Journal article · 2026

Understanding and Optimizing Counterfactual Generation in LLMs via Contribution Attribution and Target Intervention

Hangzhang Kou, Chenyu Yao, Ye Song, Deshen Li, Tingqian Shi, Zihan Wang, Chunhua Yang, Weihua Gui

IEEE Transactions on Neural Networks and Learning Systems, PP, 1–12 · Published 5 October 2026 · DOI 10.1109/tnnls.2026.3733646

View at the publisherCite this paper

In brief

“Understanding and Optimizing Counterfactual Generation in LLMs via Contribution Attribution and Target Intervention” is a 2026 journal article by Hangzhang Kou and 7 co-authors, published in IEEE Transactions on Neural Networks and Learning Systems. OpenAlex counts 0 citations as of 17 November 2026. The publisher's version is not open access, and OpenAlex records no free legal copy.

Citations
0
Authors
8

Abstract

Counterfactual generation in large language models (LLMs), designed to enhance the comprehensiveness of semantic information in datasets, is an important technique for data augmentation. While existing research has evaluated counterfactual generation across various scenarios, there is a lack of further exploration into the underlying mechanisms, leading to an inability to effectively control the quality of… Read the full abstract at the publisher.

Excerpt. This paper is not open access.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Kou, H., Yao, C., Song, Y., Li, D., Shi, T., Wang, Z., Yang, C., & Gui, W. (2026). Understanding and Optimizing Counterfactual Generation in LLMs via Contribution Attribution and Target Intervention. IEEE Transactions on Neural Networks and Learning Systems, PP, 1–12. https://doi.org/10.1109/tnnls.2026.3733646

MLA 9

Kou, Hangzhang, et al. “Understanding and Optimizing Counterfactual Generation in LLMs via Contribution Attribution and Target Intervention.” IEEE Transactions on Neural Networks and Learning Systems, vol. PP, 2026, pp. 1–12. https://doi.org/10.1109/tnnls.2026.3733646.

Chicago

Kou, Hangzhang, Chenyu Yao, Ye Song, Deshen Li, Tingqian Shi, Zihan Wang, Chunhua Yang, and Weihua Gui. 2026. “Understanding and Optimizing Counterfactual Generation in LLMs via Contribution Attribution and Target Intervention.” IEEE Transactions on Neural Networks and Learning Systems PP: 1–12. https://doi.org/10.1109/tnnls.2026.3733646.

Harvard

Kou, H. et al. (2026) ‘Understanding and Optimizing Counterfactual Generation in LLMs via Contribution Attribution and Target Intervention’, IEEE Transactions on Neural Networks and Learning Systems, PP, pp. 1–12. doi:10.1109/tnnls.2026.3733646.

IEEE

H. Kou et al., “Understanding and Optimizing Counterfactual Generation in LLMs via Contribution Attribution and Target Intervention,” IEEE Transactions on Neural Networks and Learning Systems, vol. PP, pp. 1–12, 2026, doi: 10.1109/tnnls.2026.3733646.

BibTeX

@article{kou2026understanding,
  title     = {{Understanding and Optimizing Counterfactual Generation in LLMs via Contribution Attribution and Target Intervention}},
  author    = {Kou, Hangzhang and Yao, Chenyu and Song, Ye and Li, Deshen and Shi, Tingqian and Wang, Zihan and Yang, Chunhua and Gui, Weihua},
  journal   = {IEEE Transactions on Neural Networks and Learning Systems},
  year      = {2026},
  volume    = {PP},
  pages     = {1--12},
  doi       = {10.1109/tnnls.2026.3733646},
  url       = {https://doi.org/10.1109/tnnls.2026.3733646}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)

  • counterfactual generation
  • large language models
  • mechanistic interpretability
  • sentiment analysis
  • multi-head attention
  • attention heads
  • data augmentation
  • Llama 2

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Kou, H., Yao, C., Song, Y., Li, D., Shi, T., Wang, Z., Yang, C., & Gui, W. (2026). Understanding and Optimizing Counterfactual Generation in LLMs via Contribution Attribution and Target Intervention. IEEE Transactions on Neural Networks and Learning Systems, PP, 1–12. https://doi.org/10.1109/tnnls.2026.3733646

How many times has this paper been cited?

0 times, according to OpenAlex on 17 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

OpenAlex records no free legal copy. Check your library's access, the authors' pages or a repository, or ask the corresponding author for a copy.

Who wrote this paper?

Hangzhang Kou, Chenyu Yao, Ye Song, Deshen Li, Tingqian Shi, Zihan Wang, Chunhua Yang, Weihua Gui.

What is the DOI of this paper?

10.1109/tnnls.2026.3733646, permanently at https://doi.org/10.1109/tnnls.2026.3733646. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 17 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.