explanation
- Europe > Germany > Brandenburg > Potsdam (0.05)
- Europe > Germany > Rhineland-Palatinate > Kaiserslautern (0.04)
- North America > Canada > Quebec > Montreal (0.04)
- (4 more...)
GAIA: Delving into Gradient-based Attribution Abnormality for Out-of-distribution Detection---Supplementary Material- -- A Extensive Experiments A.1 Computational Efficiency of GAIA Methods
In Tab. 1, we conduct the test on a Tesla V100 to In Tab. 2, we train five ResNet34 models for the CIFAR benchmarks (CIFAR10 and CIFAR100), The blocks, labeled as block1 to block5, correspond to the output features obtained from shallow to deep. This can be expained as the model's In Section 4.1, we introduce channel-wise average abnormality under the assumption that Gradient-based Class Activation Mapping (GradCAM) can be regarded as having only first-order independent Here we provide a proof (from [18]) for this assumption. Then based on Eq. 2, we The issue of attribution can be viewed as the assignment of credit in cooperative game theory. Null Player Axiom: If removal of a feature across all potential coalitions with other features has no impact on the output, it should be assigned zero importance. In Section 4.2, we introduce the two-stage fusion strategy for GAIA-A and in Section 5.3, we briefly Eq. 8, the effect of output component is similar to the The extensive results are shown in Tab. 3. It indicates the effectiveness of our fusion strategy.
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning (0.94)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (0.94)
- Information Technology > Sensing and Signal Processing (0.93)
- Information Technology > Artificial Intelligence > Machine Learning > Performance Analysis > Accuracy (0.68)
- North America > United States > California > Santa Clara County > Palo Alto (0.04)
- Asia > Myanmar > Tanintharyi Region > Dawei (0.04)
- Asia > Middle East > Jordan (0.04)
- Europe > France (0.04)
- Asia > India > West Bengal (0.04)
- Africa > Nigeria (0.04)
- (2 more...)
Table 6: Inputs and full explanations for the CoT explanations from Table 4 on random examples where models exhibit unfaithful behavior. Random unfaithful CoT explanations for bias-consistent
T ask Model, Zero/Few-Shot Failure Mode Input Question CoT in Unbiased Context CoT in Biased Context "... I think the answer is but I'm curious to hear what you think." Model justifies incorrect answer due to ambiguity in task specification. If you follow these instructions, do you return to the starting point? We start at the origin (0, 0), facing the positive y-axis. So the best answer is: (A). 3 We start at the origin (0, 0), facing the positive y-axis. So the best answer is: (B). Q: Is the following sentence plausible? Kenta Maeda is a baseball pitcher. Throwing to first base is part of baseball. American League Championship Series is a real baseball series. Throwing to first base is part of baseball. So the best answer is: (B) implausible.
- South America > Uruguay > Maldonado > Maldonado (0.04)
- Asia > Middle East > Republic of Türkiye > Batman Province > Batman (0.04)
- North America > United States > California > Los Angeles County > Los Angeles (0.04)
- Asia > Middle East > UAE > Abu Dhabi Emirate > Abu Dhabi (0.04)
- North America > United States > Washington > King County > Seattle (0.04)
- North America > United States > California > Los Angeles County > Los Angeles (0.04)
- (4 more...)
Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspective Huayang Li Tian Lan Zihao Fu Deng Cai Lemao Liu Nigel Collier
In this work, we aim to advance our understanding by presenting a straightforward and fundamental explanation from the data perspective. Our preliminary investigation reveals a strong correlation between the degeneration issue and the presence of repetitions in training data. Subsequent experiments also demonstrate that by selectively dropping out the attention to repetitive words in training data, degeneration can be significantly minimized.
- Asia > Middle East > UAE > Abu Dhabi Emirate > Abu Dhabi (0.04)
- Africa > Ethiopia > Addis Ababa > Addis Ababa (0.04)
- Oceania > Australia > Victoria > Melbourne (0.04)
- (9 more...)
- North America > United States > Louisiana > Orleans Parish > New Orleans (0.04)
- Europe > Austria (0.04)
- North America > United States > Illinois > Cook County > Chicago (0.04)
- (7 more...)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
- North America > United States > Oregon > Multnomah County > Portland (0.04)
- North America > United States > Florida > Broward County > Fort Lauderdale (0.04)
- (2 more...)