Are Bert Family Good Instruction Followers? A Study on Their Potential And Limitations

Yisheng Xiao, Juntao Li, Zechen Sun, Zechang Li, Qingrong Xia +3 more
2/12/2026

No official code found. Best implementation: LitterBrother-Xiao/Instruct_XMLR (5 stars, Apache-2.0, last commit 2024-03-01).

Semantic Scholar

Code Implementations(1)

LitterBrother-Xiao/Instruct_XMLRCommunity56%
Apache-2.0

[ICLR 2024] Are Bert Family Good Instruction Followers? A Study on Their Potential And Limitations

50Shell, PythonMar 1, 20242 years agoApache-2.0

Similar Papers

Why Do You Grok? A Theoretical Analysis on Grokking Modular Addition

100% match2026

AdversariaLeak: External Information Leakage Attack Using Adversarial Samples on Face Recognition Systems

96% match2026

Learned Lossless Image Compression Based on Bit Plane Slicing

96% match2026

Durable Quantization Conditioned Misalignment Attack on Large Language Models

96% match2026

Accelerated Speculative Sampling Based on Tree Monte Carlo

96% match2026

Cocktail Universal Adversarial Attack on Deep Neural Networks

96% match2026

Cite this paper

@article{xiao2026bert,
  title  = {Are Bert Family Good Instruction Followers? A Study on Their Potential And Limitations},
  author = {Yisheng Xiao and Juntao Li and Zechen Sun and Zechang Li and Qingrong Xia and Xinyu Duan and Zhefeng Wang and Min Zhang},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:4b59d32d46cdc8719e124f3de4707939e96b0f7b},
  journal = {ICLR 2024 2024}
}

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/4b59d32d46cdc8719e124f3de4707939e96b0f7b.svg)](https://codeofpaper.com/paper/4b59d32d46cdc8719e124f3de4707939e96b0f7b)

Discussion