List your company

LLM Calibration on MACE

8.6ECEConsistency
7.07217.38627.738.014Feb 8, 2026

Evaluation results

MethodLinks
ConsistencyBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Answer-level2026.028.6
Sem EntropyBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Question-level2026.029.6
ConsistencyBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Answer-level2026.0210.4
Consis-VerbBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Answer-level2026.0211.7
Consis-VerbBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Answer-level2026.0212.3
Consis-Verb-TopkBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Answer-level2026.0212.4
Sem EntropyBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Question-level2026.0212.5
Consis-Verb-TopkBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Answer-level2026.0214.3
Sem EntropyBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Question-level2026.0216.6
VerbTopkBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Answer-level2026.0219.3
Prob EntropyBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Question-level2026.0219.4
PerplexityBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Answer-level2026.0219.6
Prob EntropyBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Question-level2026.0220.8
PerplexityBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Answer-level2026.0220.9
Sem EntropyBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Question-level2026.0221.3
Consis-VerbBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Answer-level2026.0221.5
ConsistencyBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Answer-level2026.0221.6
Prob EntropyBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Question-level2026.0221.7
VerbTopkBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Answer-level2026.0221.9
VerbTopkBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Answer-level2026.0222.5
SelfAsk-CandBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Double-turn2026.0222.8
PerplexityBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Answer-level2026.0223.4
SelfAsk-CandBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Double-turn2026.0223.5
Consis-Verb-TopkBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Answer-level2026.0223.6
SelfAsk-CandBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Double-turn2026.0225.6
Prob EntropyBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Question-level2026.0226.2
SelfAsk-CandBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Double-turn2026.0226.3
ConsistencyBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Answer-level2026.0227
Consis-VerbBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Answer-level2026.0227.1
Consis-Verb-TopkBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Answer-level2026.0229.1
PTrue-Prob-CandBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Double-turn2026.0230
PTrue-Prob-CandBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Double-turn2026.0230.2
N-Prob EntropyBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Question-level2026.0230.3
PTrue-Consis-CandBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Double-turn2026.0230.4
PerplexityBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Answer-level2026.0230.6
PTrue-Consis-CandBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Double-turn2026.0230.6
PTrue-ProbBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Double-turn2026.0231.4
PTrue-ConsisBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Double-turn2026.0231.5
N-Prob EntropyBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Question-level2026.0231.7
PTrue-ProbBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Double-turn2026.0232.7
PTrue-ConsisBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Double-turn2026.0233
VerbBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Answer-level2026.0233.1
PTrue-ProbBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Double-turn2026.0233.7
PTrue-ConsisBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Double-turn2026.0234.1
VerbBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Answer-level2026.0234.6
PTrue-ProbBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Double-turn2026.0235.1
PTrue-ConsisBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Double-turn2026.0235.3
PTrue-Prob-CandBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Double-turn2026.0235.4
N-Prob EntropyBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Question-level2026.0235.5
PTrue-Consis-CandBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Double-turn2026.0235.6
VerbTopkBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Answer-level2026.0235.8
SelfAskBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Double-turn2026.0236.6
VerbBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Answer-level2026.0239.5
SelfAskBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Double-turn2026.0240.9
PTrue-Prob-CandBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Double-turn2026.0241.6
PTrue-Consis-CandBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Double-turn2026.0241.7
N-Prob EntropyBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Question-level2026.0243.5
SelfAskBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Double-turn2026.0245.8
SelfAskBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Double-turn2026.0246.7
VerbBackbone Model=LLaMA-3.1-70B-Instruct, Turn Type=Single-turn, Evaluation Level=Answer-level2026.0246.8