Related papers: CORAL: Contextual Response Retrievability Loss Fun…

In the realm of time series analysis, tackling the phenomenon of concept drift poses a significant challenge. Concept drift -- characterized by the evolving statistical properties of time series data, affects the reliability and accuracy of…

Causal representation learning (CRL) and traditional representation learning have largely developed along different trajectories. Traditional representation learning has been driven mainly by applications and empirical objectives, whereas…

Conversational recommender systems have attracted immense attention recently. The most recent approaches rely on neural models trained on recorded dialogs between humans, implementing an end-to-end learning process. These systems are…

Causal representation learning (CRL) models aim to transform high-dimensional data into a latent space, enabling interventions to generate counterfactual samples or modify existing data based on the causal relationships among latent…

The development of deep convolutional neural network architecture is critical to the improvement of image classification task performance. A lot of studies of image classification based on deep convolutional neural network focus on the…

Large Language Models (LLMs) have demonstrated impressive performance across various tasks. However, current training approaches combine standard cross-entropy loss with extensive data, human feedback, or ad hoc methods to enhance…

In multi-turn dialog, utterances do not always take the full form of sentences \cite{Carbonell1983DiscoursePA}, which naturally makes understanding the dialog context more difficult. However, it is essential to fully grasp the dialog…

Large language models (LLMs) often solve challenging math exercises yet fail to apply the concept right when the problem requires genuine understanding. Popular Reinforcement Learning with Verifiable Rewards (RLVR) pipelines reinforce final…

Reinforcement Learning (RL) faces significant challenges in adaptive healthcare interventions, such as dementia care, where data is scarce, decisions require interpretability, and underlying patient-state dynamic are complex and causal in…

Context-based offline meta-reinforcement learning (OMRL) methods have achieved appealing success by leveraging pre-collected offline datasets to develop task representations that guide policy learning. However, current context-based OMRL…

Knowledge-grounded dialogue generation aims to mitigate the issue of text degeneration by incorporating external knowledge to supplement the context. However, the model often fails to internalize this information into responses in a…

In task-oriented dialogs (TOD), reinforcement learning (RL) algorithms train a model to directly optimize response for task-related metrics. However, RL needs to perform exploration, which can be time-consuming due to the slow…

Although large language models (LLMs) perform well in general tasks, domain-specific applications suffer from hallucinations and accuracy limitations. Continual Pre-Training (CPT) approaches encounter two key issues: (1) domain-biased data…

Captioning models are typically trained using the cross-entropy loss. However, their performance is evaluated on other metrics designed to better correlate with human assessments. Recently, it has been shown that reinforcement learning (RL)…

Neural models trained for next utterance generation in dialogue task learn to mimic the n-gram sequences in the training set with training objectives like negative log-likelihood (NLL) or cross-entropy. Such commonly used training…

Large language models (LLMs) exhibit persistent miscalibration, especially after instruction tuning and preference alignment. Modified training objectives can improve calibration, but retraining is expensive. Inference-time steering offers…

Reinforcement learning (RL) is a powerful approach to enhance task-oriented dialogue (TOD) systems. However, existing RL methods tend to mainly focus on generation tasks, such as dialogue policy learning (DPL) or response generation (RG),…

Continual relation extraction (CRE) aims to solve the problem of catastrophic forgetting when learning a sequence of newly emerging relations. Recent CRE studies have found that catastrophic forgetting arises from the model's lack of…

The development of trustworthy conversational information-seeking systems relies on dialogue models that can generate faithful and accurate responses based on relevant knowledge texts. However, two main challenges hinder this task. Firstly,…

Large language models exhibit complementary reasoning errors: on the same instance, one model may succeed with a particular decomposition while another fails. We propose Collaborative Reasoning (CORE), a training-time collaboration…