Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM Text Attribution on SQuAD
Loading...
96
TPR (FPR=0.01)
Binoculars
-3.84
22.08
48
73.92
Jan 4, 2025
TPR (FPR=0.01)
Updated 25d ago
Evaluation Results
Method
Method
Links
TPR (FPR=0.01)
Binoculars
Generator Model=LLAMA...
2025.01
96
Ours
Generator Model=LLAMA...
2025.01
96
Ours
Generator Model=GPT-NE...
2025.01
92
Binoculars
Generator Model=GPT-NE...
2025.01
86
Ours
Generator Model=QWEN 32B
2025.01
72
Binoculars
Generator Model=QWEN 32B
2025.01
26
Rank
Generator Model=GPT-NE...
2025.01
18
Rank
Generator Model=LLAMA...
2025.01
7
LogRank
Generator Model=GPT-NE...
2025.01
6
log p(x)
Generator Model=GPT-NE...
2025.01
5
Entropy
Generator Model=GPT-NE...
2025.01
4
LogRank
Generator Model=LLAMA...
2025.01
2
log p(x)
Generator Model=LLAMA...
2025.01
1
Entropy
Generator Model=LLAMA...
2025.01
1
log p(x)
Generator Model=QWEN 32B
2025.01
1
Rank
Generator Model=QWEN 32B
2025.01
1
LogRank
Generator Model=QWEN 32B
2025.01
1
Entropy
Generator Model=QWEN 32B
2025.01
0
Feedback
Search any
task
Search any
task