Related papers: RobustDebias: Debiasing Language Models using Dist…

We propose a diffusion-based framework for prompt optimization that leverages Diffusion Language Models (DLMs) to iteratively refine system prompts through masked denoising. By conditioning on interaction traces, including user queries,…

Recent studies show that large language models (LLMs) improve their performance through self-feedback on certain tasks while degrade on others. We discovered that such a contrary is due to LLM's bias in evaluating their own output. In this…

Many machine learning algorithms are trained and evaluated by splitting data from a single source into training and test sets. While such focus on in-distribution learning scenarios has led to interesting advancement, it has not been able…

Although reinforcement learning (RL) has significantly advanced reasoning capabilities in large multimodal language models (MLLMs), its efficacy remains limited for lightweight models essential for edge deployments. To address this issue,…

This paper studies Distributionally Robust Optimization (DRO), a fundamental framework for enhancing the robustness and generalization of statistical learning and optimization. An effective ambiguity set for DRO must involve distributions…

Credit scoring has been catalogued by the European Commission and the Executive Office of the US President as a high-risk classification task, a key concern being the potential harms of making loan approval decisions based on models that…

Diffusion models that are based on iterative denoising have been recently proposed and leveraged in various generation tasks like image generation. Whereas, as a way inherently built for continuous data, existing diffusion models still have…

Language model pre-training, such as BERT, has achieved remarkable results in many NLP tasks. However, it is unclear why the pre-training-then-fine-tuning paradigm can improve performance and generalization capability across different…

Prompting has shown impressive success in enabling large pretrained language models (LMs) to perform diverse NLP tasks, especially when only few downstream data are available. Automatically finding the optimal prompt for each task, however,…

Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…

Popular Neural Machine Translation model training uses strategies like backtranslation to improve BLEU scores, requiring large amounts of additional data and training. We introduce a class of conditional generative-discriminative hybrid…

Although adapting pre-trained language models with few examples has shown promising performance on text classification, there is a lack of understanding of where the performance gain comes from. In this work, we propose to answer this…

Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive models (ARMs) for language modeling. However, MDMs are known to learn substantially more slowly than ARMs, which may become problematic when scaling…

Transformer-based pretrained large language models (PLM) such as BERT and GPT have achieved remarkable success in NLP tasks. However, PLMs are prone to encoding stereotypical biases. Although a burgeoning literature has emerged on…

In the field of algorithmic fairness, significant attention has been put on group fairness criteria, such as Demographic Parity and Equalized Odds. Nevertheless, these objectives, measured as global averages, have raised concerns about…

Language models (LMs) have become pivotal in the realm of technological advancements. While their capabilities are vast and transformative, they often include societal biases encoded in the human-produced datasets used for their training.…

The recent surge of generative AI has been fueled by the generative power of diffusion probabilistic models and the scalable capabilities of large language models. Despite their potential, it remains elusive whether diffusion language…

Overparameterized neural networks can be highly accurate on average on an i.i.d. test set yet consistently fail on atypical groups of the data (e.g., by learning spurious correlations that hold on average but not in such groups).…

The increasing use of foundation models highlights the urgent need to address and eliminate implicit biases present in them that arise during pretraining. In this paper, we introduce PEFTDebias, a novel approach that employs…

Large Language Models (LLMs) have become pivotal in advancing natural language processing, yet their potential to perpetuate biases poses significant concerns. This paper introduces a new framework employing Direct Preference Optimization…