11 accepted papers
Standard RLHF relies on transitive scalar rewards, failing to capture the cyclic nature of human preferences. While some approaches like the General Preference Model (GPM) address this, we identify a theoretical limitation: their implicit formulation entangles hierarchy with cyclicity, failing to gu…
Large Language Models (LLMs) are widely used in legal judgment prediction tasks, which aim to enhance judicial efficiency. However, the length of legal fact descriptions poses a significant challenge to the application of LLMs. Long inputs not only introduce noise, affecting output quality, but also
Domain adaptation is widely employed in cross-domain sentiment analysis, enabling the transfer of models from label-rich source domains to target domain with fewer or no labels. However, concerns have been raised regarding their robustness and sensitivity to data distribution shift, particularly whe…
Sequential Resource Allocation with situational constraints presents a significant challenge in real-world applications, where resource demands and priorities are context-dependent. This paper introduces a novel framework, SCRL, to address this problem. We formalize situational constraints as logic
The prevalent issue in urban trajectory data usage, notably in low-sample rate datasets, revolves around the accuracy of travel time estimations, traffic flow predictions, and trajectory similarity measurements. Conventional methods, often relying on simplistic mixes of static road networks and raw…
A summary structure is inherent to certain types of texts according to the Genre Theory of Linguistics. Such structures aid readers in efficiently locating information within summaries. However, most existing automatic summarization methods overlook the importance of summary structure, resulting in…
Quantization-aware training (QAT) and Knowledge Distillation (KD) are combined to achieve competitive performance in creating low-bit deep learning models. However, existing works applying KD to QAT require tedious hyper-parameter tuning to balance the weights of different loss terms, assume the ava…
Knowledge Transfer (KT) achieves competitive performance and is widely used for image classification tasks in model compression and transfer learning. Existing KT works transfer the information from a large model ("teacher") to train a small model ("student") by minimizing the difference of their co…
Pruning is a promising approach to compress deep learning models in order to deploy them on resource-constrained edge devices. However, many existing pruning solutions are based on unstructured pruning, which yields models that cannot efficiently run on commodity hardware; and they often require use…
Unsupervised/self-supervised graph neural networks (GNN) are susceptible to the inherent randomness in the input graph data, which adversely affects the model's performance in downstream tasks. In this paper, we propose USER, an unsupervised and robust version of GNN based on structural entropy, to…
Legal document classification is an essential task in law intelligence to automate the labor-intensive law case filing process. Unlike traditional document classification problems, legal documents should be classified by reasons and facts instead of topics. We propose a Document-to-Graph Classifier…