Adding only a small fraction of ranking data to the training blend enabled instruction-tuned LLMs to outperform existing expert ranking models.
Sources
- unifying context ranking with retrieval-augmented generation in LLMs (dl.acm.org)
- https://arxiv.org/abs/2407.02485 (arxiv.org)
- https://openreview.net/forum?id=S1fc92uemC (openreview.net)
- https://proceedings.neurips.cc//paper_files/paper/2024/hash/db93ccb6cf392f352570dd5af0a223d3-Abstract-Conference.html (proceedings.neurips.cc)
- https://simg.baai.ac.cn/paperfile/68c487ed-fafd-4bac-81e0-f8be1b56e845.pdf (simg.baai.ac.cn)
More in Technology
- The first email spam was sent in 1978 by a DEC marketing representative to 400 ARPANET users advertising computers.
- The paper introduces the concept of 'time series discords,' defined as subsequences of a longer time series that are maximally different from all other subsequences of that series.
- California's attempted AI legislation defined anyone investing more than $10 million in fine-tuning a model as a 'developer'.
- The paper 'Harmonising Artificial Intelligence' was published by Oxford Information Labs in 2021.
- In 2019, only 2.4% of new U.S.-resident PhD graduates in artificial intelligence were Black and 3.2% were Hispanic, according to a Computing Research Association survey.
- Google's smile-detection model used a racial classifier trained on four race subgroups and a gender classifier with two categories.