List your company

Multi-hop Question Answering on MuSiQue (Rubric Judge Accuracy)

39.6Rubric Judge AccuracyPredicate-Based Belief State
7.77616.03824.332.562May 7, 2026

Evaluation results

MethodLinks
Predicate-Based Belief StateHarness=Iter-RetGen, Representation=Freeform (b_free)2026.0539.6
BaselineHarness=Iter-RetGen2026.0537.1
Predicate-Based Belief StateHarness=ReAct, Representation=Freeform (b_free)2026.0536.8
Predicate-Based Belief StateHarness=MemGPT, Representation=Freeform (b_free)2026.0534.4
Predicate-Based Belief StateHarness=Iter-RetGen, Representation=Structured JSON (b_struct)2026.0533.8
BaselineHarness=MemGPT2026.0531.4
LobotomizedHarness=MemGPT2026.0530.6
Predicate-Based Belief StateHarness=ReAct, Representation=Structured JSON (b_struct)2026.0530.1
BaselineHarness=ReAct2026.0529.6
Predicate-Based Belief StateHarness=MemGPT, Representation=Structured JSON (b_struct)2026.0529.6
Predicate-Based Belief StateHarness=IRCoT, Representation=Freeform (b_free)2026.0525.9
Predicate-Based Belief StateHarness=IRCoT, Representation=Structured JSON (b_struct)2026.0521.1
BaselineHarness=IRCoT2026.0514.4
LobotomizedHarness=ReAct2026.0512.2
LobotomizedHarness=IRCoT2026.059