TopEx: Topic-based Explanations for Model Comparison

2023-06-01 · Shreya Havaldar, Adam Stein, Eric Wong, Lyle Ungar

Meaningfully comparing language models is challenging with current explanation methods. Current explanations are overwhelming for humans due to large vocabularies or incomparable across models. We present TopEx, an explanation method that enables a level playing field for comparing language models via model-agnostic topics. We demonstrate how TopEx can identify similarities and differences between DistilRoBERTa and GPT-2 on a variety of NLP tasks.

📄 PDF Abstract BibTeX arXiv:2306.00976

Code (0)

등록된 구현이 없습니다.

Tasks

model

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…

TopExNet: Entity-Centric Network Topic Exploration in News Streams

2019-05-29 · Andreas Spitz, Satya Almasian, Michael Gertz

The recent introduction of entity-centric implicit network representations of unstructured text offers novel ways for exploring entity relations in document collections and streams efficiently and interactively. Here, we…

Articles

Learning Topology-Specific Experts for Molecular Property Prediction

2023-02-27 · Su Kim, Dongha Lee, SeongKu Kang, Seonghyeon Lee 외

Recently, graph neural networks (GNNs) have been successfully applied to predicting molecular properties, which is one of the most classical cheminformatics tasks with various applications. Despite their effectiveness, w…

Molecular Property Prediction Prediction Property Prediction

ALMANACS: A Simulatability Benchmark for Language Model Explainability

2023-12-20 · Edmund Mills, Shiye Su, Stuart Russell, Scott Emmons

How do we measure the efficacy of language model explainability methods? While many explainability methods have been developed, they are typically evaluated on bespoke tasks, preventing an apples-to-apples comparison. To…

counterfactual Language Modeling Language Modelling model

Topic-Centric Explanations for News Recommendation

2023-06-13 · Dairui Liu, Derek Greene, Irene Li, Xuefei Jiang 외

News recommender systems (NRS) have been widely applied for online news websites to help users find relevant articles based on their interests. Recent methods have demonstrated considerable success in terms of recommenda…

Articles Explainable Recommendation News Recommendation Recommendation Systems

What You Like: Generating Explainable Topical Recommendations for Twitter Using Social Annotations

2022-12-23 · Parantapa Bhattacharya, Saptarshi Ghosh, Muhammad Bilal Zafar, Soumya K. Ghosh 외

With over 500 million tweets posted per day, in Twitter, it is difficult for Twitter users to discover interesting content from the deluge of uninteresting posts. In this work, we present a novel, explainable, topical re…

Collaborative Filtering Recommendation Systems