Language Models

By Jordan Boyd-Graber, Philipp Koehn. 2009

Subfields: Large Language Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Large Language Models

1. Timo Schick
2. Hinrich Schütze
3. Mohit Bansal
4. Jaemin Cho
5. Yi-Lin Sung
6. Helmut Schmid
7. Luke S. Zettlemoyer
8. Jie Tang

Citations in the corpus

• LongForm: Effective Instruction Tuning with Reverse Instructions (2023, neutral): “For a more uniform distribution across datasets, we sample a similar number from each dataset, resulting in 600 samples from BigBench and 3,684 from NIv2.”
• VL-ADAPTER: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks (2021, background): “Several papers accordingly propose new architectures and objectives to model language, such as ELMo [35], BERT [8], RoBERTa [31], GPT series [4,38,39], and encoder-decoder versions such as BART [25] and T5 [40].”
• Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification (2020, methodology): “, by appending an instruction such as “translate into French”) so that they can directly be solved by a pretrained language model (Radford et al., 2019; Schick and Schütze, 2020a; Brown et al., 2020).”