相关论文: Casual as an Anchor: Resolving Supervision Misalig…

Fine-tuning Large Language Models (LLMs) on specific datasets is a common practice to improve performance on target tasks. However, this performance gain often leads to overfitting, where the model becomes too specialized in either the task…

The deployment of Large Language Models (LLMs) in high-stakes medical settings poses a critical AI alignment challenge, as models can inherit and amplify societal biases, leading to significant disparities. Existing fairness evaluation…

Recent advances in large language models have laid the foundation for multimodal LLMs (MLLMs), which unify text, speech, and vision within a single framework. As these models are rapidly evolving toward general-purpose instruction following…

Foundation models have demonstrated a great ability to achieve general human-level intelligence far beyond traditional approaches. As the technique keeps attracting attention from the AI community, an increasing number of foundation models…

Large language models (LLMs) have exhibited impressive performance and surprising emergent properties. However, their effectiveness remains limited by the fixed context window of the transformer architecture, posing challenges for…

The prevalence of noisy labels in real-world datasets poses a significant impediment to the effective deployment of deep learning models. While meta-learning strategies have emerged as a promising approach for addressing this challenge,…

Safety benchmark scores provide incomplete evidence of deployment readiness: aligned language models often adhere to rigid rules even when a situational update flips which action is safe. We term this failure brittle safety. To diagnose it,…

Deep learning (e.g., Transformer) has been widely and successfully used in multivariate time series forecasting (MTSF). Unlike existing methods that focus on training models from a single modal of time series input, large language models…

Recently, there has been a growing interest in developing machine learning (ML) models that can promote fairness, i.e., eliminating biased predictions towards certain populations (e.g., individuals from a specific demographic group). Most…

Due to the advantages of leveraging unlabeled data and learning meaningful representations, semi-supervised learning and contrastive learning have been progressively combined to achieve better performances in popular applications with few…

Student engagement with large language models (LLMs) in academic writing is not a stable trait, an adoption decision, or a competency level; it is a continuously negotiated process that existing frameworks cannot adequately theorize.…

Modern visual recognition models often display overconfidence due to their reliance on complex deep neural networks and one-hot target supervision, resulting in unreliable confidence scores that necessitate calibration. While current…

In recent research on large language models (LLMs), there has been a growing emphasis on aligning these models with human values to reduce the impact of harmful content. However, current alignment methods often rely solely on singular forms…

Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing safety training techniques like Supervised Fine-tuning (SFT)…

Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique to make large language models (LLMs) more capable in complex settings. RLHF proceeds as collecting human preference data, training a reward model on said…

As machine learning models continue to increase in complexity, collecting large hand-labeled training sets has become one of the biggest roadblocks in practice. Instead, weaker forms of supervision that provide noisier but cheaper labels…

Machine learning classifiers' capability is largely dependent on the scale of available training data and limited by the model overfitting in data-scarce learning tasks. To address this problem, this work proposes a novel framework of Meta…

Several benchmarks have been built with heavy investment in resources to track our progress in NLP. Thousands of papers published in response to those benchmarks have competed to top leaderboards, with models often surpassing human…

Fine-tuning LLMs on narrowly harmful datasets can lead to behavior that is broadly misaligned with respect to human values. To understand when and how this emergent misalignment occurs, we develop a comprehensive framework for detecting and…

Deep supervised learning has achieved remarkable success across a wide range of tasks, yet it remains susceptible to overfitting when confronted with noisy labels. To address this issue, noise-robust loss functions offer an effective…