Can Language Models Learn Truthfulness?

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

• He He, New York University
• Thursday 18 January 2024, 15:00-16:00
• https://cam-ac-uk.zoom.us/j/97599459216?pwd=QTRsOWZCOXRTREVnbTJBdXVpOXFvdz09.

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

Today’s large language models (LLMs) are trained on vast amounts of text from the internet, which contains both factual and misleading information about the world. Can language models discern truth from falsehood in this contradicting data? This talk introduces a hypothesis for how LLMs can model truthfulness. Inspired by the agent-model view of language models, we hypothesize that they can cluster truthful text by modeling a truthful persona: a group of agents that are likely to produce truthful text and share similar features. I will discuss both results on real data and controlled experiments on synthetic data that support the hypothesis. Overall, our findings suggest that models can exploit hierarchical structures in the data to learn abstract concepts like truthfulness.

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

This talk is included in these lists:

• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge talks
• Chris Davis' list
• Guy Emerson's list
• Interested Talks
• Language Sciences for Graduate Students
• Language Technology Lab Seminars
• Simon Baker's List
• Trust & Technology Initiative - interesting events
• bld31
• https://cam-ac-uk.zoom.us/j/97599459216?pwd=QTRsOWZCOXRTREVnbTJBdXVpOXFvdz09
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.