LLaMa-2-7B-Chat + TruthX

Reported on 2 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing2 results

Question AnsweringonTruthfulQA
MC1· 2024-02-27
0.54
best: 0.59 (GPT-4 (RLHF))
TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space arXiv:2402.17811
Question AnsweringonTruthfulQA
MC2· 2024-02-27
0.74
best: 0.75 (Mistral-7B-Instruct-v0.2 + TruthX)
TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space arXiv:2402.17811