Related papers: GAPX: Generalized Autoregressive Paraphrase-Identi…
The proliferation of complex, black-box AI models has intensified the need for techniques that can explain their decisions. Feature attribution methods have become a popular solution for providing post-hoc explanations, yet the field has…
The recent success of large language models for text generation poses a severe threat to academic integrity, as plagiarists can generate realistic paraphrases indistinguishable from original work. However, the role of large autoregressive…
Inference, especially those derived from inductive processes, is a crucial component in our conversation to complement the information implicitly or explicitly conveyed by a speaker. While recent large language models show remarkable…
We evaluated whether model explanations could efficiently detect bias in image classification by highlighting discriminating features, thereby removing the reliance on sensitive attributes for fairness calculations. To this end, we…
State-of-the-art approaches for Knowledge Base Completion (KBC) exploit deep neural networks trained with both false and true assertions: positive assertions are explicitly taken from the knowledge base, whereas negative ones are generated…
Pairwise difference learning (PDL) has recently been introduced as a new meta-learning technique for regression. Instead of learning a mapping from instances to outcomes in the standard way, the key idea is to learn a function that takes…
This paper addresses the quality issues in existing Twitter-based paraphrase datasets, and discusses the necessity of using two separate definitions of paraphrase for identification and generation tasks. We present a new Multi-Topic…
Despite noise and caption quality having been acknowledged as important factors impacting vision-language contrastive pre-training, in this paper, we show that the full potential of improving the training process by addressing such issues…
Distribution shift is a common situation in machine learning tasks, where the data used for training a model is different from the data the model is applied to in the real world. This issue arises across multiple technical settings: from…
Adversarial training methods typically align distributions by solving two-player games. However, in most current formulations, even if the generator aligns perfectly with data, a sub-optimal discriminator can still drive the two apart.…
This paper develops a computational model of paraphrase under which text modification is carried out reluctantly; that is, there are external constraints, such as length or readability, on an otherwise ideal text, and modifications to the…
Paraphrasing is the task of re-writing an input text using other words, without altering the meaning of the original content. Conversational systems can exploit automatic paraphrasing to make the conversation more natural, e.g., talking…
Language model fine-tuning is essential for modern natural language processing, but is computationally expensive and time-consuming. Further, the effectiveness of fine-tuning is limited by the inclusion of training examples that negatively…
Inverse problems, i.e., estimating parameters of physical models from experimental data, are ubiquitous in science and engineering. The Bayesian formulation is the gold standard because it alleviates ill-posedness issues and quantifies…
Prediction models can perform poorly when deployed to target distributions different from the training distribution. To understand these operational failure modes, we develop a method, called DIstribution Shift DEcomposition (DISDE), to…
ChatGPT is one of the most popular language models which achieve amazing performance on various natural language tasks. Consequently, there is also an urgent need to detect the texts generated ChatGPT from human written. One of the…
The task of abductive natural language inference (\alpha{}nli), to decide which hypothesis is the more likely explanation for a set of observations, is a particularly difficult type of NLI. Instead of just determining a causal relationship,…
Learning intents and slot labels from user utterances is a fundamental step in all spoken language understanding (SLU) and dialog systems. State-of-the-art neural network based methods, after deployment, often suffer from performance…
Neural Processes (NPs) (Garnelo et al 2018a;b) approach regression by learning to map a context set of observed input-output pairs to a distribution over regression functions. Each function models the distribution of the output given an…
While counterfactual examples are useful for analysis and training of NLP models, current generation methods either rely on manual labor to create very few counterfactuals, or only instantiate limited types of perturbations such as…