TopEx: Topic-based Explanations for Model Comparison

Shreya Havaldar, Adam Stein, Eric Wong, Lyle Ungar
6/1/2023
cs.CL

No confident code implementation found for this paper.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Explainability for Large Language Models: A Survey

86% match2023

Exploring Iterative Enhancement for Improving Learnersourced Multiple-Choice Question Explanations with Large Language Models

85% match1 repo22023

Comparative Analysis of CHATGPT and the evolution of language models

85% match2023

Sequential Integrated Gradients: a simple but effective method for explaining language models

85% match1 repo722023

Open, Closed, or Small Language Models for Text Classification?

85% match2023

Using Captum to Explain Generative Language Models

85% match2023

Cite this paper

@article{havaldar2023topex,
  title  = {TopEx: Topic-based Explanations for Model Comparison},
  author = {Shreya Havaldar and Adam Stein and Eric Wong and Lyle Ungar},
  year   = {2023},
  eprint = {2306.00976},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2306.00976v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2306.00976.svg)](https://codeofpaper.com/paper/2306.00976)

Discussion