Related papers: Aioli: A Unified Optimization Framework for Langua…

Detecting out of policy speech (OOPS) content is important but difficult. While machine learning is a powerful tool to tackle this challenging task, it is hard to break the performance ceiling due to factors like quantity and quality…

Artificial Intelligence (AI) has increasingly influenced modern society, recently in particular through significant advancements in Large Language Models (LLMs). However, high computational and storage demands of LLMs still limit their…

Existing alignment methods for preference optimization of large language models (LLMs) aim to enhance model performance by utilizing pairs of positive and negative samples. However, due to the limited capacity of models in scoring or…

Uncertainty estimation remains a key challenge when adapting pre-trained language models to downstream classification tasks, with overconfidence often observed for difficult inputs. While predictive entropy provides a strong baseline for…

Large Language Models (LLMs) have made significant strides in the field of artificial intelligence, showcasing their ability to interact with humans and influence human cognition through information dissemination. However, recent studies…

A fundamental problem in robotic perception is matching identical objects or data, with applications such as loop closure detection, place recognition, object tracking, and map fusion. While the problem becomes considerably more challenging…

The emergence of learned indexes has caused a paradigm shift in our perception of indexing by considering indexes as predictive models that estimate keys' positions within a data set, resulting in notable improvements in key search…

Fine-tuning pretrained language models (PLMs) on downstream tasks has become common practice in natural language processing. However, most of the PLMs are vulnerable, e.g., they are brittle under adversarial attacks or imbalanced data,…

In language model training, it is desirable to equip models with capabilities from various tasks. However, it is not clear how to directly obtain the right data mixtures for these capabilities as the relationship between data and tasks is…

Multimodal learning has significantly enhanced machine learning performance but still faces numerous challenges and limitations. Imbalanced multimodal learning is one of the problems extensively studied in recent works and is typically…

Large Language Models (LLMs) can adapt to new tasks via in-context learning (ICL). ICL is efficient as it does not require any parameter updates to the trained LLM, but only few annotated examples as input for the LLM. In this work, we…

Ensuring that Large Language Models (LLMs) generate text representative of diverse sub-populations is essential, particularly when key concepts related to under-represented groups are scarce in the training data. We address this challenge…

Large volumes of text data have contributed significantly to the development of large language models (LLMs) in recent years. This data is typically acquired by scraping the internet, leading to pretraining datasets comprised of noisy web…

Determining an effective data mixture is a key factor in Large Language Model (LLM) pre-training, where models must balance general competence with proficiency on hard tasks such as math and code. However, identifying an optimal mixture…

The increasing prevalence of AI-generated content alongside human-written text underscores the need for reliable discrimination methods. To address this challenge, we propose a novel framework with textual embeddings from Pre-trained…

Training reliable respiratory sound classification models remains challenging due to the limited size and subject diversity of datasets. Ensemble methods can improve robustness, but when base models are trained on identical data, models…

Accurate uncertainty quantification is crucial for the safe deployment of machine learning models, and prior research has demonstrated improvements in the calibration of modern language models (LMs). We study in-context learning (ICL), a…

Comprehending natural language and following human instructions are critical capabilities for intelligent agents. However, the flexibility of linguistic instructions induces substantial ambiguity across language-conditioned tasks, severely…

Large-scale pre-trained language models have demonstrated high performance on standard datasets for natural language inference (NLI) tasks. Unfortunately, these evaluations can be misleading, as although the models can perform well on…

This paper introduces two novel modifications to the Dynamic sAmpling Policy Optimization (DAPO) algorithm [1], approached from a mixed-policy perspective. Standard policy gradient methods can suffer from instability and sample…