nb_scholar.bib

@inproceedings{louvan2016cross,
  title={Cross-Sentence Inference for Process Knowledge},
  author={Louvan, Samuel and Naik, Chetan and Kumaravel, Sadhana and Kwon, Heeyoung and Balasubramanian, Niranjan and Clark, Peter},
  booktitle={Conference on Empirical Methods in Natural Language Processing},
  year={2016}
}

@inproceedings{jansen2016s,
  title={What’s in an explanation? characterizing knowledge and inference requirements for elementary science exams},
  author={Jansen, Peter and Balasubramanian, Niranjan and Surdeanu, Mihai and Clark, Peter},
  booktitle={Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers},
  pages={2956--2965},
  year={2016}
}

@inproceedings{jain2017pria,
  title={PrIA: A private intelligent assistant},
  author={Jain, Shashank and Tiwari, Vivek and Balasubramanian, Aruna and Balasubramanian, Niranjan and Chakraborty, Supriyo},
  booktitle={Proceedings of the 18th International Workshop on Mobile Computing Systems and Applications},
  pages={91--96},
  year={2017}
}

@inproceedings{lynn2016poe,
  title={POE: A Pathology Extraction Tool for Finding Attribute-Value Pairs in Glioma Pathology Reports.},
  author={Lynn, Veronica E and Balasubramanian, Niranjan and Kur{\c{c}}, Tahsin M and Saltz, Joel H and Jacobson, Rebecca},
  booktitle={AMIA},
  year={2016}
}

@inproceedings{cao2017mobirnn,
  title={MobiRNN: Efficient recurrent neural network execution on mobile GPU},
  author={Cao, Qingqing and Balasubramanian, Niranjan and Balasubramanian, Aruna},
  booktitle={Proceedings of the 1st International Workshop on Deep Learning for Mobile Systems and Applications},
  pages={1--6},
  year={2017}
}

@inproceedings{lynn2017human,
  title={Human centered NLP with user-factor adaptation},
  author={Lynn, Veronica and Son, Youngseo and Kulkarni, Vivek and Balasubramanian, Niranjan and Schwartz, H Andrew},
  booktitle={Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
  pages={1146--1155},
  year={2017}
}

@inproceedings{weber2018event,
  title={Event Representations with Tensor-based Compositions},
  author={Weber, Noah and Balasubramanian, Niranjan and Chambers, Nathaniel},
  booktitle={AAAI Conference on Artificial Intelligence},
  year={2018}
}

@inproceedings{kwon2018controlling,
  title={Controlling Information Aggregation for Complex Question Answering},
  author={Kwon, Heeyoung and Trivedi, Harsh, Balasubramanian, Niranjan and Jansen, Peter and Surdeanu, Mihai},
  booktitle={European Conference on Information Retrieval},
  year={2018}
}

@article{weber2018controlling,
  title={Controlling decoding for more abstractive summaries with copy-based networks},
  author={Weber, Noah and Shekhar, Leena and Balasubramanian, Niranjan and Cho, Kyunghyun},
  journal={arXiv preprint arXiv:1803.07038},
  year={2018}
}

@article{ranjan2018fake,
  title={Fake sentence detection as a training task for sentence encoding},
  author={Ranjan, Viresh and Kwon, Heeyoung and Balasubramanian, Niranjan and Hoai, Minh},
  journal={arXiv preprint arXiv:1808.03840},
  year={2018}
}

@inproceedings{mohammadzaman2018residualized,
  title={Residualized Factor Adaptation for Community Social Media Prediction Tasks},
  author={Mohammadzaman, Zamani and Schwartz, H. Andrew and Lynn, Veronica E. and Giorgi, Salvatore and Balasubramanian, Niranjan},
  booktitle={Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing},
  pages={3560--3569},
  year={2018}
}

@inproceedings{weber2018hierarchical,
  title={Hierarchical Quantized Representations for Script Generation},
  author={Weber, Noah and Shekhar, Leena and Balasubramanian, Niranjan and Chambers, Nate},
  booktitle={Conference on Empirical Methods in Natural Language Processing},
  pages={3783--3792},
  year={2018}
}

@article{kang2019pomo,
  title={PoMo: Generating entity-specific post-modifiers in context},
  author={Kang, Jun Seok and Logan IV, Robert L and Chu, Zewei and Chen, Yang and Dua, Dheeru and Gimpel, Kevin and Singh, Sameer and Balasubramanian, Niranjan},
  journal={arXiv preprint arXiv:1904.03111},
  year={2019}
}

@inproceedings{weber2018fine,
  title={The Fine Line between Linguistic Generalization and Failure in Seq2Seq-Attention Models},
  author={Weber, Noah and Shekhar, Leena and Balasubramanian, Niranjan},
  booktitle={Workshop on Generalization in the Age of Deep Learning in NAACL},
  pages={24--27},
  year={2018}
}

@inproceedings{lynn2019tweet,
  title={Tweet classification without the tweet: An empirical examination of user versus document attributes},
  author={Lynn, Veronica and Giorgi, Salvatore and Balasubramanian, Niranjan and Schwartz, H Andrew},
  booktitle={Proceedings of the third workshop on natural language processing and computational social science},
  pages={18--28},
  year={2019}
}

@inproceedings{cao2019deqa,
  title={Deqa: On-device question answering},
  author={Cao, Qingqing and Weber, Noah and Balasubramanian, Niranjan and Balasubramanian, Aruna},
  booktitle={Proceedings of the 17th Annual International Conference on Mobile Systems, Applications, and Services},
  pages={27--40},
  year={2019}
}

@inproceedings{trivedi2019repurposing,
  title={Repurposing Entailment for Multi-Hop Question Answering Tasks},
  author={Trivedi, Harsh and Kwon, Heeyoung and Khot, Tushar and Sabharwal, Ashish and Balasubramanian, Niranjan},
  booktitle={North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  pages={2948--2958},
  year={2019}
}

@inproceedings{liu2020adaptive,
  title={Adaptive activation network and functional regularization for efficient and flexible deep multi-task learning},
  author={Liu, Yingru and Yang, Xuewen and Xie, Dongliang and Wang, Xin and Shen, Li and Huang, Haozhi and Balasubramanian, Niranjan},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={34},
  number={04},
  pages={4924--4931},
  year={2020}
}

@article{weber2020generating,
  title={Generating narrative text in a switching dynamical system},
  author={Weber, Noah and Shekhar, Leena and Kwon, Heeyoung and Balasubramanian, Niranjan and Chambers, Nathanael},
  journal={arXiv preprint arXiv:2004.03762},
  year={2020}
}

@inproceedings{wei2020learning,
  title={Learning visual emotion representations from web data},
  author={Wei, Zijun and Zhang, Jianming and Lin, Zhe and Lee, Joon-Young and Balasubramanian, Niranjan and Hoai, Minh and Samaras, Dimitris},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={13106--13115},
  year={2020}
}

@article{trivedi2020measuring,
  title={Measuring and reducing non-multifact reasoning in multi-hop question answering},
  author={Trivedi, Harsh and Balasubramanian, Niranjan and Khot, Tushar and Sabharwal, Ashish},
  journal={arXiv preprint arXiv:2005.00789},
  year={2020}
}

@mastersthesis{gaonkar2019modeling,
  title={Modeling label semantics for predicting emotional reactions},
  author={Gaonkar, Radhika Shamsunder},
  year={2019},
  school={State University of New York at Stony Brook}
}

@article{cao2020faster,
  title={Faster and just as accurate: A simple decomposition for transformer models},
  author={Cao, Qingqing and Trivedi, Harsh and Balasubramanian, Aruna and Balasubramanian, Niranjan},
  year={2020}
}

@inproceedings{lynn2020hierarchical,
  title={Hierarchical modeling for user personality prediction: The role of message-level attention},
  author={Lynn, Veronica and Balasubramanian, Niranjan and Schwartz, H Andrew},
  booktitle={Proceedings of the 58th annual meeting of the association for computational linguistics},
  pages={5306--5316},
  year={2020}
}

@inproceedings{yang2019latent,
  title={Latent Part-of-Speech Sequences for Neural Machine Translation},
  author={Yang, Xuewen and Liu, Yingru and Xie, Dongliang and Wang, Xin and Balasubramanian, Niranjan},
  booktitle={Conference on Empirical Methods in Natural Language Processing},
  pages={780--790},
  year={2019}
}

@article{kwon2020modeling,
  title={Modeling preconditions in text with a crowd-sourced dataset},
  author={Kwon, Heeyoung and Koupaee, Mahnaz and Singh, Pratyush and Sawhney, Gargi and Shukla, Anmol and Kallur, Keerthi Kumar and Chambers, Nathanael and Balasubramanian, Niranjan},
  journal={arXiv preprint arXiv:2010.02429},
  year={2020}
}

@article{cao2020towards,
  title={Towards accurate and reliable energy measurement of NLP models},
  author={Cao, Qingqing and Balasubramanian, Aruna and Balasubramanian, Niranjan},
  journal={arXiv preprint arXiv:2010.05248},
  year={2020}
}

@article{trivedi2020multihop,
  title={Is multihop QA in DiRe condition? Measuring and reducing disconnected reasoning},
  author={Trivedi, Harsh and Balasubramanian, Niranjan and Khot, Tushar and Sabharwal, Ashish},
  journal={arXiv preprint arXiv:2005.00789},
  year={2020}
}

@article{bastan2020author,
  title={Author's sentiment prediction},
  author={Bastan, Mohaddeseh and Koupaee, Mahnaz and Son, Youngseo and Sicoli, Richard and Balasubramanian, Niranjan},
  journal={arXiv preprint arXiv:2011.06128},
  year={2020}
}

@article{singh2020open4business,
  title={Open4Business (O4B): An Open Access Dataset for Summarizing Business Documents},
  author={Singh, Amanpreet and Balasubramanian, Niranjan},
  journal={arXiv preprint arXiv:2011.07636},
  year={2020}
}

@article{cao2020bew,
  title={Bew: Towards Answering Business-Entity-Related Web Questions},
  author={Cao, Qingqing and Riva, Oriana and Balasubramanian, Aruna and Balasubramanian, Niranjan},
  journal={arXiv preprint arXiv:2012.05818},
  year={2020}
}

@inproceedings{cao2020deformer,
  title={DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering},
  author={Cao, Qingqing and Trivedi, Harsh and Balasubramanian, Aruna and Balasubramanian, Niranjan},
  booktitle={Annual Meeting of the Association for Computational Linguistics},
  pages={4487--4497},
  year={2020}
}

@article{ji2021distribution,
  title={On the distribution, sparsity, and inference-time quantization of attention values in transformers},
  author={Ji, Tianchu and Jain, Shraddhan and Ferdman, Michael and Milder, Peter and Schwartz, H Andrew and Balasubramanian, Niranjan},
  journal={arXiv preprint arXiv:2106.01335},
  year={2021}
}

@article{lal2021tellmewhy,
  title={TellMeWhy: A dataset for answering why-questions in narratives},
  author={Lal, Yash Kumar and Chambers, Nathanael and Mooney, Raymond and Balasubramanian, Niranjan},
  journal={arXiv preprint arXiv:2106.06132},
  year={2021}
}

@article{kwon2021toward,
  title={Toward diverse precondition generation},
  author={Kwon, Heeyoung and Chambers, Nathanael and Balasubramanian, Niranjan},
  journal={arXiv preprint arXiv:2106.07117},
  year={2021}
}

@inproceedings{koupaee2021don,
  title={Don’t let discourse confine your model: Sequence perturbations for improved event language models},
  author={Koupaee, Mahnaz and Durrett, Greg and Chambers, Nathanael and Balasubramanian, Niranjan},
  booktitle={Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)},
  pages={599--604},
  year={2021}
}

@inproceedings{tran2021progressive,
  title={Progressive knowledge distillation for early action recognition},
  author={Tran, Vinh and Balasubramanian, Niranjan and Hoai, Minh},
  booktitle={2021 IEEE International Conference on Image Processing (ICIP)},
  pages={2583--2587},
  year={2021},
  organization={IEEE}
}

@article{inoue2021summarize,
  title={Summarize-then-answer: Generating concise explanations for multi-hop reading comprehension},
  author={Inoue, Naoya and Trivedi, Harsh and Sinha, Steven and Balasubramanian, Niranjan and Inui, Kentaro},
  journal={arXiv preprint arXiv:2109.06853},
  year={2021}
}

@inproceedings{lal2021irene,
  title={IrEne-viz: Visualizing Energy Consumption of Transformer Models},
  author={Lal, Yash Kumar and Singh, Reetu and Trivedi, Harsh and Cao, Qingqing and Balasubramanian, Aruna and Balasubramanian, Niranjan},
  booktitle={Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations},
  pages={251--258},
  year={2021}
}

@article{matero2021melt,
  title={MeLT: Message-level transformer with masked document representations as pre-training for stance detection},
  author={Matero, Matthew and Soni, Nikita and Balasubramanian, Niranjan and Schwartz, H Andrew},
  journal={arXiv preprint arXiv:2109.08113},
  year={2021}
}

@inproceedings{lal2022analyzing,
  title={Analyzing the contribution of commonsense knowledge sources for why-question answering},
  author={Lal, Yash Kumar and Liu, Horace and Tandon, Niket and Chambers, Nathanael and Mooney, Ray and Balasubramanian, Niranjan},
  booktitle={ACL 2022 Workshop on Commonsense Representation and Reasoning},
  year={2022}
}

@inproceedings{vu2022modeling,
  title={Modeling latent dimensions of human beliefs},
  author={Vu, Huy and Giorgi, Salvatore and Clifton, Jeremy DW and Balasubramanian, Niranjan and Schwartz, H Andrew},
  booktitle={Proceedings of the International AAAI Conference on Web and Social Media},
  volume={16},
  pages={1064--1074},
  year={2022}
}

@article{trivedi2022musique,
  title={♫ MuSiQue: Multihop Questions via Single-hop Question Composition},
  author={Trivedi, Harsh and Balasubramanian, Niranjan and Khot, Tushar and Sabharwal, Ashish},
  journal={Transactions of the Association for Computational Linguistics},
  volume={10},
  pages={539--554},
  year={2022},
  publisher={MIT Press}
}

@inproceedings{soni2022human,
  title={Human Language Modeling},
  author={Soni, Nikita and Matero, Matthew and Balasubramanian, Niranjan and Schwartz, H Andrew},
  booktitle={Findings of the Association for Computational Linguistics},
  year={2022}
}

@article{bai2022learning,
  title={Learning for Expressive Task-Related Sentence Representations},
  author={Bai, Xueying and Shang, Jinghuan and Sun, Yifan and Balasubramanian, Niranjan},
  journal={arXiv},
  year={2022}
}

@article{ghosh2023pasta,
  title={PASTA: A Dataset for Modeling PArticipant STAtes in Narratives},
  author={Ghosh, Sayontan and Koupaee, Mahnaz and Chen, Isabella and Ferraro, Francis and Chambers, Nathanael and Balasubramanian, Niranjan},
  journal={Transactions of the Association for Computational Linguistics},
  volume={11},
  pages={1283--1300},
  year={2023},
  publisher={MIT Press One Broadway, 12th Floor, Cambridge, Massachusetts 02142, USA~…}
}

@article{cao2021irene,
  title={IrEne: Interpretable energy prediction for transformers},
  author={Cao, Qingqing and Lal, Yash Kumar and Trivedi, Harsh and Balasubramanian, Aruna and Balasubramanian, Niranjan},
  journal={arXiv preprint arXiv:2106.01199},
  year={2021}
}

@article{treviso2023efficient,
  title={Efficient methods for natural language processing: A survey},
  author={Treviso, Marcos and Lee, Ji-Ung and Ji, Tianchu and Aken, Betty van and Cao, Qingqing and Ciosici, Manuel R and Hassid, Michael and Heafield, Kenneth and Hooker, Sara and Raffel, Colin and others},
  journal={Transactions of the Association for Computational Linguistics},
  volume={11},
  pages={826--860},
  year={2023},
  publisher={MIT Press One Broadway, 12th Floor, Cambridge, Massachusetts 02142, USA~…}
}

@article{tran4219649progressive,
  title={Progressive Knowledge Distillation for Early Recognition of Human Actions in Video},
  author={Tran, Vinh Quang and Balasubramanian, Niranjan and Nguyen, Minh Hoai},
  journal={Available at SSRN 4219649}
}

@inproceedings{ghosh2022specnfs,
  title={SpecNFS: a challenge dataset towards extracting formal models from natural language specifications},
  author={Ghosh, Sayontan and Singh, Amanpreet and Merenstein, Alex and Su, Wei and Smolka, Scott A and Zadok, Erez and Balasubramanian, Niranjan},
  booktitle={Proceedings of the Thirteenth Language Resources and Evaluation Conference},
  pages={2166--2176},
  year={2022}
}

@article{ghosh2022distilling,
  title={Distilling knowledge from language models for video-based action anticipation},
  author={Ghosh, Sayontan and Aggarwal, Tanvi and Hoai, Minh and Balasubramanian, Niranjan},
  journal={arXiv preprint arXiv},
  volume={2210},
  pages={57},
  year={2022}
}

@article{bastan2022bionli,
  title={Bionli: Generating a biomedical nli dataset using lexico-semantic constraints for adversarial examples},
  author={Bastan, Mohaddeseh and Surdeanu, Mihai and Balasubramanian, Niranjan},
  journal={arXiv preprint arXiv:2210.14814},
  year={2022}
}

@article{trivedi2022teaching,
  title={Teaching broad reasoning skills for multi-step QA by generating hard contexts},
  author={Trivedi, Harsh and Balasubramanian, Niranjan and Khot, Tushar and Sabharwal, Ashish},
  journal={arXiv preprint arXiv:2205.12496},
  year={2022}
}

@inproceedings{tran2022within,
  title={From within to between: Knowledge distillation for cross modality retrieval},
  author={Tran, Vinh and Balasubramanian, Niranjan and Hoai, Minh},
  booktitle={Proceedings of the Asian Conference on Computer Vision},
  pages={3223--3240},
  year={2022}
}

@inproceedings{lal2022using,
  title={Using commonsense knowledge to answer why-questions},
  author={Lal, Yash Kumar and Tandon, Niket and Aggarwal, Tanvi and Liu, Horace and Chambers, Nathanael and Mooney, Raymond and Balasubramanian, Niranjan},
  booktitle={Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing},
  pages={1204--1219},
  year={2022}
}

@article{vallurupalli2022poque,
  title={POQue: Asking participant-specific outcome questions for a deeper understanding of complex events},
  author={Vallurupalli, Sai and Ghosh, Sayontan and Erk, Katrin and Balasubramanian, Niranjan and Ferraro, Francis},
  journal={arXiv preprint arXiv:2212.02629},
  year={2022}
}

@article{trivedi2022interleaving,
  title={Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions},
  author={Trivedi, Harsh and Balasubramanian, Niranjan and Khot, Tushar and Sabharwal, Ashish},
  journal={arXiv preprint arXiv:2212.10509},
  year={2022}
}

@article{gaonkar2020modeling,
  title={Modeling label semantics for predicting emotional reactions},
  author={Gaonkar, Radhika and Kwon, Heeyoung and Bastan, Mohaddeseh and Balasubramanian, Niranjan and Chambers, Nathanael},
  journal={arXiv preprint arXiv:2006.05489},
  year={2020}
}

@article{koupaee2023modeling,
  title={Modeling complex event scenarios via simple entity-focused questions},
  author={Koupaee, Mahnaz and Durrett, Greg and Chambers, Nathanael and Balasubramanian, Niranjan},
  journal={arXiv preprint arXiv:2302.07139},
  year={2023}
}

@article{ghosh2022text,
  title={Text-derived knowledge helps vision: A simple cross-modal distillation for video-based action anticipation},
  author={Ghosh, Sayontan and Aggarwal, Tanvi and Hoai, Minh and Balasubramanian, Niranjan},
  journal={arXiv preprint arXiv:2210.05991},
  year={2022}
}

@inproceedings{bastan2023neurostructural,
  title={Neurostructural decoding: Neural text generation with structural constraints},
  author={Bastan, Mohaddeseh and Surdeanu, Mihai and Balasubramanian, Niranjan},
  booktitle={Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  pages={9496--9510},
  year={2023}
}

@article{bastan2022sume,
  title={Sume: A dataset towards summarizing biomedical mechanisms},
  author={Bastan, Mohaddeseh and Shankar, Nishant and Surdeanu, Mihai and Balasubramanian, Niranjan},
  journal={arXiv preprint arXiv:2205.04652},
  year={2022}
}

@inproceedings{tsoukaladelis2024times,
  title={The times they are a-changin’: Characterizing post-publication changes to online news},
  author={Tsoukaladelis, Chris and Kondracki, Brian and Balasubramanian, Niranjan and Nikiforakis, Nick},
  booktitle={2024 IEEE Symposium on Security and Privacy (SP)},
  pages={1573--1589},
  year={2024},
  organization={IEEE}
}

@article{soni2023large,
  title={Large human language models: A need and the challenges},
  author={Soni, Nikita and Schwartz, H Andrew and Sedoc, Jo{\~a}o and Balasubramanian, Niranjan},
  journal={arXiv preprint arXiv:2312.07751},
  year={2023}
}

@article{baicontinual,
  title={Continual Learning with Global Prototypes: Beyond the Scope of Task Supervision},
  author={Bai, Xueying and Shang, Jinghuan and Sun, Yifan and Balasubramanian, Niranjan}
}

@article{soni2024comparing,
  title={Comparing Human-Centered Language Modeling: Is it Better to Model Groups, Individual Traits, or Both?},
  author={Soni, Nikita and Balasubramanian, Niranjan and Schwartz, H Andrew and Hovy, Dirk},
  journal={arXiv preprint arXiv:2401.12492},
  year={2024}
}

@article{bai2022enhancing,
  title={Enhancing Continual Learning with Global Prototypes: Counteracting Negative Representation Drift},
  author={Bai, Xueying and Shang, Jinghuan and Sun, Yifan and Balasubramanian, Niranjan},
  journal={arXiv preprint arXiv:2205.12186},
  year={2022}
}

@article{lal2024cat,
  title={CAT-BENCH: Benchmarking Language Model Understanding of Causal and Temporal Dependencies in Plans},
  author={Lal, Yash Kumar and Cohen, Vanya and Chambers, Nathanael and Balasubramanian, Niranjan and Mooney, Raymond},
  journal={arXiv preprint arXiv:2406.15823},
  year={2024}
}

@article{kim2024initializing,
  title={On Initializing Transformers with Pre-trained Embeddings},
  author={Kim, Ha Young and Balasubramanian, Niranjan and Kang, Byungkon},
  journal={arXiv preprint arXiv:2407.12514},
  year={2024}
}

@article{trivedi2024appworld,
  title={Appworld: A controllable world of apps and people for benchmarking interactive coding agents},
  author={Trivedi, Harsh and Khot, Tushar and Hartmann, Mareike and Manku, Ruskin and Dong, Vinty and Li, Edward and Gupta, Shashank and Sabharwal, Ashish and Balasubramanian, Niranjan},
  journal={arXiv preprint arXiv:2407.18901},
  year={2024}
}

@inproceedings{mondal2025look,
  title={Look Hear: Gaze Prediction for Speech-directed Human Attention},
  author={Mondal, Sounak and Ahn, Seoyoung and Yang, Zhibo and Balasubramanian, Niranjan and Samaras, Dimitris and Zelinsky, Gregory and Hoai, Minh},
  booktitle={European Conference on Computer Vision},
  pages={236--255},
  year={2025},
  organization={Springer, Cham}
}

@inproceedings{soni2024comparing,
  title={Comparing Pre-trained Human Language Models: Is it Better with Human Context as Groups, Individual Traits, or Both?},
  author={Soni, Nikita and Balasubramanian, Niranjan and Schwartz, H and Hovy, Dirk},
  booktitle={Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, \& Social Media Analysis},
  pages={316--328},
  year={2024}
}

@article{bai2024does,
  title={Does roberta perform better than bert in continual learning: An attention sink perspective},
  author={Bai, Xueying and Sun, Yifan and Balasubramanian, Niranjan},
  journal={arXiv preprint arXiv:2410.05648},
  year={2024}
}

@inproceedings{hasan2024handling,
  title={Handling Open-Vocabulary Constructs in Formalizing Specifications: Retrieval Augmented Parsing with Expert Knowledge},
  author={Hasan, Mohammad Saqib and Ghosh, Sayontan and Verma, Dhruv and Kuenning, Geoff and Zadok, Erez and Smolka, Scott and Balasubramanian, Niranjan},
  booktitle={First Conference on Language Modeling},
  year={2024}
}

@inproceedings{baicontinual,
  title={Continual Learning with Global Alignment},
  author={Bai, Xueying and Shang, Jinghuan and Sun, Yifan and Balasubramanian, Niranjan},
  booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems}
}