Related papers: On Length Divergence Bias in Textual Matching Mode…
Large language models (LLMs) have shown promise as interactive agents that solve tasks through extended sequences of environment interactions. While prior work has primarily focused on system-level optimizations or algorithmic improvements,…
When data is publicly released for human consumption, it is unclear how to prevent its unauthorized usage for machine learning purposes. Successful model training may be preventable with carefully designed dataset modifications, and we…
When pre-processing observational data via matching, we seek to approximate each unit with maximally similar peers that had an alternative treatment status--essentially replicating a randomized block design. However, as one considers a…
Large language models (LLMs) are the foundation of the current successes of artificial intelligence (AI), however, they are unavoidably biased. To effectively communicate the risks and encourage mitigation efforts these models need adequate…
Language models that are trained on the next-word prediction task have been shown to accurately model human behavior in word prediction and reading speed. In contrast with these findings, we present a scenario in which the performance of…
Large language models (LLMs) have achieved state-of-the-art performance on a series of natural language understanding tasks. However, these LLMs might rely on dataset bias and artifacts as shortcuts for prediction. This has significantly…
Examining the alignment of large language models (LLMs) has become increasingly important, e.g., when LLMs fail to operate as intended. This study examines the alignment of LLMs with human values for the domain of politics. Prior research…
Deploying large language models (LLMs) encounters challenges due to intensive computational and memory requirements. Our research examines vocabulary trimming (VT) inspired by restricting embedding entries to the language of interest to…
Linguistic representation learning in deep neural language models (LMs) has been studied for decades, for both practical and theoretical reasons. However, finding representations in LMs remains an unsolved problem, in part due to a dilemma…
Large Language Models (LLMs) inherit explicit and implicit biases from their training datasets. Identifying and mitigating biases in LLMs is crucial to ensure fair outputs, as they can perpetuate harmful stereotypes and misinformation. This…
Neural networks have a number of shortcomings. Amongst the severest ones is the sensitivity to distribution shifts which allows models to be easily fooled into wrong predictions by small perturbations to inputs that are often imperceivable…
Large Language Models (LLMs) are increasingly used in tasks such as psychological text analysis and decision-making in automated workflows. However, their reliability remains a concern due to potential biases inherited from their training…
Deep LSTM is an ideal candidate for text recognition. However text recognition involves some initial image processing steps like segmentation of lines and words which can induce error to the recognition system. Without segmentation,…
Readability assessment aims to automatically classify text by the level appropriate for learning readers. Traditional approaches to this task utilize a variety of linguistically motivated features paired with simple machine learning models.…
Large language models (LLMs) are powerful zero- and few-shot learners. However, when predicting over a set of candidate options, LLMs suffer from label biases, and existing calibration methods overlook biases arising from multi-token class…
Language models suffer from various degenerate behaviors. These differ between tasks: machine translation (MT) exhibits length bias, while tasks like story generation exhibit excessive repetition. Recent work has attributed the difference…
Adversarial attacking aims to fool deep neural networks with adversarial examples. In the field of natural language processing, various textual adversarial attack models have been proposed, varying in the accessibility to the victim model.…
Training models that are robust to data domain shift has gained an increasing interest both in academia and industry. Question-Answering language models, being one of the typical problem in Natural Language Processing (NLP) research, has…
Modeling topics effectively in short texts, such as tweets and news snippets, is crucial to capturing rapidly evolving social trends. Existing topic models often struggle to accurately capture the underlying semantic patterns of short…
Large language models are becoming the go-to solution for the ever-growing number of tasks. However, with growing capacity, models are prone to rely on spurious correlations stemming from biases and stereotypes present in the training data.…