TOME-2

Reported on 3 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Natural Language Processing3 results

Question AnsweringonComplexWebQuestions
EM· 2021-10-12
47.7
best: 81.4 (PoG-GPT4 (Tan et al., 2024))
SOTA
Mention Memory: incorporating textual knowledge into Transformers through entity mention attention arXiv:2110.06176
Information RetrievalonEntityQuestions
Recall@20· 2021-10-12
0.838
SOTA
Mention Memory: incorporating textual knowledge into Transformers through entity mention attention arXiv:2110.06176
Question AnsweringonTriviaQA
EM· 2021-10-12
65.8
best: 87.5 (Claude 2 (few-shot, k=5))
Mention Memory: incorporating textual knowledge into Transformers through entity mention attention arXiv:2110.06176