Grounding gaps in language model generations
LLMs produce fewer grounding acts than humans and tend to presume common ground rather than actively establishing it, exposing a structural gap between human and machine conversation.
7 entries
LLMs produce fewer grounding acts than humans and tend to presume common ground rather than actively establishing it, exposing a structural gap between human and machine conversation.
The foundational framework for how conversational participants establish mutual understanding. Introduces common ground and the grounding process as the basis of successful communication.
An onboarding checklist for conversation designers.
5 checks to keep your content on track, and your clients happy.
Voor taalkundigen, conversation designers en iedereen die iets heeft met taal!
Sketchnotes of the Voicelunch session with Brian Roemmele, the best voicelunch I never attended.
Want to know what you can do to make your voice action sound more speech-like? Part 2 covers backchannelling, discourse markers, and deixis.