Share your thoughts, 1 month free Claude Pro on usSee more

Selective Question Answering on TriviaQA

2,849Score (Coverage 14%)

LLM-RAG

Updated 14d ago

Evaluation Results

Method
LLM-RAG 2026.05	2,849	2,505	2,627	2,759	2,835	2,849	2,849	2,849	2,849
BalanceRAG 2026.05	2,839	-	2,549	2,718	2,807	2,843	2,843	2,843	2,843
BalanceRAG 2026.05	2,738	2,366	2,573	2,702	2,737	2,738	2,738	2,738	2,738
LLM-RAG 2026.05	2,707	2,521	2,660	2,706	2,707	2,707	2,707	2,707	2,707
LLM-RAG 2026.05	2,691	2,118	2,320	2,490	2,633	2,694	2,694	2,694	2,694
BalanceRAG 2026.05	2,691	2,073	2,288	2,430	2,584	2,727	2,734	2,736	2,737
BalanceRAG 2026.05	2,660	2,499	2,634	2,629	2,629	2,661	2,661	2,661	2,661
LLM-RAG 2026.05	2,529	1,856	2,036	2,198	2,382	2,652	2,711	2,713	2,713
UCB-Cascaded-CP 2026.05	2,467	-	-	2,310	2,362	2,538	2,533	2,525	2,497
UCB-Cascaded-CP 2026.05	2,442	1,820	1,992	2,284	2,377	2,499	2,531	2,534	2,557
UCB-Cascaded-CP 2026.05	2,360	1,553	1,849	2,084	2,264	2,434	2,486	2,505	2,482
LLM-only 2026.05	2,347	1,856	1,988	2,148	2,255	2,422	2,473	2,522	2,564
LLM-RAG 2026.05	2,280	1,473	1,680	1,907	2,105	2,400	2,475	2,500	2,501
BalanceRAG 2026.05	2,279	1,569	1,733	1,907	2,110	2,421	2,498	2,512	2,514
UCB-Cascaded-HFD 2026.05	2,205	-	1,716	1,880	2,035	2,301	2,392	2,455	2,502
LLM-only 2026.05	2,165	1,587	1,780	1,928	2,070	2,218	2,277	2,345	2,402
UCB-Cascaded-CP 2026.05	2,126	-	1,746	1,834	2,016	2,240	2,463	2,533	2,587
LLM-only 2026.05	2,093	-	1,764	1,871	1,995	2,159	2,233	2,301	2,357
LLM-only 2026.05	2,073	-	-	1,836	1,964	2,176	2,259	2,314	2,363
UCB-Cascaded-HFD 2026.05	2,058	-	-	-	-	2,215	2,359	2,410	2,420
UCB-Cascaded-HFD 2026.05	1,992	-	1,395	1,607	1,810	2,148	2,248	2,351	2,400
BalanceRAG 2026.05	1,973	1,347	1,643	1,774	1,873	2,073	2,159	2,229	2,290
UCB-Cascaded-CP 2026.05	1,952	-	1,291	1,633	1,834	2,049	2,143	2,237	2,304
UCB-Cascaded-HFD 2026.05	1,902	-	-	1,726	1,781	2,048	2,133	2,224	2,338
UCB-Cascaded-CP 2026.05	1,850	832	1,028	1,488	1,749	1,917	1,991	2,065	2,142
LLM-RAG 2026.05	1,760	1,367	1,390	1,532	1,646	1,876	1,949	2,036	2,117
UCB-Cascaded-HFD 2026.05	1,555	-	-	-	-	1,799	1,955	2,051	2,152
BalanceRAG 2026.05	1,533	1,297	1,367	1,430	1,487	1,580	1,629	1,667	1,694
LLM-RAG 2026.05	1,512	1,256	1,330	1,401	1,455	1,564	1,611	1,648	1,675
UCB-Cascaded-CP 2026.05	1,354	981	1,102	1,236	1,306	1,395	1,426	1,469	1,504
UCB-Cascaded-HFD 2026.05	1,328	-	-	820	964	1,661	1,799	1,899	1,990
LLM-only 2026.05	1,283	870	988	1,116	1,214	1,371	1,443	1,513	1,589
BalanceRAG 2026.05	1,168	983	1,041	1,091	1,124	1,203	1,237	1,262	1,274
LLM-RAG 2026.05	1,101	875	939	987	1,041	1,163	1,207	1,250	1,270
LLM-only 2026.05	1,049	-	798	885	971	1,137	1,227	1,316	1,397
LLM-only 2026.05	1,049	792	868	935	992	1,115	1,189	1,250	1,294
UCB-Cascaded-HFD 2026.05	1,011	542	603	776	876	1,147	1,266	1,333	1,355
LLM-only 2026.05	1,002	775	861	919	961	1,043	1,081	1,110	1,138
UCB-Cascaded-CP 2026.05	998	750	868	925	962	1,031	1,070	1,100	1,127
UCB-Cascaded-HFD 2026.05	888	-	669	694	806	946	989	1,035	1,078