Fine-tuning language models to find agreement among humans with diverse preferences
Recent work in large language modeling (LLMs) has used fine-tuning to align outputs with
the preferences of a prototypical user. This work assumes that human preferences are static …
the preferences of a prototypical user. This work assumes that human preferences are static …
[PDF][PDF] Fine-tuning language models to find agreement among humans with diverse preferences
M Bakker - ai4comm.media.mit.edu
230222 Group alignment MIT GenAI Page 1 Fine-tuning language models to find agreement
among humans with diverse preferences MIT Generative AI for Constructive Communication …
among humans with diverse preferences MIT Generative AI for Constructive Communication …
Fine-tuning language models to find agreement among humans with diverse preferences
M Bakker, M Chadwick, H Sheahan… - Advances in …, 2022 - proceedings.neurips.cc
Recent work in large language modeling (LLMs) has used fine-tuning to align outputs with
the preferences of a prototypical user. This work assumes that human preferences are static …
the preferences of a prototypical user. This work assumes that human preferences are static …
[PDF][PDF] Fine-tuning language models to find agreement among humans with diverse preferences
MA Bakker, MJ Chadwick, HR Sheahan, MH Tessler… - proceedings.nips.cc
Recent work in large language modeling (LLMs) has used fine-tuning to align outputs with
the preferences of a prototypical user. This work assumes that human preferences are static …
the preferences of a prototypical user. This work assumes that human preferences are static …
Fine-tuning language models to find agreement among humans with diverse preferences
MA Bakker, MJ Chadwick, HR Sheahan… - Proceedings of the 36th …, 2022 - dl.acm.org
Recent work in large language modeling (LLMs) has used fine-tuning to align outputs with
the preferences of a prototypical user. This work assumes that human preferences are static …
the preferences of a prototypical user. This work assumes that human preferences are static …
Fine-tuning language models to find agreement among humans with diverse preferences
MA Bakker, MJ Chadwick, HR Sheahan… - arXiv preprint arXiv …, 2022 - arxiv.org
Recent work in large language modeling (LLMs) has used fine-tuning to align outputs with
the preferences of a prototypical user. This work assumes that human preferences are static …
the preferences of a prototypical user. This work assumes that human preferences are static …
Fine-tuning language models to find agreement among humans with diverse preferences
MA Bakker, MJ Chadwick, HR Sheahan… - arXiv e …, 2022 - ui.adsabs.harvard.edu
Recent work in large language modeling (LLMs) has used fine-tuning to align outputs with
the preferences of a prototypical user. This work assumes that human preferences are static …
the preferences of a prototypical user. This work assumes that human preferences are static …
Fine-tuning language models to find agreement among humans with diverse preferences
MA Bakker, MJ Chadwick, H Sheahan… - Advances in Neural …, 2022 - openreview.net
Recent work in large language modeling (LLMs) has used fine-tuning to align outputs with
the preferences of a prototypical user. This work assumes that human preferences are static …
the preferences of a prototypical user. This work assumes that human preferences are static …