pith. sign in

arxiv: 2102.01818 · v1 · pith:72DQD437new · submitted 2021-02-03 · 💻 cs.CL · cs.LG

Memorization vs. Generalization: Quantifying Data Leakage in NLP Performance Evaluation

classification 💻 cs.CL cs.LG
keywords dataabilitydatasetsleakageevaluategeneralizememorizemethods
0
0 comments X
read the original abstract

Public datasets are often used to evaluate the efficacy and generalizability of state-of-the-art methods for many tasks in natural language processing (NLP). However, the presence of overlap between the train and test datasets can lead to inflated results, inadvertently evaluating the model's ability to memorize and interpreting it as the ability to generalize. In addition, such data sets may not provide an effective indicator of the performance of these methods in real world scenarios. We identify leakage of training data into test data on several publicly available datasets used to evaluate NLP tasks, including named entity recognition and relation extraction, and study them to assess the impact of that leakage on the model's ability to memorize versus generalize.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Fin-Bias: Comprehensive Evaluation for LLM Decision-Making under human bias in Finance Domain

    cs.CL 2026-05 unverdicted novelty 7.0

    LLMs copy biased analyst ratings in investment decisions but a new detection method encourages independent reasoning and can improve stock return predictions beyond human levels.