Search Results for author:
Found 9 papers, 7 papers with code
In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation
Large language models (LLMs) frequently hallucinate and produce factual errors, yet our understanding of why they make these errors remains limited.
Prompt-and-Align: Prompt-Based Social Alignment for Few-Shot Fake News Detection
Despite considerable advances in automated fake news detection, due to the timely nature of news, it remains a critical open question how to effectively predict the veracity of news articles based on limited fact-checks.
Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs
To better break down the problem, we define a systematic framework with three components: prompting strategies for eliciting verbalized confidence, sampling methods for generating multiple responses, and aggregation techniques for computing consistency.
Proximity-Informed Calibration for Deep Neural Networks
We examine the problem over 504 pretrained ImageNet models and observe that: 1) Proximity bias exists across a wide variety of model architectures and sizes; 2) Transformer-based models are relatively more susceptible to proximity bias than CNN-based models; 3) Proximity bias persists even after performing popular calibration algorithms like temperature scaling; 4) Models tend to overfit more heavily on low proximity samples than on high proximity samples.
GraphCleaner: Detecting Mislabelled Samples in Popular Graph Learning Benchmarks
Label errors have been found to be prevalent in popular text, vision, and audio datasets, which heavily influence the safe development and evaluation of machine learning algorithms.
Great Models Think Alike: Improving Model Reliability via Inter-Model Latent Agreement
To overcome this incoherence issue, we design a \emph{neighborhood agreement measure} between latent spaces and find that this agreement is surprisingly well-correlated with the reliability of a model's predictions.
Trust, but Verify: Using Self-Supervised Probing to Improve Trustworthiness
Trustworthy machine learning is of primary importance to the practical deployment of deep learning models.
Probabilistic Knowledge Distillation of Face Ensembles
Mean ensemble (i. e. averaging predictions from multiple models) is a commonly-used technique in machine learning that improves the performance of each individual model.
Birds of a Feather Trust Together: Knowing When to Trust a Classifier via Adaptive Neighborhood Aggregation
How do we know when the predictions made by a classifier can be trusted?
