Search Results for author:
Found 7 papers, 3 papers with code
Towards Reliable Latent Knowledge Estimation in LLMs: In-Context Learning vs. Prompting Based Factual Knowledge Extraction
We propose an approach for estimating the latent knowledge embedded inside large language models (LLMs).
Pointwise Representational Similarity
Concretely, we show how PNKA can be leveraged to develop a deeper understanding of (a) the input examples that are likely to be misclassified, (b) the concepts encoded by (individual) neurons in a layer, and (c) the effects of fairness interventions on learned representations.
Measuring Representational Robustness of Neural Networks Through Shared Invariances
Our work offers a new view on robustness by using another reference NN to define the set of perturbations a given NN should be invariant to, thus generalizing the reliance on a reference ``human NN'' to any NN.
Unifying Model Explainability and Robustness via Machine-Checkable Concepts
Our framework defines a large number of concepts that the DNN explanations could be based on and performs the explanation-conformity check at test time to assess prediction robustness.
A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual & Group Unfairness via Inequality Indices
Further, our work reveals overlooked tradeoffs between different fairness notions: using our proposed measures, the overall individual-level unfairness of an algorithm can be decomposed into a between-group and a within-group component.
A Generalized Language Model as the Combination of Skipped n-grams and Modified Kneser-Ney Smoothing
In an extensive empirical experiment over English text corpora we demonstrate that our generalized language models lead to a substantial reduction of perplexity between 3. 1% and 12. 7% in comparison to traditional language models using modified Kneser-Ney smoothing.
