Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning

57 citations recorded by the source corpus.

How researchers see this paper

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

The Flan Collection: Designing Data and Methods for Effective Instruction Tuning (2023, background): “New Directions Concurrent and future work is beginning to explore two new directions: (a) expanding task diversity evenmore aggressively with synthetic data generation, particularly in creative, and open-ended dialogue (Wang et al., 2022b; Honovich et al., 2022; Ye et al., 2022; Gupta et al., 2022),”
DialGuide: Aligning Dialogue Model Behavior with Developer Guidelines (2022, methodology): “We consider the following models: • DialBart0-noguideline: A Bart-large model pre-trained on Instructdial (Gupta et al., 2022b) and tested on zero-shot generation without guidelines.”
Style Over Substance: Evaluation Biases for Large Language Models (2023, unknown): “Therefore, we recommend a multi-dimensional evaluation approach for assessing machine-generated text rather than relying on a single metric, and advise caution when using crowd annotators for LLM evaluations.”