Doing Good or Doing Right? Exploring the Weakness of Commonsense Causal
Reasoning Models
- URL: http://arxiv.org/abs/2107.01791v1
- Date: Mon, 5 Jul 2021 05:08:30 GMT
- Title: Doing Good or Doing Right? Exploring the Weakness of Commonsense Causal
Reasoning Models
- Authors: Mingyue Han and Yinglin Wang
- Abstract summary: We investigate the problem of semantic similarity bias and reveal the vulnerability of current COPA models by certain attacks.
We mitigate this problem by simply adding a regularization loss and experimental results show that this solution improves the model's generalization ability.
- Score: 0.38073142980733
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Pretrained language models (PLM) achieve surprising performance on the Choice
of Plausible Alternatives (COPA) task. However, whether PLMs have truly
acquired the ability of causal reasoning remains a question. In this paper, we
investigate the problem of semantic similarity bias and reveal the
vulnerability of current COPA models by certain attacks. Previous solutions
that tackle the superficial cues of unbalanced token distribution still
encounter the same problem of semantic bias, even more seriously due to the
utilization of more training data. We mitigate this problem by simply adding a
regularization loss and experimental results show that this solution not only
improves the model's generalization ability, but also assists the models to
perform more robustly on a challenging dataset, BCOPA-CE, which has unbiased
token distribution and is more difficult for models to distinguish cause and
effect.
Related papers
- Debiasing Algorithm through Model Adaptation [5.482673673984126]
We perform causal analysis to identify problematic model components and discover that mid-upper feed-forward layers are most prone to convey bias.
Based on the analysis results, we intervene in the model by applying a linear projection to the weight matrices of these layers.
Our titular method, DAMA, significantly decreases bias as measured by diverse metrics while maintaining the model's performance on downstream tasks.
arXiv Detail & Related papers (2023-10-29T05:50:03Z) - Delving into Identify-Emphasize Paradigm for Combating Unknown Bias [52.76758938921129]
We propose an effective bias-conflicting scoring method (ECS) to boost the identification accuracy.
We also propose gradient alignment (GA) to balance the contributions of the mined bias-aligned and bias-conflicting samples.
Experiments are conducted on multiple datasets in various settings, demonstrating that the proposed solution can mitigate the impact of unknown biases.
arXiv Detail & Related papers (2023-02-22T14:50:24Z) - Uncertainty Estimation for Language Reward Models [5.33024001730262]
Language models can learn a range of capabilities from unsupervised training on text corpora.
It is often easier for humans to choose between options than to provide labeled data, and prior work has achieved state-of-the-art performance by training a reward model from such preference comparisons.
We seek to address these problems via uncertainty estimation, which can improve sample efficiency and robustness using active learning and risk-averse reinforcement learning.
arXiv Detail & Related papers (2022-03-14T20:13:21Z) - General Greedy De-bias Learning [163.65789778416172]
We propose a General Greedy De-bias learning framework (GGD), which greedily trains the biased models and the base model like gradient descent in functional space.
GGD can learn a more robust base model under the settings of both task-specific biased models with prior knowledge and self-ensemble biased model without prior knowledge.
arXiv Detail & Related papers (2021-12-20T14:47:32Z) - Identifying and Mitigating Spurious Correlations for Improving
Robustness in NLP Models [19.21465581259624]
Many problems can be attributed to models exploiting spurious correlations, or shortcuts between the training data and the task labels.
In this paper, we aim to automatically identify such spurious correlations in NLP models at scale.
We show that our proposed method can effectively and efficiently identify a scalable set of "shortcuts", and mitigating these leads to more robust models in multiple applications.
arXiv Detail & Related papers (2021-10-14T21:40:03Z) - Self-Damaging Contrastive Learning [92.34124578823977]
Unlabeled data in reality is commonly imbalanced and shows a long-tail distribution.
This paper proposes a principled framework called Self-Damaging Contrastive Learning to automatically balance the representation learning without knowing the classes.
Our experiments show that SDCLR significantly improves not only overall accuracies but also balancedness.
arXiv Detail & Related papers (2021-06-06T00:04:49Z) - On the Efficacy of Adversarial Data Collection for Question Answering:
Results from a Large-Scale Randomized Study [65.17429512679695]
In adversarial data collection (ADC), a human workforce interacts with a model in real time, attempting to produce examples that elicit incorrect predictions.
Despite ADC's intuitive appeal, it remains unclear when training on adversarial datasets produces more robust models.
arXiv Detail & Related papers (2021-06-02T00:48:33Z) - Recoding latent sentence representations -- Dynamic gradient-based
activation modification in RNNs [0.0]
In RNNs, encoding information in a suboptimal way can impact the quality of representations based on later elements in the sequence.
I propose an augmentation to standard RNNs in form of a gradient-based correction mechanism.
I conduct different experiments in the context of language modeling, where the impact of using such a mechanism is examined in detail.
arXiv Detail & Related papers (2021-01-03T17:54:17Z) - Learning from others' mistakes: Avoiding dataset biases without modeling
them [111.17078939377313]
State-of-the-art natural language processing (NLP) models often learn to model dataset biases and surface form correlations instead of features that target the intended task.
Previous work has demonstrated effective methods to circumvent these issues when knowledge of the bias is available.
We show a method for training models that learn to ignore these problematic correlations.
arXiv Detail & Related papers (2020-12-02T16:10:54Z) - Mind the Trade-off: Debiasing NLU Models without Degrading the
In-distribution Performance [70.31427277842239]
We introduce a novel debiasing method called confidence regularization.
It discourages models from exploiting biases while enabling them to receive enough incentive to learn from all the training examples.
We evaluate our method on three NLU tasks and show that, in contrast to its predecessors, it improves the performance on out-of-distribution datasets.
arXiv Detail & Related papers (2020-05-01T11:22:55Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.