Added blocking and renamed implicit explicit

changelinglab · Aug 23, 2024 · 349f5cc · 349f5cc
1 parent 02ebb18
commit 349f5cc
Show file tree

Hide file tree

Showing 2 changed files with 12 additions and 0 deletions.
diff --git a/_projects/9_project.md → _projects/11_blocking.md b/_projects/9_project.md → _projects/11_blocking.md
diff --git a/_projects/9_implicit_explicit.md b/_projects/9_implicit_explicit.md
@@ -0,0 +1,12 @@
+---
+layout: page
+title: Blocking in LLMs
+description: Do LLMs know the badness of badity?
+img: /assets/img/luzern-panorama-proj.jpg
+importance: 3
+category: llm
+---
+
+Blocking is a well-known linguistic phenomenon. In brief, constructions (including words) are dispreferred if there is an already established construction with the same meaning. For example, *childs* is dispreferred as a plural of *child* (even though it follows the regular rule for pluralization in English) because it is “blocked” by the semantically identical word *children*.
+
+In this project, we investigate the hypothesis that LLMs do not display blocking behavior in the same way the humans do.