TREC DL and LLM AggreFact experiments for relevance benchmark + promp…

…ts comparisons and groundedness vs Bespoke Minicheck 7B (#1660) * save * improve trubasicapp setup for competitive experiments, add mlflow instrumentation * save * save progress * save * save * add agreement analysis with scoreddocs * notebook updates * cleanup * dataset preprocessing script update * cleanup competitive analysis * add llm aggrefact nb * add llm-aggrefact experiment notebook * move notebooks * edits * pr comments * add back e2e/data nb
truera · Dec 10, 2024 · f549d91 · f549d91
1 parent e25b561
commit f549d91
Show file tree

Hide file tree

Showing 7 changed files with 1,941 additions and 303 deletions.
diff --git a/.gitignore b/.gitignore
@@ -52,6 +52,9 @@ credentials.toml
 # test files generated by benchmark experiments
 **/tests/*.csv
 **/results/*.csv
+**/experiments/mlruns/
+**/experiments/*.zip
+**/experiments/*/*.csv
 
 # test files generated by pytest
 test-output.xml