Search Results for author:
Found 11 papers, 6 papers with code
GrounDial: Human-norm Grounded Safe Dialog Response Generation
Current conversational AI systems based on large language models (LLMs) are known to generate unsafe responses, agreeing to offensive user input or including toxic content.
Probabilistic Concept Bottleneck Models
To provide a reliable interpretation against this ambiguity, we propose Probabilistic Concept Bottleneck Models (ProbCBM).
On the Impact of Knowledge Distillation for Model Interpretability
Several recent studies have elucidated why knowledge distillation (KD) improves model performance.
Grounding Counterfactual Explanation of Image Classifiers to Textual Concept Space
In this paper, we propose counterfactual explanation with text-driven concepts (CounTEX), where the concepts are defined only from text by leveraging a pre-trained multi-modal joint embedding space without additional concept-annotated datasets.
Grounding Visual Representations with Texts for Domain Generalization
In this work, we advocate for leveraging natural language supervision for the domain generalization task.
Bridging the Gap between Classification and Localization for Weakly Supervised Object Localization
Weakly supervised object localization aims to find a target object region in a given image with only weak supervision, such as image-level labels.
Towards a Rigorous Evaluation of Time-series Anomaly Detection
Furthermore, we question the potential of existing TAD methods by showing that an untrained model obtains comparable detection performance to the existing methods even when PA is forbidden.
XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanations
Automated diagnosis using deep neural networks in chest radiography can help radiologists detect life-threatening diseases.
Interpretation of NLP models through input marginalization
To demystify the "black box" property of deep neural networks for natural language processing (NLP), several methods have been proposed to interpret their predictions by measuring the change in prediction probability after erasing each token of an input.
Information-Theoretic Visual Explanation for Black-Box Classifiers
IG map provides a class-independent answer to "How informative is each pixel?
Pre-Training of Deep Bidirectional Protein Sequence Representations with Structural Information
Bridging the exponentially growing gap between the numbers of unlabeled and labeled protein sequences, several studies adopted semi-supervised learning for protein sequence modeling.
Ranked #17 on
Only Connect Walls Dataset Task 1 (Grouping)
on OCW
(using extra training data)
