Publications | Natural Language Processing

Preprints

• Are self-explanations from Large Language Models faithful?
  Andreas Madsen, Sarath Chandar, and Siva Reddy
  In ArXiv, 2024.
  #NLP
  [arXiv], [code]

• Faithfulness Measurable Masked Language Models
  Andreas Madsen, Siva Reddy, and Sarath Chandar
  In ArXiv, 2023.
  #NLP
  [arXiv], [code], [YouTube]

• Should We Attend More or Less? Modulating Attention for Fairness
  Abdelrahman Zayed, Gonçalo Mordido, Samira Shabanian, and Sarath Chandar
  In ArXiv, 2023.
  #NLP
  [arXiv]

Conference and Journal Papers

2024

15. Fairness-Aware Structured Pruning in Transformers
    Abdelrahman Zayed, Gonçalo Mordido, Samira Shabanian, Ioana Baldini, and Sarath Chandar
    AAAI Conference on Artificial Intelligence (AAAI), 2024.
    #NLP
    [arXiv]

2023

14. Self-Influence Guided Data Reweighting for Language Model Pre-training
    Megh Thakkar, Tolga Bolukbasi, Sriram Ganapathy, Shikhar Vashishth, Sarath Chandar, and Partha Talukdar
    Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023.
    #NLP
    [arXiv]

15. EpiK-Eval: Evaluation for Language Models as Epistemic Models
    Gabriele Prato, Jerry Huang, Prasanna Parthasarathi, Shagun Sodhani, and Sarath Chandar
    Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023.
    #NLP
    [arXiv], [code]

16. Measuring the Knowledge Acquisition-Utilization Gap in Pretrained Language Models
    Amirhossein Kazemnejad, Mehdi Rezagholizadeh, Prasanna Parthasarathi, and Sarath Chandar
    Findings of Empirical Methods in Natural Language Processing (EMNLP), 2023.
    #NLP
    [arXiv]

17. Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairness
    Abdelrahman Zayed, Prasanna Parthasarathi, Gonçalo Mordido, Hamid Palangi, Samira Shabanian, and Sarath Chandar
    AAAI Conference on Artificial Intelligence (AAAI), 2023.
    #NLP
    [arXiv]

2022

10. Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining
    Andreas Madsen, Nicholas Meade, Vaibhav Adlakha, and Siva Reddy
    Findings of Empirical Methods in Natural Language Processing (EMNLP), 2022.
    [BlackboxNLP Workshop, 2022]
    #NLP
    [arXiv], [code]

11. Detecting Languages Unintelligible to Multilingual Models through Local Structure Probes
    Louis Clouâtre, Prasanna Parthasarathi, Amal Zouaq, and Sarath Chandar
    Findings of Empirical Methods in Natural Language Processing (EMNLP), 2022.
    #NLP
    

12. Local Structure Matters Most in Most Languages
    Louis Clouâtre, Prasanna Parthasarathi, Amal Zouaq, and Sarath Chandar
    Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing (AACL-IJCNLP), 2022.
    #NLP
    

13. Post-hoc Interpretability for Neural NLP: A Survey
    Andreas Madsen, Siva Reddy, and Sarath Chandar
    ACM Computing Surveys, 2022.
    #NLP
    [arXiv]

14. Local Structure Matters Most: Perturbation Study in NLU
    Louis Clouâtre, Prasanna Parthasarathi, Amal Zouaq, and Sarath Chandar
    Findings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2022.
    #NLP
    [arXiv]

2021

5. MLMLM: Link Prediction with Mean Likelihood Masked Language Model
   Louis Clouâtre, Philippe Trempe, Amal Zouaq, and Sarath Chandar
   Findings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2021.
   #NLP
   [arXiv]

6. Benchmarking Bias Mitigation Algorithms in Representation Learning through Fairness Metrics
   Charan Reddy, Deepak Sharma, Soroush Mehri, Adriana Romero, Samira Shabanian, and Sina Honari
   Proceedings of the Neural Information Processing Systems (NeurIPS) Track on Datasets and Benchmarks, 2021.
   #NLP
   [openreview], [code]

7. A Brief Study on the Effects of Training Generative Dialogue Models with a Semantic loss
   Prasanna Parthasarathi, Mohamed Abdelsalam, Joelle Pineau, and Sarath Chandar
   Proceedings of the 22nd Annual SIGdial Meeting on Discourse and Dialogue, 2021.
   #NLP
   

8. Do Encoder Representations of Generative Dialogue Models Encode Sufficient Information about the Task ?
   Prasanna Parthasarathi, Sarath Chandar, and Joelle Pineau
   Proceedings of the 22nd Annual SIGdial Meeting on Discourse and Dialogue, 2021.
   #NLP
   

9. A Survey of Data Augmentation Approaches for NLP
   Steven Y. Feng, Varun Gangal, Jason Wei, Sarath Chandar, Soroush Vosoughi, Teruko Mitamura, and Eduard Hovy
   Findings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2021.
   #NLP
   [arXiv]