Related papers: Correcting Negative Bias in Large Language Models …

Deep neural models (e.g. Transformer) naturally learn spurious features, which create a ``shortcut'' between the labels and inputs, thus impairing the generalization and robustness. This paper advances the self-attention mechanism to its…

Recent research has revealed that deep neural networks often take dataset biases as a shortcut to make decisions rather than understand tasks, leading to failures in real-world applications. In this study, we focus on the spurious…

Answer selection (AS) is a critical subtask of the open-domain question answering (QA) problem. The present paper proposes a method called RLAS-BIABC for AS, which is established on attention mechanism-based long short-term memory (LSTM)…

Recent research has shown the potential of Nash Learning via Human Feedback for large language model alignment by incorporating the notion of a preference model in a minimax game setup. We take this idea further by casting the alignment as…

"LLM-as-a-judge," which utilizes large language models (LLMs) as evaluators, has proven effective in many evaluation tasks. However, evaluator LLMs exhibit numerical bias, a phenomenon where certain evaluation scores are generated…

Large language models (LLMs) often exhibit societal biases in their outputs, prompting ethical concerns regarding fairness and harm. In this work, we propose KLAAD (KL-Attention Alignment Debiasing), an attention-based debiasing framework…

Reward models (RMs) play a central role in aligning large language models (LLMs) with human preferences. However, RMs are often sensitive to spurious features such as response length. Existing inference-time approaches for mitigating these…

Biases in the dataset often enable the model to achieve high performance on in-distribution data, while poorly performing on out-of-distribution data. To mitigate the detrimental effect of the bias on the networks, previous works have…

Recently, speech separation (SS) task has achieved remarkable progress driven by deep learning technique. However, it is still challenging to separate target speech from noisy mixture, as the neural model is vulnerable to assign background…

Large Language Models (LLMs) tend to generate a long reasoning chain when solving complex tasks. However, as the reasoning chain extends, critical intermediate steps and the original prompt will be buried in the context, receiving…

Subjective Answer Grading (SAG) plays a crucial role in education, standardized testing, and automated assessment systems, particularly for evaluating short-form responses in Short Answer Scoring (SAS). However, existing approaches often…

Position bias has proven to be a prevalent issue of modern language models (LMs), where the models prioritize content based on its position within the given context. This bias often leads to unexpected model failures and hurts performance,…

Automated short answer scoring (ASAS) is shifting from discriminative, fine-tuned models to large language models (LLMs) used in few-shot settings. This paradigm leverages LLMs broad world knowledge and ease of deployment, but limited…

Two-sample multiple testing problems of sparse spatial data are frequently arising in a variety of scientific applications. In this article, we develop a novel neighborhood-assisted and posterior-adjusted (NAPA) approach to incorporate both…

Contrastive learning has proven instrumental in learning unbiased representations of data, especially in complex environments characterized by high-cardinality and high-dimensional sensitive information. However, existing approaches within…

Automated Short Answer Scoring (SAS) is the task of automatically scoring a given input to a prompt based on rubrics and reference answers. Although SAS is useful in real-world applications, both rubrics and reference answers differ between…

Neural architecture search (NAS) can have a significant impact in computer vision by automatically designing optimal neural network architectures for various tasks. A variant, binarized neural architecture search (BNAS), with a search space…

Large Language Models (LLMs) are trained on large corpora written by humans and demonstrate high performance on various tasks. However, as humans are susceptible to cognitive biases, which can result in irrational judgments, LLMs can also…

Neural language models do not scale well when the vocabulary is large. Noise-contrastive estimation (NCE) is a sampling-based method that allows for fast learning with large vocabularies. Although NCE has shown promising performance in…

Negative binomial regression is commonly employed to analyze overdispersed count data. With small to moderate sample sizes, the maximum likelihood estimator of the dispersion parameter may be subject to a significant bias, that in turn…