feat: openai results

lukasellinger · Aug 19, 2024 · 1873942 · 1873942
1 parent 479cd1b
commit 1873942
Show file tree

Hide file tree

Showing 135 changed files with 36,189 additions and 4,338 deletions.
diff --git a/.gitignore b/.gitignore
@@ -245,4 +245,6 @@ fabric.properties
 
 /wiki-pages
 
-*.safetensors
+*.safetensors
+
+dataset/jan
diff --git a/data/evaluation/fever_base.jsonl b/data/evaluation/fever_base.jsonl
diff --git a/data/evaluation/fever_finetuned.jsonl b/data/evaluation/fever_finetuned.jsonl
diff --git a/.../input/input_ablation_translated_claims-german_dpr-claim_verification-gpt-3.5-turbo.jsonl b/.../input/input_ablation_translated_claims-german_dpr-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/...ms/input/input_ablation_translated_claims-german_dpr-claim_verification-gpt-4o-mini.jsonl b/...ms/input/input_ablation_translated_claims-german_dpr-claim_verification-gpt-4o-mini.jsonl
diff --git a/..._claims/input/input_ablation_translated_claims-german_dpr-claim_verification-gpt-4o.jsonl b/..._claims/input/input_ablation_translated_claims-german_dpr-claim_verification-gpt-4o.jsonl
diff --git a/...utput/output_ablation_translated_claims-german_dpr-claim_verification-gpt-3.5-turbo.jsonl b/...utput/output_ablation_translated_claims-german_dpr-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/.../output/output_ablation_translated_claims-german_dpr-claim_verification-gpt-4o-mini.jsonl b/.../output/output_ablation_translated_claims-german_dpr-claim_verification-gpt-4o-mini.jsonl
diff --git a/...laims/output/output_ablation_translated_claims-german_dpr-claim_verification-gpt-4o.jsonl b/...laims/output/output_ablation_translated_claims-german_dpr-claim_verification-gpt-4o.jsonl
diff --git a/...t/raw_output_ablation_translated_claims-german_dpr-claim_verification-gpt-3.5-turbo.jsonl b/...t/raw_output_ablation_translated_claims-german_dpr-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/...put/raw_output_ablation_translated_claims-german_dpr-claim_verification-gpt-4o-mini.jsonl b/...put/raw_output_ablation_translated_claims-german_dpr-claim_verification-gpt-4o-mini.jsonl
diff --git a/...w_output/raw_output_ablation_translated_claims-german_dpr-claim_verification-gpt-4o.jsonl b/...w_output/raw_output_ablation_translated_claims-german_dpr-claim_verification-gpt-4o.jsonl
diff --git a/...ication/zero_shot/input/input_zero_shot-german_dpr-claim_verification-gpt-3.5-turbo.jsonl b/...ication/zero_shot/input/input_zero_shot-german_dpr-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/...ification/zero_shot/input/input_zero_shot-german_dpr-claim_verification-gpt-4o-mini.jsonl b/...ification/zero_shot/input/input_zero_shot-german_dpr-claim_verification-gpt-4o-mini.jsonl
diff --git a/...m_verification/zero_shot/input/input_zero_shot-german_dpr-claim_verification-gpt-4o.jsonl b/...m_verification/zero_shot/input/input_zero_shot-german_dpr-claim_verification-gpt-4o.jsonl
diff --git a/...ation/zero_shot/output/output_zero_shot-german_dpr-claim_verification-gpt-3.5-turbo.jsonl b/...ation/zero_shot/output/output_zero_shot-german_dpr-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/...ication/zero_shot/output/output_zero_shot-german_dpr-claim_verification-gpt-4o-mini.jsonl b/...ication/zero_shot/output/output_zero_shot-german_dpr-claim_verification-gpt-4o-mini.jsonl
diff --git a/...verification/zero_shot/output/output_zero_shot-german_dpr-claim_verification-gpt-4o.jsonl b/...verification/zero_shot/output/output_zero_shot-german_dpr-claim_verification-gpt-4o.jsonl
diff --git a/...ro_shot/raw_output/raw_output_zero_shot-german_dpr-claim_verification-gpt-3.5-turbo.jsonl b/...ro_shot/raw_output/raw_output_zero_shot-german_dpr-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/...zero_shot/raw_output/raw_output_zero_shot-german_dpr-claim_verification-gpt-4o-mini.jsonl b/...zero_shot/raw_output/raw_output_zero_shot-german_dpr-claim_verification-gpt-4o-mini.jsonl
diff --git a/...tion/zero_shot/raw_output/raw_output_zero_shot-german_dpr-claim_verification-gpt-4o.jsonl b/...tion/zero_shot/raw_output/raw_output_zero_shot-german_dpr-claim_verification-gpt-4o.jsonl
diff --git a/...acts/input/input_zero_shot_DisSim_facts-german_dpr-claim_verification-gpt-3.5-turbo.jsonl b/...acts/input/input_zero_shot_DisSim_facts-german_dpr-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/..._facts/input/input_zero_shot_DisSim_facts-german_dpr-claim_verification-gpt-4o-mini.jsonl b/..._facts/input/input_zero_shot_DisSim_facts-german_dpr-claim_verification-gpt-4o-mini.jsonl
diff --git a/...isSim_facts/input/input_zero_shot_DisSim_facts-german_dpr-claim_verification-gpt-4o.jsonl b/...isSim_facts/input/input_zero_shot_DisSim_facts-german_dpr-claim_verification-gpt-4o.jsonl
diff --git a/...ts/output/output_zero_shot_DisSim_facts-german_dpr-claim_verification-gpt-3.5-turbo.jsonl b/...ts/output/output_zero_shot_DisSim_facts-german_dpr-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/...acts/output/output_zero_shot_DisSim_facts-german_dpr-claim_verification-gpt-4o-mini.jsonl b/...acts/output/output_zero_shot_DisSim_facts-german_dpr-claim_verification-gpt-4o-mini.jsonl
diff --git a/...Sim_facts/output/output_zero_shot_DisSim_facts-german_dpr-claim_verification-gpt-4o.jsonl b/...Sim_facts/output/output_zero_shot_DisSim_facts-german_dpr-claim_verification-gpt-4o.jsonl
diff --git a/...utput/raw_output_zero_shot_DisSim_facts-german_dpr-claim_verification-gpt-3.5-turbo.jsonl b/...utput/raw_output_zero_shot_DisSim_facts-german_dpr-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/..._output/raw_output_zero_shot_DisSim_facts-german_dpr-claim_verification-gpt-4o-mini.jsonl b/..._output/raw_output_zero_shot_DisSim_facts-german_dpr-claim_verification-gpt-4o-mini.jsonl
diff --git a/...s/raw_output/raw_output_zero_shot_DisSim_facts-german_dpr-claim_verification-gpt-4o.jsonl b/...s/raw_output/raw_output_zero_shot_DisSim_facts-german_dpr-claim_verification-gpt-4o.jsonl
diff --git a/...s/input/input_zero_shot_Factscore_facts-german_dpr-claim_verification-gpt-3.5-turbo.jsonl b/...s/input/input_zero_shot_Factscore_facts-german_dpr-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/...cts/input/input_zero_shot_Factscore_facts-german_dpr-claim_verification-gpt-4o-mini.jsonl b/...cts/input/input_zero_shot_Factscore_facts-german_dpr-claim_verification-gpt-4o-mini.jsonl
diff --git a/...re_facts/input/input_zero_shot_Factscore_facts-german_dpr-claim_verification-gpt-4o.jsonl b/...re_facts/input/input_zero_shot_Factscore_facts-german_dpr-claim_verification-gpt-4o.jsonl
diff --git a/...output/output_zero_shot_Factscore_facts-german_dpr-claim_verification-gpt-3.5-turbo.jsonl b/...output/output_zero_shot_Factscore_facts-german_dpr-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/...s/output/output_zero_shot_Factscore_facts-german_dpr-claim_verification-gpt-4o-mini.jsonl b/...s/output/output_zero_shot_Factscore_facts-german_dpr-claim_verification-gpt-4o-mini.jsonl
diff --git a/..._facts/output/output_zero_shot_Factscore_facts-german_dpr-claim_verification-gpt-4o.jsonl b/..._facts/output/output_zero_shot_Factscore_facts-german_dpr-claim_verification-gpt-4o.jsonl
diff --git a/...ut/raw_output_zero_shot_Factscore_facts-german_dpr-claim_verification-gpt-3.5-turbo.jsonl b/...ut/raw_output_zero_shot_Factscore_facts-german_dpr-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/...tput/raw_output_zero_shot_Factscore_facts-german_dpr-claim_verification-gpt-4o-mini.jsonl b/...tput/raw_output_zero_shot_Factscore_facts-german_dpr-claim_verification-gpt-4o-mini.jsonl
diff --git a/...aw_output/raw_output_zero_shot_Factscore_facts-german_dpr-claim_verification-gpt-4o.jsonl b/...aw_output/raw_output_zero_shot_Factscore_facts-german_dpr-claim_verification-gpt-4o.jsonl
diff --git a/...t/input_zero_shot_T5SplitRephrase_facts-german_dpr-claim_verification-gpt-3.5-turbo.jsonl b/...t/input_zero_shot_T5SplitRephrase_facts-german_dpr-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/...put/input_zero_shot_T5SplitRephrase_facts-german_dpr-claim_verification-gpt-4o-mini.jsonl b/...put/input_zero_shot_T5SplitRephrase_facts-german_dpr-claim_verification-gpt-4o-mini.jsonl
diff --git a/...ts/input/input_zero_shot_T5SplitRephrase_facts-german_dpr-claim_verification-gpt-4o.jsonl b/...ts/input/input_zero_shot_T5SplitRephrase_facts-german_dpr-claim_verification-gpt-4o.jsonl
diff --git a/.../output_zero_shot_T5SplitRephrase_facts-german_dpr-claim_verification-gpt-3.5-turbo.jsonl b/.../output_zero_shot_T5SplitRephrase_facts-german_dpr-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/...ut/output_zero_shot_T5SplitRephrase_facts-german_dpr-claim_verification-gpt-4o-mini.jsonl b/...ut/output_zero_shot_T5SplitRephrase_facts-german_dpr-claim_verification-gpt-4o-mini.jsonl
diff --git a/.../output/output_zero_shot_T5SplitRephrase_facts-german_dpr-claim_verification-gpt-4o.jsonl b/.../output/output_zero_shot_T5SplitRephrase_facts-german_dpr-claim_verification-gpt-4o.jsonl
diff --git a/..._output_zero_shot_T5SplitRephrase_facts-german_dpr-claim_verification-gpt-3.5-turbo.jsonl b/..._output_zero_shot_T5SplitRephrase_facts-german_dpr-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/...aw_output_zero_shot_T5SplitRephrase_facts-german_dpr-claim_verification-gpt-4o-mini.jsonl b/...aw_output_zero_shot_T5SplitRephrase_facts-german_dpr-claim_verification-gpt-4o-mini.jsonl
diff --git a/...put/raw_output_zero_shot_T5SplitRephrase_facts-german_dpr-claim_verification-gpt-4o.jsonl b/...put/raw_output_zero_shot_T5SplitRephrase_facts-german_dpr-claim_verification-gpt-4o.jsonl
diff --git a/data/evaluation/german_dpr-claim_verification_base.jsonl b/data/evaluation/german_dpr-claim_verification_base.jsonl
diff --git a/data/evaluation/german_dpr-claim_verification_finetuned.jsonl b/data/evaluation/german_dpr-claim_verification_finetuned.jsonl
diff --git a/..._ablation_translated_claims-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl b/..._ablation_translated_claims-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl
diff --git a/...ut_ablation_translated_claims-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl b/...ut_ablation_translated_claims-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl
diff --git a/...t/input_ablation_translated_claims-german_wiktionary-claim_verification-mini-gpt-4o.jsonl b/...t/input_ablation_translated_claims-german_wiktionary-claim_verification-mini-gpt-4o.jsonl
diff --git a/..._ablation_translated_claims-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl b/..._ablation_translated_claims-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl
diff --git a/...ut_ablation_translated_claims-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl b/...ut_ablation_translated_claims-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl
diff --git a/.../output_ablation_translated_claims-german_wiktionary-claim_verification-mini-gpt-4o.jsonl b/.../output_ablation_translated_claims-german_wiktionary-claim_verification-mini-gpt-4o.jsonl
diff --git a/..._ablation_translated_claims-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl b/..._ablation_translated_claims-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl
diff --git a/...ut_ablation_translated_claims-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl b/...ut_ablation_translated_claims-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl
diff --git a/..._output_ablation_translated_claims-german_wiktionary-claim_verification-mini-gpt-4o.jsonl b/..._output_ablation_translated_claims-german_wiktionary-claim_verification-mini-gpt-4o.jsonl
diff --git a/..._shot/input/input_zero_shot-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl b/..._shot/input/input_zero_shot-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl
diff --git a/...ro_shot/input/input_zero_shot-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl b/...ro_shot/input/input_zero_shot-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl
diff --git a/...ni/zero_shot/input/input_zero_shot-german_wiktionary-claim_verification-mini-gpt-4o.jsonl b/...ni/zero_shot/input/input_zero_shot-german_wiktionary-claim_verification-mini-gpt-4o.jsonl
diff --git a/...hot/output/output_zero_shot-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl b/...hot/output/output_zero_shot-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl
diff --git a/..._shot/output/output_zero_shot-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl b/..._shot/output/output_zero_shot-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl
diff --git a/.../zero_shot/output/output_zero_shot-german_wiktionary-claim_verification-mini-gpt-4o.jsonl b/.../zero_shot/output/output_zero_shot-german_wiktionary-claim_verification-mini-gpt-4o.jsonl
diff --git a/...output/raw_output_zero_shot-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl b/...output/raw_output_zero_shot-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl
diff --git a/...w_output/raw_output_zero_shot-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl b/...w_output/raw_output_zero_shot-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl
diff --git a/...ot/raw_output/raw_output_zero_shot-german_wiktionary-claim_verification-mini-gpt-4o.jsonl b/...ot/raw_output/raw_output_zero_shot-german_wiktionary-claim_verification-mini-gpt-4o.jsonl
diff --git a/...nput_zero_shot_DisSim_facts-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl b/...nput_zero_shot_DisSim_facts-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl
diff --git a/.../input_zero_shot_DisSim_facts-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl b/.../input_zero_shot_DisSim_facts-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl
diff --git a/...input/input_zero_shot_DisSim_facts-german_wiktionary-claim_verification-mini-gpt-4o.jsonl b/...input/input_zero_shot_DisSim_facts-german_wiktionary-claim_verification-mini-gpt-4o.jsonl
diff --git a/...tput_zero_shot_DisSim_facts-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl b/...tput_zero_shot_DisSim_facts-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl
diff --git a/...output_zero_shot_DisSim_facts-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl b/...output_zero_shot_DisSim_facts-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl
diff --git a/...tput/output_zero_shot_DisSim_facts-german_wiktionary-claim_verification-mini-gpt-4o.jsonl b/...tput/output_zero_shot_DisSim_facts-german_wiktionary-claim_verification-mini-gpt-4o.jsonl
diff --git a/...tput_zero_shot_DisSim_facts-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl b/...tput_zero_shot_DisSim_facts-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl
diff --git a/...output_zero_shot_DisSim_facts-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl b/...output_zero_shot_DisSim_facts-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl
diff --git a/.../raw_output_zero_shot_DisSim_facts-german_wiktionary-claim_verification-mini-gpt-4o.jsonl b/.../raw_output_zero_shot_DisSim_facts-german_wiktionary-claim_verification-mini-gpt-4o.jsonl
diff --git a/...t_zero_shot_Factscore_facts-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl b/...t_zero_shot_Factscore_facts-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl
diff --git a/...put_zero_shot_Factscore_facts-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl b/...put_zero_shot_Factscore_facts-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl
diff --git a/...ut/input_zero_shot_Factscore_facts-german_wiktionary-claim_verification-mini-gpt-4o.jsonl b/...ut/input_zero_shot_Factscore_facts-german_wiktionary-claim_verification-mini-gpt-4o.jsonl
diff --git a/...t_zero_shot_Factscore_facts-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl b/...t_zero_shot_Factscore_facts-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl
diff --git a/...put_zero_shot_Factscore_facts-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl b/...put_zero_shot_Factscore_facts-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl
diff --git a/...t/output_zero_shot_Factscore_facts-german_wiktionary-claim_verification-mini-gpt-4o.jsonl b/...t/output_zero_shot_Factscore_facts-german_wiktionary-claim_verification-mini-gpt-4o.jsonl
diff --git a/...t_zero_shot_Factscore_facts-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl b/...t_zero_shot_Factscore_facts-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl
diff --git a/...put_zero_shot_Factscore_facts-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl b/...put_zero_shot_Factscore_facts-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl
diff --git a/...w_output_zero_shot_Factscore_facts-german_wiktionary-claim_verification-mini-gpt-4o.jsonl b/...w_output_zero_shot_Factscore_facts-german_wiktionary-claim_verification-mini-gpt-4o.jsonl
diff --git a/..._shot_T5SplitRephrase_facts-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl b/..._shot_T5SplitRephrase_facts-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl
diff --git a/...ro_shot_T5SplitRephrase_facts-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl b/...ro_shot_T5SplitRephrase_facts-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl
diff --git a/...ut_zero_shot_T5SplitRephrase_facts-german_wiktionary-claim_verification-mini-gpt-4o.jsonl b/...ut_zero_shot_T5SplitRephrase_facts-german_wiktionary-claim_verification-mini-gpt-4o.jsonl
diff --git a/..._shot_T5SplitRephrase_facts-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl b/..._shot_T5SplitRephrase_facts-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl
diff --git a/...ro_shot_T5SplitRephrase_facts-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl b/...ro_shot_T5SplitRephrase_facts-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl
diff --git a/...ut_zero_shot_T5SplitRephrase_facts-german_wiktionary-claim_verification-mini-gpt-4o.jsonl b/...ut_zero_shot_T5SplitRephrase_facts-german_wiktionary-claim_verification-mini-gpt-4o.jsonl
diff --git a/..._shot_T5SplitRephrase_facts-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl b/..._shot_T5SplitRephrase_facts-german_wiktionary-claim_verification-mini-gpt-3.5-turbo.jsonl
diff --git a/...ro_shot_T5SplitRephrase_facts-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl b/...ro_shot_T5SplitRephrase_facts-german_wiktionary-claim_verification-mini-gpt-4o-mini.jsonl
diff --git a/...ut_zero_shot_T5SplitRephrase_facts-german_wiktionary-claim_verification-mini-gpt-4o.jsonl b/...ut_zero_shot_T5SplitRephrase_facts-german_wiktionary-claim_verification-mini-gpt-4o.jsonl
diff --git a/...verification/zero_shot/input/input_zero_shot-squad-claim_verification-gpt-3.5-turbo.jsonl b/...verification/zero_shot/input/input_zero_shot-squad-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/...m_verification/zero_shot/input/input_zero_shot-squad-claim_verification-gpt-4o-mini.jsonl b/...m_verification/zero_shot/input/input_zero_shot-squad-claim_verification-gpt-4o-mini.jsonl
diff --git a/...-claim_verification/zero_shot/input/input_zero_shot-squad-claim_verification-gpt-4o.jsonl b/...-claim_verification/zero_shot/input/input_zero_shot-squad-claim_verification-gpt-4o.jsonl
diff --git a/...rification/zero_shot/output/output_zero_shot-squad-claim_verification-gpt-3.5-turbo.jsonl b/...rification/zero_shot/output/output_zero_shot-squad-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/...verification/zero_shot/output/output_zero_shot-squad-claim_verification-gpt-4o-mini.jsonl b/...verification/zero_shot/output/output_zero_shot-squad-claim_verification-gpt-4o-mini.jsonl
diff --git a/...laim_verification/zero_shot/output/output_zero_shot-squad-claim_verification-gpt-4o.jsonl b/...laim_verification/zero_shot/output/output_zero_shot-squad-claim_verification-gpt-4o.jsonl
diff --git a/...on/zero_shot/raw_output/raw_output_zero_shot-squad-claim_verification-gpt-3.5-turbo.jsonl b/...on/zero_shot/raw_output/raw_output_zero_shot-squad-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/...tion/zero_shot/raw_output/raw_output_zero_shot-squad-claim_verification-gpt-4o-mini.jsonl b/...tion/zero_shot/raw_output/raw_output_zero_shot-squad-claim_verification-gpt-4o-mini.jsonl
diff --git a/...ification/zero_shot/raw_output/raw_output_zero_shot-squad-claim_verification-gpt-4o.jsonl b/...ification/zero_shot/raw_output/raw_output_zero_shot-squad-claim_verification-gpt-4o.jsonl
diff --git a/...Sim_facts/input/input_zero_shot_DisSim_facts-squad-claim_verification-gpt-3.5-turbo.jsonl b/...Sim_facts/input/input_zero_shot_DisSim_facts-squad-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/...isSim_facts/input/input_zero_shot_DisSim_facts-squad-claim_verification-gpt-4o-mini.jsonl b/...isSim_facts/input/input_zero_shot_DisSim_facts-squad-claim_verification-gpt-4o-mini.jsonl
diff --git a/...hot_DisSim_facts/input/input_zero_shot_DisSim_facts-squad-claim_verification-gpt-4o.jsonl b/...hot_DisSim_facts/input/input_zero_shot_DisSim_facts-squad-claim_verification-gpt-4o.jsonl
diff --git a/...m_facts/output/output_zero_shot_DisSim_facts-squad-claim_verification-gpt-3.5-turbo.jsonl b/...m_facts/output/output_zero_shot_DisSim_facts-squad-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/...Sim_facts/output/output_zero_shot_DisSim_facts-squad-claim_verification-gpt-4o-mini.jsonl b/...Sim_facts/output/output_zero_shot_DisSim_facts-squad-claim_verification-gpt-4o-mini.jsonl
diff --git a/...t_DisSim_facts/output/output_zero_shot_DisSim_facts-squad-claim_verification-gpt-4o.jsonl b/...t_DisSim_facts/output/output_zero_shot_DisSim_facts-squad-claim_verification-gpt-4o.jsonl
diff --git a/...raw_output/raw_output_zero_shot_DisSim_facts-squad-claim_verification-gpt-3.5-turbo.jsonl b/...raw_output/raw_output_zero_shot_DisSim_facts-squad-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/...s/raw_output/raw_output_zero_shot_DisSim_facts-squad-claim_verification-gpt-4o-mini.jsonl b/...s/raw_output/raw_output_zero_shot_DisSim_facts-squad-claim_verification-gpt-4o-mini.jsonl
diff --git a/..._facts/raw_output/raw_output_zero_shot_DisSim_facts-squad-claim_verification-gpt-4o.jsonl b/..._facts/raw_output/raw_output_zero_shot_DisSim_facts-squad-claim_verification-gpt-4o.jsonl
diff --git a/..._facts/input/input_zero_shot_Factscore_facts-squad-claim_verification-gpt-3.5-turbo.jsonl b/..._facts/input/input_zero_shot_Factscore_facts-squad-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/...re_facts/input/input_zero_shot_Factscore_facts-squad-claim_verification-gpt-4o-mini.jsonl b/...re_facts/input/input_zero_shot_Factscore_facts-squad-claim_verification-gpt-4o-mini.jsonl
diff --git a/...ctscore_facts/input/input_zero_shot_Factscore_facts-squad-claim_verification-gpt-4o.jsonl b/...ctscore_facts/input/input_zero_shot_Factscore_facts-squad-claim_verification-gpt-4o.jsonl
diff --git a/...acts/output/output_zero_shot_Factscore_facts-squad-claim_verification-gpt-3.5-turbo.jsonl b/...acts/output/output_zero_shot_Factscore_facts-squad-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/..._facts/output/output_zero_shot_Factscore_facts-squad-claim_verification-gpt-4o-mini.jsonl b/..._facts/output/output_zero_shot_Factscore_facts-squad-claim_verification-gpt-4o-mini.jsonl
diff --git a/...score_facts/output/output_zero_shot_Factscore_facts-squad-claim_verification-gpt-4o.jsonl b/...score_facts/output/output_zero_shot_Factscore_facts-squad-claim_verification-gpt-4o.jsonl
diff --git a/..._output/raw_output_zero_shot_Factscore_facts-squad-claim_verification-gpt-3.5-turbo.jsonl b/..._output/raw_output_zero_shot_Factscore_facts-squad-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/...aw_output/raw_output_zero_shot_Factscore_facts-squad-claim_verification-gpt-4o-mini.jsonl b/...aw_output/raw_output_zero_shot_Factscore_facts-squad-claim_verification-gpt-4o-mini.jsonl
diff --git a/...cts/raw_output/raw_output_zero_shot_Factscore_facts-squad-claim_verification-gpt-4o.jsonl b/...cts/raw_output/raw_output_zero_shot_Factscore_facts-squad-claim_verification-gpt-4o.jsonl
diff --git a/.../input/input_zero_shot_T5SplitRephrase_facts-squad-claim_verification-gpt-3.5-turbo.jsonl b/.../input/input_zero_shot_T5SplitRephrase_facts-squad-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/...ts/input/input_zero_shot_T5SplitRephrase_facts-squad-claim_verification-gpt-4o-mini.jsonl b/...ts/input/input_zero_shot_T5SplitRephrase_facts-squad-claim_verification-gpt-4o-mini.jsonl
diff --git a/...e_facts/input/input_zero_shot_T5SplitRephrase_facts-squad-claim_verification-gpt-4o.jsonl b/...e_facts/input/input_zero_shot_T5SplitRephrase_facts-squad-claim_verification-gpt-4o.jsonl
diff --git a/...utput/output_zero_shot_T5SplitRephrase_facts-squad-claim_verification-gpt-3.5-turbo.jsonl b/...utput/output_zero_shot_T5SplitRephrase_facts-squad-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/.../output/output_zero_shot_T5SplitRephrase_facts-squad-claim_verification-gpt-4o-mini.jsonl b/.../output/output_zero_shot_T5SplitRephrase_facts-squad-claim_verification-gpt-4o-mini.jsonl
diff --git a/...facts/output/output_zero_shot_T5SplitRephrase_facts-squad-claim_verification-gpt-4o.jsonl b/...facts/output/output_zero_shot_T5SplitRephrase_facts-squad-claim_verification-gpt-4o.jsonl
diff --git a/...t/raw_output_zero_shot_T5SplitRephrase_facts-squad-claim_verification-gpt-3.5-turbo.jsonl b/...t/raw_output_zero_shot_T5SplitRephrase_facts-squad-claim_verification-gpt-3.5-turbo.jsonl
diff --git a/...put/raw_output_zero_shot_T5SplitRephrase_facts-squad-claim_verification-gpt-4o-mini.jsonl b/...put/raw_output_zero_shot_T5SplitRephrase_facts-squad-claim_verification-gpt-4o-mini.jsonl
diff --git a/...w_output/raw_output_zero_shot_T5SplitRephrase_facts-squad-claim_verification-gpt-4o.jsonl b/...w_output/raw_output_zero_shot_T5SplitRephrase_facts-squad-claim_verification-gpt-4o.jsonl
diff --git a/general_utils/reader.py b/general_utils/reader.py
@@ -43,7 +43,7 @@ def process(self, file):
 
     def _write(self, file, lines):
         for line in lines:
-            json.dump(line, file)
+            json.dump(line, file, ensure_ascii=False)
             file.write('\n')
 
 

diff --git a/notebooks/factscore.ipynb b/notebooks/factscore.ipynb
diff --git a/notebooks/openai_evaluation.ipynb b/notebooks/openai_evaluation.ipynb
diff --git a/notebooks/pipeline_evaluation.ipynb b/notebooks/pipeline_evaluation.ipynb
@@ -152,10 +152,6 @@
     "        'dataset': load_dataset('lukasellinger/german_wiktionary-claim_verification-mini', split='test'),\n",
     "        'lang': 'de'\n",
     "    },\n",
-    "    #'german-claim_verification': {\n",
-    "    #    'dataset': load_dataset('lukasellinger/german-claim_verification', split='test'),\n",
-    "    #    'lang': 'de'\n",
-    "    #},\n",
     "    'squad-claim_verification': {\n",
     "        'dataset': load_dataset('lukasellinger/squad-claim_verification', split='test'),\n",
     "        'lang': 'en'\n",
@@ -164,7 +160,12 @@
     "    #'german_wiktionary-claim_verification-large': {\n",
     "    #    'dataset': load_dataset('lukasellinger/german_wiktionary-claim_verification-large', split='test'),\n",
     "    #    'lang': 'de'\n",
-    "    #}\n",
+    "    #},\n",
+    "    # outdated\n",
+    "    #'german-claim_verification': {\n",
+    "    #    'dataset': load_dataset('lukasellinger/german-claim_verification', split='test'),\n",
+    "    #    'lang': 'de'\n",
+    "    #},\n",
     "}"
    ],
    "id": "26dff9eae25d4da9",