List your company

Hallucination Detection on NQ_Open

79.35macF1SAPLMA + LaaB
45.560454.332763.10571.8773May 5, 2026

Evaluation results

MethodLinks
SAPLMA + LaaBLLM=Qwen-2.5-32B-Instruct2026.0579.3580.65
Lookback Lens + LaaBLLM=Qwen-2.5-32B-Instruct2026.0578.0879.32
SAPLMALLM=Qwen-2.5-32B-Instruct2026.0576.8177.55
Lookback LensLLM=Qwen-2.5-32B-Instruct2026.0576.6277.99
SelfCheckGPTLLM=Qwen-2.5-32B-Instruct2026.0574.8376.81
SAPLMA + LaaBLLM=Mistral-7B-Instruct-v0.32026.0574.4875.11
SAPLMA + LaaBLLM=Llama-3.1-8B-Instruct2026.0573.177.13
SAPLMALLM=Llama-3.1-8B-Instruct2026.0573.0175.15
SAPLMALLM=Mistral-7B-Instruct-v0.32026.0572.9674.36
Lookback Lens + LaaBLLM=Llama-3.1-8B-Instruct2026.0572.6375.46
SAPLMA + LaaBLLM=Llama-3.1-70B-Instruct2026.0571.7178.48
Lookback Lens + LaaBLLM=Mistral-7B-Instruct-v0.32026.0571.6773.01
SAPLMALLM=Llama-3.1-70B-Instruct2026.0571.6478.62
Lookback LensLLM=Mistral-7B-Instruct-v0.32026.0571.4672.26
Self-JudgeLLM=Qwen-2.5-32B-Instruct2026.0571.2973.99
SelfCheckGPTLLM=Llama-3.1-8B-Instruct2026.0569.7773.17
Self-JudgeLLM=Llama-3.1-70B-Instruct2026.0568.6579.21
Lookback LensLLM=Llama-3.1-8B-Instruct2026.0568.670.88
SelfCheckGPTLLM=Llama-3.1-70B-Instruct2026.0567.7377.31
Logits Lens + LaaBLLM=Qwen-2.5-32B-Instruct2026.0567.2170.61
Lookback Lens + LaaBLLM=Llama-3.1-70B-Instruct2026.0566.6576.28
SelfCheckGPTLLM=Mistral-7B-Instruct-v0.32026.0566.3168.07
Logits Lens + LaaBLLM=Llama-3.1-8B-Instruct2026.0565.7268.9
Logits LensLLM=Qwen-2.5-32B-Instruct2026.0565.0266.03
Eigen-ScoreLLM=Llama-3.1-8B-Instruct2026.0564.8267.07
Lookback LensLLM=Llama-3.1-70B-Instruct2026.0564.368.67
Logits LensLLM=Llama-3.1-8B-Instruct2026.0562.6363.26
Eigen-ScoreLLM=Qwen-2.5-32B-Instruct2026.0561.3362.63
Eigen-ScoreLLM=Llama-3.1-70B-Instruct2026.0560.5971.6
Eigen-ScoreLLM=Mistral-7B-Instruct-v0.32026.0559.1462.67
Self-JudgeLLM=Llama-3.1-8B-Instruct2026.0559.1259.14
Logits LensLLM=Mistral-7B-Instruct-v0.32026.0558.9462.82
Logits Lens + LaaBLLM=Mistral-7B-Instruct-v0.32026.0558.9462.07
Logits Lens + LaaBLLM=Llama-3.1-70B-Instruct2026.0557.2171.74
Logits LensLLM=Llama-3.1-70B-Instruct2026.0554.560.03
Self-JudgeLLM=Mistral-7B-Instruct-v0.32026.0546.8664.81