41 accepted papers
Aligning large language models (LLMs) to heterogeneous and rapidly evolving safety requirements remains a critical challenge. Existing instruction-tuned LLMs and standalone safety classifiers often fail to generalize to new safety configurations, motivating the need for Reward Models (RMs) that are …
An agent must try new behaviors to explore and improve. In high-stakes environments, an agent that violates safety constraints may cause harm and must be taken offline, curtailing any future interaction. Imitating old behavior is safe, but excessive conservatism discourages exploration. How much beh…
Large language models (LLMs) can be influenced by harmful or irrelevant context, which can significantly harm model performance on downstream tasks. This motivates principled designs in which LLM systems include built-in mechanisms to guard against such "garbage in, garbage out" scenarios. We propos…
Autonomous driving requires safe planning, but most learning-based planners lack explicit self-correction ability: once an unsafe action is proposed, there is no mechanism to correct it. Thus, we propose CorrectionPlanner, an autoregressive planner with self-correction that models planning as motion…
Offline-to-Online Reinforcement Learning (O2O-RL) leverages an offline, pre-trained policy to minimize costly online interactions. Although data-efficient, O2O-RL is susceptible to shifts between offline and online distributions. Existing work aims to mitigate the harm of this shift by finetuning th…
Supervised Fine-Tuning (SFT) is used to specialize model behavior by training weights to produce intended target responses for queries. In contrast, In-Context Learning (ICL) adapts models during inference with instructions or demonstrations in the prompt. ICL can offer better generalizability and…
We study off-dynamics offline reinforcement learning, where the goal is to learn a policy from offline source and limited target datasets with mismatched dynamics. Existing methods either penalize the reward or discard source transitions occurring in parts of the transition space with high dynamics…
The opioid crisis represents a significant moment in public health that reveals systemic shortcomings across regulatory systems, healthcare practices, corporate governance, and public policy. Analyzing how these interconnected systems simultaneously failed to protect public health requires innovativ
Calibration aligns a model's predictive uncertainty with the frequencies of its empirical outcomes and is important toward understanding and trusting reported probabilities. Recent work shows that enforcing calibration at the level of individual predictors can substantially improve ensemble performa…
Language model outputs are not always reliable, thus prompting research into how to adapt model responses based on uncertainty. Common approaches include: abstention, where models refrain from generating responses when uncertain; and linguistic calibration, where models hedge their statements using…
Hallucinations pose a challenge to the application of large language models (LLMs) thereby motivating the development of metrics to evaluate factual precision. We observe that popular metrics using the Decompose-Then-Verify framework, such as FActScore, can be manipulated by adding obvious or repeti…
Recent works have suggested that In-Context Learning (ICL) operates in dual modes, i.e. task retrieval (remember learned patterns from pre-training) and task learning (inference-time ”learning” from demonstrations). However, disentangling these the two modes remains a challenging goal. We introduce
Interruptions, a fundamental component of human communication, can enhance the dynamics and effectiveness of conversations, but only when effectively managed by all parties involved. Despite advancements in robotic systems, state-of-the-art systems still have limited capabilities in handling user-in…
Reliable and accurate estimation of the error of an ML model in unseen test domains is an important problem for safe intelligent systems. Prior work uses \textit{disagreement discrepancy} (\disdis) to derive practical error bounds under distribution shifts. It optimizes for a maximally disagreeing c
By leveraging the representation power of deep neural networks, neural upper confidence bound (UCB) algorithms have shown success in contextual bandits. To further balance the exploration and exploitation, we propose Neural-$\sigma^2$-LinearUCB, a variance-aware algorithm that utilizes $\sigma^2_t$,…
Responsibly deploying artificial intelligence (AI) / machine learning (ML) systems in high-stakes settings arguably requires not only proof of system reliability, but also continual, post-deployment monitoring to quickly detect and address any unsafe behavior. Methods for nonparametric sequential te…
Research in document image understanding is hindered by limited high-quality document data. To address this, we introduce ADOPD, a comprehensive dataset for document page decomposition. ADOPD stands out with its data-driven approach for document taxonomy discovery during data collection, complemente…
As artificial intelligence (AI) / machine learning (ML) gain widespread adoption, practitioners are increasingly seeking means to quantify and control the risk these systems incur. This challenge is especially salient when such systems have autonomy to collect their own data, such as in black-box op…
Morden deep ensembles technique achieves strong uncertainty estimation performance by going through multiple forward passes with different models. This is at the price of a high storage space and a slow speed in the inference (test) time. To address this issue, we propose Density-Regression, a metho…
Sampling-based methods, e.g., Deep Ensembles and Bayesian Neural Nets have become promising approaches to improve the quality of uncertainty estimation and robust generalization. However, they suffer from a large model size and high latency at test time, which limits the scalability needed for low-r…
Training a policy in a source domain for deployment in the target domain under a dynamics shift can be challenging, often resulting in performance degradation. Previous work tackles this challenge by training on the source domain with modified rewards derived by matching distributions between the so…
Free-text rationales play a pivotal role in explainable NLP, bridging the knowledge and reasoning gaps behind a model’s decision-making. However, due to the diversity of potential reasoning paths and a corresponding lack of definitive ground truth, their evaluation remains a challenge. Existing metr…
Despite advancements in robotic-assisted surgery, automating complex tasks like suturing remains challenging due to the need for adaptability and precision. Learning-based approaches, particularly reinforcement learning (RL) and imitation learning (IL), require realistic simulation environments for…
Large-scale pre-training is widely used in recent document understanding tasks. During deployment, one may expect that models should trigger a conservative fallback policy when encountering out-of-distribution (OOD) samples, which highlights the importance of OOD detection. However, most existing OO…
Learning an optimal policy from offline data is notoriously challenging, which requires the evaluation of the learning policy using data pre-collected from a static logging policy. We study the policy optimization problem in offline contextual bandits using policy gradient methods. We employ a distr…
Supervised learning is often affected by a covariate shift in which the marginal distributions of instances (covariates $x$) of training and testing samples $p_\text{tr}(x)$ and $p_\text{te}(x)$ are different but the label conditionals coincide. Existing approaches address such covariate shift by ei…
In the target-oriented dialogue, the representation and achievement of targets are two interrelated essential issues. In current approaches, the target is typically supposed to be a single object represented as a word, which makes it relatively easy to achieve the target through dialogue with the he…
We study the efficient estimation of predictive confidence intervals for black-box predictors when the common data exchangeability (e.g., i.i.d.) assumption is violated due to potentially feedback-induced shifts in the input data distribution. That is, we focus on standard and feedback covariate shi…
We propose a framework for learning calibrated uncertainties under domain shifts, considering the case where the source (training) distribution differs from the target (test) distribution. We detect such domain shifts through the use of a differentiable density ratio estimator and train it together…
Target-oriented dialogue guides the dialogue to a target quickly and smoothly. The latest approaches focus on global planning, which plans toward the target before the conversation instead of adopting a greedy strategy during the conversation. However, the global plan in existing works is fixed to c…
Contemporary vision benchmarks predominantly consider tasks on which humans can achieve near-perfect performance. However, humans are frequently presented with visual data that they cannot classify with 100% certainty, and models trained on standard vision benchmarks achieve low performance when eva…
We investigate model calibration in the setting of zero-shot cross-lingual transfer with large-scale pre-trained language models. The level of model calibration is an important metric for evaluating the trustworthiness of predictive models. There exists an essential need for model calibration when n…
We propose \textbf{JAWS}, a series of wrapper methods for distribution-free uncertainty quantification tasks under covariate shift, centered on the core method \textbf{JAW}, the \textbf{JA}ckknife+ \textbf{W}eighted with data-dependent likelihood-ratio weights. JAWS also includes computationally eff…
We address the problem of active learning under label shift: when the class proportions of source and target domains differ. We introduce a "medial distribution" to incorporate a tradeoff between importance weighting and class-balanced sampling and propose their combined usage in active learning. Ou…
Learning-based control algorithms require data collection with abundant supervision for training. Safe exploration algorithms ensure the safety of this data collection process even when only partial knowledge is available. We present a new approach for optimal motion planning with safe exploration t
In recent years, single image super-resolution based on convolution neural network (CNN) has been extensively researched. However, most CNN-based methods only focus on mining features at a single resolution, which will cause the loss of some useful information. Besides, most of them still have diffi…
Making predictions that are fair with regard to protected attributes (race, gender, age, etc.) has become an important requirement for classification algorithms. Existing techniques derive a fair model from sampled labeled data relying on the assumption that training and testing data are identically…
Active learning methods, like uncertainty sampling, combined with probabilistic prediction techniques have achieved success in various problems like image classification and text classification. For more complex multivariate prediction tasks, the relationships between labels play an important role i…
We propose Regularized Learning under Label shifts (RLLS), a principled and a practical domain-adaptation algorithm to correct for shifts in the label distribution between a source and a target domain. We first estimate importance weights using labeled source data and unlabeled target data, and then…
Recently proposed adversarial classification methods have shown promising results for cost sensitive and multivariate losses. In contrast with empirical risk minimization (ERM) methods, which use convex surrogate losses to approximate the desired non-convex target loss function, adversarial methods…
In many learning settings, the source data available to train a regression model differs from the target data it encounters when making predictions due to input distribution shift. Appropriately dealing with this situation remains an important challenge. Existing methods attempt to “reweight” the so…