
AWS • 33%
Advertising • 33%
AI Initiatives • 34%
Streaming pause ad placement • 33%
Interactive shopping ads • 33%
Traditional video ads • 34%
SQL generation • 33%
Coding • 33%
Language translation • 34%
Yes • 50%
No • 50%
Data Privacy • 25%
Customer Service • 25%
Predictive Analytics • 25%
Other • 25%