University of Cambridge > Talks.cam > Language Technology Lab Seminars > Prosocial Language Models

  Browse A-Z

Log in

Cambridge users (raven)details Other usersdetails No account?details

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

Prosocial Language Models

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Panagiotis Fytas.

Large language models, such as GPT -4, have marked a significant advancement in the field of natural language processing, achieving near-human performance across a variety of tasks with minimal to no additional training data. The remarkable capabilities of these models can be attributed to their substantial parameter counts, often reaching into the hundreds or thousands of millions, and the extensive datasets sourced from the web for their pre-training. Despite their successes, the very characteristics that empower these models also render them susceptible to mirroring web-based biases and antisocial behaviors. Such reflections pose considerable challenges in deploying these models in real-world scenarios, particularly in socially sensitive applications. In response, our laboratory focuses on developing techniques for the post hoc mitigation of these antisocial tendencies, allowing for the enforcement of prosocial behaviors during model inference without the need for resource-intensive retraining. This presentation will delve into our latest efforts to reduce bias and enhance alignment with human ethical standards in language models through inference-time interventions.

This talk is part of the Language Technology Lab Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Food 4 Thought Webinars Statistical Laboratory Open Afternoon Communications Research Group Seminar

Other talks

The Sassoons: The Great Global Merchants and the Making of an Empire Title TBC Identification of novel antibiotic resistance mechanisms in Klebsiella pneumoniae using machine learning CANCELLED: CSAR lecture: Graphene, Two Dimensional Materials & Delivering the Future of Electronic Devices Nonlinearity in structural dynamics: when does it matter? How storm develops as the wind blows
 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity