Search Results for author:
Found 18 papers, 6 papers with code
Leveraging Gloss Knowledge in Neural Word Sense Disambiguation by Hierarchical Co-Attention
The goal of Word Sense Disambiguation (WSD) is to identify the correct meaning of a word in the particular context.
Learning Robust Representations by Projecting Superficial Statistics Out
We test our method on the battery of standard domain generalization data sets and, interestingly, achieve comparable or better performance as compared to other domain generalization methods that explicitly require samples from the target distribution for training.
Ranked #113 on
Domain Generalization
on PACS
Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding
Written language carries explicit and implicit biases that can distract from meaningful signals.
Weakly Supervised Contrastive Learning for Chest X-Ray Report Generation
Radiology report generation aims at generating descriptive text from radiology images automatically, which may present an opportunity to improve radiology reporting and interpretation.
Leashing the Inner Demons: Self-Detoxification for Language Models
Language models (LMs) can reproduce (or amplify) toxic language seen during training, which poses a risk to their practical application.
Controlling Bias Exposure for Fair Interpretable Predictions
However, when sensitive information is semantically entangled with the task information of the input, e. g., gender information is predictive for a profession, a fair trade-off between task performance and bias mitigation is difficult to achieve.
InterFair: Debiasing with Natural Language Feedback for Fair Interpretable Predictions
In the other setup, human feedback was able to disentangle associated bias and predictive information from the input leading to superior bias mitigation and improved task performance (4-5%) simultaneously.
Synthetic Pre-Training Tasks for Neural Machine Translation
Pre-training models with large crawled corpora can lead to issues such as toxicity and bias, as well as copyright and privacy concerns.
"Nothing Abnormal": Disambiguating Medical Reports via Contrastive Knowledge Infusion
Based on our analysis, we define a disambiguation rewriting task to regenerate an input to be unambiguous while preserving information about the original content.
Targeted Data Generation: Finding and Fixing Model Weaknesses
Even when aggregate accuracy is high, state-of-the-art NLP models often fail systematically on specific subgroups of data, resulting in unfair outcomes and eroding user trust.
Learning Concise and Descriptive Attributes for Visual Recognition
Recent advances in foundation models present new opportunities for interpretable visual recognition -- one can first query Large Language Models (LLMs) to obtain a set of attributes that describe each class, then apply vision-language models to classify images via these attributes.
Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Models
Medical image classification is a critical problem for healthcare, with the potential to alleviate the workload of doctors and facilitate diagnoses of patients.
Farzi Data: Autoregressive Data Distillation
We study data distillation for auto-regressive machine learning tasks, where the input and output have a strict left-to-right causal structure.
MedEval: A Multi-Level, Multi-Task, and Multi-Domain Medical Benchmark for Language Model Evaluation
Curated datasets for healthcare are often limited due to the need of human annotations from experts.
Deciphering Compatibility Relationships with Textual Descriptions via Extraction and Explanation
This fine-tuning allows the model to generate explanations that convey the compatibility relationships between items.
InfoRank: Unbiased Learning-to-Rank via Conditional Mutual Information Minimization
Subsequently, we minimize the mutual information between the observation estimation and the relevance estimation conditioned on the input features.
LVCHAT: Facilitating Long Video Comprehension
To address this issue, we propose Long Video Chat (LVChat), where Frame-Scalable Encoding (FSE) is introduced to dynamically adjust the number of embeddings in alignment with the duration of the video to ensure long videos are not overly compressed into a few embeddings.
CAMELoT: Towards Large Language Models with Training-Free Consolidated Associative Memory
Large Language Models (LLMs) struggle to handle long input sequences due to high memory and runtime costs.
