Search Results for author:
Found 11 papers, 10 papers with code
InterpretCC: Conditional Computation for Inherently Interpretable Neural Networks
Real-world interpretability for neural networks is a tradeoff between three concerns: 1) it requires humans to trust the explanation approximation (e. g. post-hoc approaches), 2) it compromises the understandability of the explanation (e. g. automatically identified feature masks), and 3) it compromises the model performance (e. g. decision trees).
MEDITRON-70B: Scaling Medical Pretraining for Large Language Models
Large language models (LLMs) can potentially democratize access to medical knowledge.
Ranked #1 on
Multiple Choice Question Answering (MCQA)
on MedMCQA
(Dev Set (Acc-%) metric)
Conditional Text Generation
Multiple Choice Question Answering (MCQA)
Unraveling Downstream Gender Bias from Large Language Models: A Study on AI Educational Writing Assistance
Our results demonstrate that there is no significant difference in gender bias between the resulting peer reviews of groups with and without LLM suggestions.
MultiModN- Multimodal, Multi-Task, Interpretable Modular Networks
Predicting multiple real-world tasks in a single model often requires a particularly diverse feature space.
The future of human-centric eXplainable Artificial Intelligence (XAI) is not post-hoc explanations
Explainable Artificial Intelligence (XAI) plays a crucial role in enabling human understanding and trust in deep learning systems, often defined as determining which features are most important to a model's prediction.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
Trusting the Explainers: Teacher Validation of Explainable Artificial Intelligence for Course Design
Deep learning models for learning analytics have become increasingly popular over the last few years; however, these approaches are still not widely adopted in real-world settings, likely due to a lack of trust and transparency.
RIPPLE: Concept-Based Interpretation for Raw Time Series Models in Education
Time series is the most prevalent form of input data for educational prediction tasks.
Bias at a Second Glance: A Deep Dive into Bias for German Educational Peer-Review Data Modeling
We conduct a Word Embedding Association Test (WEAT) analysis on (1) our collected corpus in connection with the clustered labels, (2) the most common pre-trained German language models (T5, BERT, and GPT-2) and GloVe embeddings, and (3) the language models after fine-tuning on our collected data-set.
Evaluating the Explainers: Black-Box Explainable Machine Learning for Student Success Prediction in MOOCs
Neural networks are ubiquitous in applied machine learning for education.
Meta Transfer Learning for Early Success Prediction in MOOCs
Despite the increasing popularity of massive open online courses (MOOCs), many suffer from high dropout and low success rates.
Interpreting Language Models Through Knowledge Graph Extraction
In this paper, we compare BERT-based language models through snapshots of acquired knowledge at sequential stages of the training process.
