List your company

Question Answering on AdversarialQA (test)

73.2Average AccuracyProCL
51.67257.26162.8568.439May 13, 2026

Evaluation results

MethodLinks
ProCLLLM=Llama-3.1-8B2026.0573.2
DEALLLM=Qwen3-8B2026.0572.9
ProCLLLM=Qwen3-8B2026.0572.8
ProCLLLM=Qwen3-4B2026.0572.5
O-LoRALLM=Llama-3.1-8B2026.0572.4
DEALLLM=Llama-3.1-8B2026.0572.1
ProCLLLM=Llama-3.2-3B2026.0569.8
ProCLLLM=Average2026.0569.1
DEALLLM=Qwen3-4B2026.0568.2
EWCLLM=Llama-3.2-3B2026.0568.1
O-LoRALLM=Llama-3.2-3B2026.0568.1
Seq-LoRALLM=Llama-3.2-3B2026.0567.7
ReplayLLM=Llama-3.2-3B2026.0567.6
DEALLLM=Llama-3.2-3B2026.0566.4
DEALLLM=Average2026.0566.2
EWCLLM=Llama-3.1-8B2026.0565.3
Seq-LoRALLM=Llama-3.1-8B2026.0564.5
ProCLLLM=Flan-T5-Large2026.0563.4
ReplayLLM=Llama-3.1-8B2026.0562.8
ProCLLLM=Flan-T5-Base2026.0562.8
ReplayLLM=Flan-T5-Large2026.0562.8
EWCLLM=Flan-T5-Large2026.0562.6
Seq-LoRALLM=Flan-T5-Large2026.0562
O-LoRALLM=Average2026.0561.9
EWCLLM=Average2026.0561.7
O-LoRALLM=Flan-T5-Large2026.0561.6
DEALLLM=Flan-T5-Base2026.0561.4
Seq-LoRALLM=Flan-T5-Base2026.0561.3
Seq-LoRALLM=Average2026.0561.2
ReplayLLM=Average2026.0561.2
EWCLLM=Flan-T5-Base2026.0560.9
ReplayLLM=Flan-T5-Base2026.0560.6
Seq-LoRALLM=Qwen3-8B2026.0559.1
ReplayLLM=Qwen3-8B2026.0558.8
EWCLLM=Qwen3-8B2026.0558.7
O-LoRALLM=Qwen3-8B2026.0558.6
O-LoRALLM=Qwen3-4B2026.0556.6
DEALLLM=Flan-T5-Large2026.0555.9
ReplayLLM=Qwen3-4B2026.0554.8
EWCLLM=Qwen3-4B2026.0554.5
O-LoRALLM=Flan-T5-Base2026.0554.2
Seq-LoRALLM=Qwen3-4B2026.0552.5