Dataset Groups Activity Stream Learning to summarize with human feedback The paper presents a study on the impact of synthetic data on large language models (LLMs) and proposes a method to steer LLMs towards desirable non-differentiable attributes. BibTex: @dataset{Nisan_Stiennon_and_Long_Ouyang_and_Jeffrey_Wu_and_Daniel_Ziegler_and_Ryan_Lowe_and_Chelsea_Voss_and_Alec_Radford_and_Dario_Amodei_2024, abstract = {The paper presents a study on the impact of synthetic data on large language models (LLMs) and proposes a method to steer LLMs towards desirable non-differentiable attributes.}, author = {Nisan Stiennon and Long Ouyang and Jeffrey Wu and Daniel Ziegler and Ryan Lowe and Chelsea Voss and Alec Radford and Dario Amodei}, doi = {10.57702/bakxgny5}, institution = {No Organization}, keyword = {'Data generation', 'Large language models', 'Non-differentiable attributes', 'Summarization', 'factually-consistent summarization', 'machine learning', 'natural language processing'}, month = {dec}, publisher = {TIB}, title = {Learning to summarize with human feedback}, url = {https://service.tib.eu/ldmservice/dataset/learning-to-summarize-with-human-feedback}, year = {2024} }
