14 citations · 31 across the 16 of their papers we have counts for
17 papers
REAL: Reading Out Transformer Activations for Precise Localization in Language Model Steering
Li-Ming Zhan, Bo Liu, Chengqiang Xie +2
Inference-time steering aims to alter a large language model's (LLM's) responses without changing its parameters, but a central challenge is identifying the internal modules that m…
GeoEdit: Geometric Knowledge Editing for Large Language Models
Yujie Feng, Liming Zhan, Zexin Lu +6
Regular updates are essential for maintaining up-to-date knowledge in large language models (LLMs). Consequently, various model editing methods have been developed to update specif…
GEMeX: A Large-Scale, Groundable, and Explainable Medical VQA Benchmark for Chest X-ray Diagnosis
Bo Liu, Ke Zou, Liming Zhan +7
Medical Visual Question Answering (Med-VQA) combines computer vision and natural language processing to automatically answer clinical inquiries about medical images. However, curre…
Diversity-grounded Channel Prototypical Learning for Out-of-Distribution Intent Detection
Bo Liu, Liming Zhan, Yujie Feng +5
In the realm of task-oriented dialogue systems, a robust intent detection mechanism must effectively handle malformed utterances encountered in real-world scenarios. This study pre…
Continual Dialogue State Tracking via Reason-of-Select Distillation
Yujie Feng, Bo Liu, Xiaoyu Dong +4
An ideal dialogue system requires continuous skill acquisition and adaptation to new tasks while retaining prior knowledge. Dialogue State Tracking (DST), vital in these systems, o…
VI-OOD: A Unified Representation Learning Framework for Textual Out-of-distribution Detection
Li-Ming Zhan, Bo Liu, Xiao-Ming Wu
Out-of-distribution (OOD) detection plays a crucial role in ensuring the safety and reliability of deep neural networks in various applications. While there has been a growing focu…
Towards LLM-driven Dialogue State Tracking
Yujie Feng, Zexin Lu, Bo Liu +2
Dialogue State Tracking (DST) is of paramount importance in ensuring accurate tracking of user goals and system actions within task-oriented dialogue systems. The emergence of larg…
How Good Are LLMs at Out-of-Distribution Detection?
Bo Liu, Liming Zhan, Zexin Lu +3
Out-of-distribution (OOD) detection plays a vital role in enhancing the reliability of machine learning (ML) models. The emergence of large language models (LLMs) has catalyzed a p…
Revisit Few-shot Intent Classification with PLMs: Direct Fine-tuning vs. Continual Pre-training
Haode Zhang, Haowen Liang, Liming Zhan +2
We consider the task of few-shot intent detection, which involves training a deep learning model to classify utterances based on their underlying intents using only a small amount…
New Intent Discovery with Pre-training and Contrastive Learning
Yuwei Zhang, Haode Zhang, Li-Ming Zhan +2
New intent discovery aims to uncover novel intent categories from user utterances to expand the set of supported intent classes. It is a critical task for the development and servi…
Fine-tuning Pre-trained Language Models for Few-shot Intent Detection: Supervised Pre-training and Isotropization
Haode Zhang, Haowen Liang, Yuwei Zhang +4
It is challenging to train a good intent classifier for a task-oriented dialogue system with only a few annotations. Recent studies have shown that fine-tuning pre-trained language…
Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima
Guangyuan Shi, Jiaxin Chen, Wenlong Zhang +2
This paper considers incremental few-shot learning, which requires a model to continually recognize new categories with only a few examples provided. Our study shows that existing…
Effectiveness of Pre-training for Few-shot Intent Classification
Haode Zhang, Yuwei Zhang, Li-Ming Zhan +4
This paper investigates the effectiveness of pre-training for few-shot intent classification. While existing paradigms commonly further pre-train language models such as BERT on a…
Adaptation-Agnostic Meta-Training
Jiaxin Chen, Li-Ming Zhan, Xiao-Ming Wu +1
Many meta-learning algorithms can be formulated into an interleaved process, in the sense that task-specific predictors are learned during inner-task adaptation and meta-parameters…
Out-of-Scope Intent Detection with Self-Supervision and Discriminative Training
Li-Ming Zhan, Haowen Liang, Bo Liu +3
Out-of-scope intent detection is of practical importance in task-oriented dialogue systems. Since the distribution of outlier utterances is arbitrary and unknown in the training st…
SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering
Bo Liu, Li-Ming Zhan, Li Xu +3
Medical visual question answering (Med-VQA) has tremendous potential in healthcare. However, the development of this technology is hindered by the lacking of publicly-available and…
Variational Metric Scaling for Metric-Based Meta-Learning
Jiaxin Chen, Li-Ming Zhan, Xiao-Ming Wu +1
Metric-based meta-learning has attracted a lot of attention due to its effectiveness and efficiency in few-shot learning. Recent studies show that metric scaling plays a crucial ro…