List your company

Open-Domain Question Answering on LoCoMo Open-Domain (test)

15.12F1 ScoreReproduced Baselines
5.7088.151510.59513.0385Feb 17, 2026

Evaluation results

MethodLinks
Reproduced BaselinesModel=GPT-oss:20b, Memory=A-mem2026.0215.1215.870
ER-MIAModel=Llama3.2:3b, Attack Size=2 Memories / Question, Memory=A-mem2026.0214.0613.44-46.8
Reproduced BaselinesModel=Gemma3:27b, Memory=Mem02026.0212.2210.30
ER-MIAModel=Llama3.2:3b, Attack Size=1 Memory / Question, Memory=A-mem2026.0212.1410.93-40.2
PoisonedRAGModel=GPT-oss:20b, Memory=A-mem2026.0212.069.78-7.2
ER-MIAModel=GPT-oss:20b, Attack Size=1 Memory / Question, Memory=A-mem2026.0211.4511.11-48.4
Reproduced BaselinesModel=GPT-oss:20b, Memory=Mem02026.0211.098.560
Reproduced BaselinesModel=Llama3.2:3b, Memory=Mem02026.0211.028.870
PoisonedRAGModel=Gemma3:27b, Memory=Mem02026.0210.448.55-6.1
ER-MIAModel=Llama3.2:3b, Attack Size=1 Memory / Question, Memory=Mem02026.0210.378.48-44.1
Reproduced BaselinesModel=Llama3.2:3b, Memory=A-mem2026.028.968.20
ER-MIAModel=Gemma3:27b, Attack Size=1 Memory / Question, Memory=A-mem2026.028.817.03-46.5
ER-MIAModel=GPT-oss:20b, Attack Size=2 Memories / Question, Memory=A-mem2026.028.798.64-55.5
PoisonedRAGModel=Llama3.2:3b, Memory=A-mem2026.028.668.17-7.1
ER-MIAModel=GPT-oss:20b, Attack Size=1 Memory / Question, Memory=Mem02026.028.627.3-51.6
PoisonedRAGModel=Llama3.2:3b, Memory=Mem02026.028.67.51-4.2
ER-MIAModel=Llama3.2:3b, Attack Size=2 Memories / Question, Memory=Mem02026.028.597.73-53
ER-MIAModel=GPT-oss:20b, Attack Size=2 Memories / Question, Memory=Mem02026.028.527.61-56.7
ER-MIAModel=Gemma3:27b, Attack Size=2 Memories / Question, Memory=Mem02026.028.247.2-53.6
ER-MIAModel=Gemma3:27b, Attack Size=1 Memory / Question, Memory=Mem02026.028.076.64-48.4
Reproduced BaselinesModel=Gemma3:27b, Memory=A-mem2026.027.976.450
PoisonedRAGModel=GPT-oss:20b, Memory=Mem02026.027.086.95-13.1
PoisonedRAGModel=Gemma3:27b, Memory=A-mem2026.026.124.48-13.4
ER-MIAModel=Gemma3:27b, Attack Size=2 Memories / Question, Memory=A-mem2026.026.07—-61.6