added new papers

_data/bibs/2023.bib

@@ -1,3 +1,22 @@
+@article{gupta2023whispers,
+ title={Whispers of Doubt Amidst Echoes of Triumph in NLP Robustness}, 
+ author={Ashim Gupta and Rishanth Rajendhran and Nathan Stringham and Vivek Srikumar and Ana Marasović},
+ year={2023},
+ eprint={2311.09694},
+ archivePrefix={arXiv},
+ primaryClass={cs.CL},
+ paper = {https://arxiv.org/abs/2311.09694}
+}
+
+@inproceedings{
+chaleshtori2023on,
+title={On Evaluating Explanation Utility for Human-{AI} Decision-Making in {NLP}},
+author={Fateme Hashemi Chaleshtori and Atreya Ghosal and Ana Marasovic},
+booktitle={XAI in Action: Past, Present, and Future Applications},
+year={2023},
+url={https://openreview.net/forum?id=8BR8EaWNTZ}
+}
+
 @article{singhal2023intendd,
  title={IntenDD: A Unified Contrastive Learning Approach for Intent Detection and Discovery}, 
  author={Bhavuk Singhal and Ashim Gupta and Shivasankaran V P and Amrith Krishna},
@@ -18,14 +37,24 @@ @article{li2023learning
  paper = {https://arxiv.org/abs/2305.14600}
 }
 
-@article{johnson2023consistency,
- title={How Much Consistency Is Your Accuracy Worth?},
- author={Jacob K. Johnson and Ana Marasović},
- year={2023},
- eprint={2310.13781},
- archivePrefix={arXiv},
- primaryClass={cs.CL},
- paper = {https://arxiv.org/abs/2310.13781}
+@inproceedings{johnson-marasovic-2023-much,
+ title = "How Much Consistency Is Your Accuracy Worth?",
+ author = "Johnson, Jacob K. and
+ Marasovi{\'c}, Ana",
+ editor = "Belinkov, Yonatan and
+ Hao, Sophie and
+ Jumelet, Jaap and
+ Kim, Najoung and
+ McCarthy, Arya and
+ Mohebbi, Hosein",
+ booktitle = "Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP",
+ month = dec,
+ year = "2023",
+ address = "Singapore",
+ publisher = "Association for Computational Linguistics",
+ url = "https://aclanthology.org/2023.blackboxnlp-1.19",
+ pages = "250--260",
+ abstract = "Contrast set consistency is a robustness measurement that evaluates the rate at which a model correctly responds to all instances in a bundle of minimally different examples relying on the same knowledge. To draw additional insights, we propose to complement consistency with relative consistency{---}the probability that an equally accurate model would surpass the consistency of the proposed model, given a distribution over possible consistencies. Models with 100{\%} relative consistency have reached a consistency peak for their accuracy. We reflect on prior work that reports consistency in contrast sets and observe that relative consistency can alter the assessment of a model{'}s consistency compared to another. We anticipate that our proposed measurement and insights will influence future studies aiming to promote consistent behavior in models.",
 }
 
 @article{broadbent2023machine,