Computer Science (CS) stands as a testament to the intricacies of human intelligence, profoundly advancing the development of artificial intelligence and modern society. However, the current community of large language models (LLMs) overly focuses on …
Pre-trained language models have been successful in many scenarios. However, their usefulness in task-oriented dialogues is limited due to the intrinsic linguistic differences between general text and task-oriented dialogues. Current task-oriented …
Language models pre-trained on general text have achieved impressive results in diverse fields. Yet, the distinct linguistic characteristics of task-oriented dialogues (TOD) compared to general text limit the practical utility of existing language …
Addressing the discrepancies between predictions and actual outcomes often aids individuals in expanding their thought processes and engaging in reflection, thereby facilitating reasoning in the correct direction. In this paper, we introduce PreAct, …
In the deployment of large language models (LLMs), accurate confidence estimation is critical for assessing the credibility of model predictions. However, existing methods often fail to overcome the issue of overconfidence on incorrect answers. In …
Code Large Language Models (Code LLMs) have demonstrated outstanding performance in code-related tasks. Several instruction tuning approaches have been proposed to boost the code generation performance of pre-trained Code LLMs. In this paper, we …
Knowledge editing (KE) aims to efficiently and precisely modify the behavior of large language models (LLMs) to update specific knowledge without negatively influencing other knowledge. Current research primarily focuses on white-box LLMs editing, …
We utilize a multi-level data augmentation method (character, word, and sentence levels) to construct a candidate data pool, and carefully design two ways of automatic task demonstration construction strategies (instance-level and entity-level) with …
Zero-shot Dialogue State Tracking (DST) addresses the challenge of acquiring and annotating task-oriented dialogues, which can be time consuming and costly. However, DST extends beyond simple slot-filling and requires effective updating strategies …