Related papers: Unbiased Math Word Problems Benchmark for Mitigati…
We develop a new approach to obtaining high probability regret bounds for online learning with bandit feedback against an adaptive adversary. While existing approaches all require carefully constructing optimistic and biased loss…
Dataset bias is a significant problem in training fair classifiers. When attributes unrelated to classification exhibit strong biases towards certain classes, classifiers trained on such dataset may overfit to these bias attributes,…
Deep-learning based speech separation models confront poor generalization problem that even the state-of-the-art models could abruptly fail when evaluating them in mismatch conditions. To address this problem, we propose an…
Computerized Adaptive Testing (CAT) is a widely used technology for evaluating learners' proficiency in online education platforms. By leveraging prior estimates of proficiency to select questions and updating the estimates iteratively…
Recent studies have shown that generative language models often reflect and amplify societal biases in their outputs. However, these studies frequently conflate observed biases with other task-specific shortcomings, such as comprehension…
Unsupervised neural machine translation (UNMT) has recently attracted great interest in the machine translation community. The main advantage of the UNMT lies in its easy collection of required large training text sentences while with only…
Probabilistic learning is increasingly being tackled as an optimization problem, with gradient-based approaches as predominant methods. When modelling multivariate likelihoods, a usual but undesirable outcome is that the learned model fits…
When training multilingual machine translation (MT) models that can translate to/from multiple languages, we are faced with imbalanced training sets: some languages have much more training data than others. Standard practice is to up-sample…
Given multiple source word embeddings learnt using diverse algorithms and lexical resources, meta word embedding learning methods attempt to learn more accurate and wide-coverage word embeddings. Prior work on meta-embedding has repeatedly…
Unsupervised spoken term discovery (UTD) aims at finding recurring segments of speech from a corpus of acoustic speech data. One potential approach to this problem is to use dynamic time warping (DTW) to find well-aligning patterns from the…
Modern recommendation systems rank candidates by aggregating multiple behavioral signals through a value model. However, many commonly used signals are inherently affected by heterogeneous biases. For example, watch time naturally favors…
Word embeddings trained on large corpora have shown to encode high levels of unfair discriminatory gender, racial, religious and ethnic biases. In contrast, human-written dictionaries describe the meanings of words in a concise, objective…
State-of-the-art language models can match human performance on many tasks, but they still struggle to robustly perform multi-step mathematical reasoning. To diagnose the failures of current models and support research, we introduce GSM8K,…
Artificial intelligence nowadays plays an increasingly prominent role in our life since decisions that were once made by humans are now delegated to automated systems. A machine learning algorithm trained based on biased data, however,…
This paper investigates the question of what makes math word problems (MWPs) in English challenging for large language models (LLMs). We conduct an in-depth analysis of the key linguistic and mathematical characteristics of MWPs. In…
Models notoriously suffer from dataset biases which are detrimental to robustness and generalization. The identify-emphasize paradigm shows a promising effect in dealing with unknown biases. However, we find that it is still plagued by two…
The widespread adoption of ChatGPT has raised concerns about its misuse, highlighting the need for robust detection of AI-generated text. Current word-level detectors are vulnerable to paraphrasing or simple prompts (PSP), suffer from…
Mathematical word problems (MWPs) involve the task of converting textual descriptions into mathematical equations. This poses a significant challenge in natural language processing, particularly for low-resource languages such as Bengali.…
Research in machine learning (ML) has primarily argued that models trained on incomplete or biased datasets can lead to discriminatory outputs. In this commentary, we propose moving the research focus beyond bias-oriented framings by…
Mislabeled, duplicated, or biased data in real-world scenarios can lead to prolonged training and even hinder model convergence. Traditional solutions prioritizing easy or hard samples lack the flexibility to handle such a variety…