Related papers: Should We Attend More or Less? Modulating Attentio…
Current natural language processing (NLP) research tends to focus on only one or, less frequently, two dimensions - e.g., performance, privacy, fairness, or efficiency - at a time, which may lead to suboptimal conclusions and often…
Attention is a powerful and ubiquitous mechanism for allowing neural models to focus on particular salient pieces of information by taking their weighted average when making predictions. In particular, multi-headed attention is a driving…
Attention mechanisms have seen wide adoption in neural NLP models. In addition to improving predictive performance, these are often touted as affording transparency: models equipped with attention provide a distribution over attended-to…
Attention mechanisms are ubiquitous components in neural architectures applied to natural language processing. In addition to yielding gains in predictive accuracy, attention weights are often claimed to confer interpretability, purportedly…
Natural Language Inference (NLI) models are known to learn from biases and artefacts within their training data, impacting how well they generalise to other unseen datasets. Existing de-biasing approaches focus on preventing the models from…
This paper explores pruning attention heads as a post-processing bias mitigation method for large language models (LLMs). Modern AI systems such as LLMs are expanding into sensitive social contexts where fairness concerns become especially…
Advances in language modeling have led to the development of deep attention-based models that are performant across a wide variety of natural language processing (NLP) problems. These language models are typified by a pre-training process…
Attention mechanisms have recently boosted performance on a range of NLP tasks. Because attention layers explicitly weight input components' representations, it is also often assumed that attention can be used to identify information that…
We explore the internal mechanisms of how bias emerges in large language models (LLMs) when provided with ambiguous comparative prompts: inputs that compare or enforce choosing between two or more entities without providing clear context…
Attention mechanism has become the dominant module in natural language processing models. It is computationally intensive and depends on massive power-hungry multiplications. In this paper, we rethink variants of attention mechanism from…
Attention mechanisms have recently demonstrated impressive performance on a range of NLP tasks, and attention scores are often used as a proxy for model explainability. However, there is a debate on whether attention weights can, in fact,…
Modern NLP systems exhibit a range of biases, which a growing literature on model debiasing attempts to correct. However current progress is hampered by a plurality of definitions of bias, means of quantification, and oftentimes vague…
Attention mechanisms have improved the performance of NLP tasks while allowing models to remain explainable. Self-attention is currently widely used, however interpretability is difficult due to the numerous attention distributions. Recent…
The increasing size of large language models (LLMs) has introduced challenges in their training and inference. Removing model components is perceived as a solution to tackle the large model sizes, however, existing pruning methods solely…
Common methods for interpreting neural models in natural language processing typically examine either their structure or their behavior, but not both. We propose a methodology grounded in the theory of causal mediation analysis for…
Pre-trained language models (PLM) have demonstrated their effectiveness for a broad range of information retrieval and natural language processing tasks. As the core part of PLM, multi-head self-attention is appealing for its ability to…
Class imbalance is a common challenge in many NLP tasks, and has clear connections to bias, in that bias in training data often leads to higher accuracy for majority groups at the expense of minority groups. However there has traditionally…
First derived from human intuition, later adapted to machine translation for automatic token alignment, attention mechanism, a simple method that can be used for encoding sequence data based on the importance score each element is assigned,…
As NLP models become more integrated with the everyday lives of people, it becomes important to examine the social effect that the usage of these systems has. While these models understand language and have increased accuracy on difficult…
Unwanted and often harmful social biases are becoming ever more salient in NLP research, affecting both models and datasets. In this work, we ask whether training on demographically perturbed data leads to fairer language models. We collect…