Publications

Yulu Qin, Dheeraj Varghese, Adam Dahlgren Lindstrom, Lucia Donatelli, Kanishka Misra, Najoung Kim (2025). Vision-and-Language Training Helps Deploy Taxonomic Knowledge but Does Not Fundamentally Alter It. In arxiv 2025.

Code arxiv website

William Sheffield, Kanishka Misra, Valentina Pyatkin, Ashwini Deo, Kyle Mahowald, Jessy Li (2025). Is It JUST Semantics? A Case Study of Discourse Particle Understanding in LLMs. In ACL 2025 Findings.

Code arxiv ACL Anthology

Sriram Padmanabhan, Kanishka Misra, Kyle Mahowald, Eunsol Choi (2025). On Language Models' Sensitivity to Suspicious Coincidences. In PragLM 2025 (COLM).

Code arxiv

Qing Yao, Kanishka Misra, Leonie Weissweiler, Kyle Mahowald (2025). Both Direct and Indirect Evidence Contribute to Dative Alternation Preferences in Language Models. In COLM 2025.

Code arxiv

Juan Diego Rodriguez, Aaron Mueller, Kanishka Misra (2024). Characterizing the Role of Similarity in the Property Inferences of Language Models. In Arxiv.

Code arxiv

Kanishka Misra, Najoung Kim (2024). Generating novel experimental hypotheses from language models: A case study on cross-dative generalization. In arxiv 2024.

Code arxiv

Kanishka Misra, Kyle Mahowald (2024). Language Models Learn Rare Phenomena from Less Rare Phenomena: The Case of the Missing AANNs. In EMNLP 2024.

Code Poster arxiv ACL Anthology

Kanishka Misra, Allyson Ettinger, Kyle Mahowald (2024). Experimental Contexts Can Facilitate Robust Semantic Property Inference in Language Models, but Inconsistently. In EMNLP 2024.

Code Poster arxiv ACL Anthology

Kanishka Misra, Najoung Kim (2023). Abstraction via exemplars? A representational case study on lexical category inference in BERT. In BUCLD 48.

PDF Poster

Koustuv Sinha, Jon Gauthier, Aaron Mueller, Kanishka Misra, Keren Fuentes, Roger Levy, Adina Williams (2023). Language model acceptability judgements are not always robust to context. In ACL 2023.

ACL Anthology

Kanishka Misra, Cicero Nogueira dos Santos, Siamak Shakeri (2023). Triggering Multi-Hop Reasoning for Question Answering in Language Models using Soft Prompts and Random Walks. In Findings of ACL 2023.

ACL Anthology

Kanishka Misra, Julia Taylor Rayz, Allyson Ettinger (2023). COMPS: Conceptual Minimal Pair Sentences for testing Robust Property Knowledge and its Inheritance in Pre-trained Language Models. In EACL 2023.

Code arxiv ACL Anthology Video

Kanishka Misra, Julia Taylor Rayz, Allyson Ettinger (2022). A Property Induction Framework for Neural Language Models. In CogSci 2022.

Code Poster arxiv Proceedings Supplementary

Kanishka Misra (2022). minicons: Enabling Flexible Behavioral and Representational Analyses of Transformer Language Models. In arxiv.

Code arxiv

Kanishka Misra (2021). On Semantic Cognition, Inductive Generalization, and Language Models. In AAAI 2022 Doctoral Consortium.

Poster arxiv

Kanishka Misra, Allyson Ettinger, Julia Taylor Rayz (2021). Do language models learn typicality judgments from text?. In CogSci 2021.

Code Slides Video arxiv Proceedings

Kanishka Misra, Julia Taylor Rayz (2021). Finding fuzziness in Neural Network Models of Language Processing (Forthcoming). In NAFIPS 2021.

Code arxiv

Kanishka Misra, Allyson Ettinger, Julia Taylor Rayz (2020). Exploring BERT’s Sensitivity to Lexical Cues using Tests from Semantic Priming. In Findings of ACL: EMNLP 2020.

Poster arxiv Anthology

Kanishka Misra, Allyson Ettinger, Julia Taylor Rayz (2020). Exploring Lexical Relations in BERT using Semantic Priming (Forthcoming). In CogSci 2020.

PDF Poster Video Supplementary

Kanishka Misra, Julia Taylor Rayz (2020). An Approximate Perspective on Word Prediction in Context: Ontological Semantics meets BERT (Forthcoming). In NAFIPS 2020.

PDF Slides

Tatiana Ringenberg, Kanishka Misra, Julia Taylor Rayz (2019). Not So Cute but Fuzzy: Estimating Risk of Sexual Predation in Online Conversations. In IEEE SMC 2019.

PDF Slides DOI Custom Link

Kanishka Misra, Hemanth Devarapalli, Tatiana Ringenberg, Julia Taylor Rayz (2019). Authorship Analysis of Online Predatory Conversations using Character Level Convolution Neural Networks. In IEEE SMC 2019.

PDF Slides DOI Custom Link

Qiaofei Ye, Kanishka Misra, Hemanth Devarapalli, Julia Taylor Rayz (2019). A Sentiment Based Non-Factoid Question-Answering Framework. In IEEE SMC 2019.

PDF DOI Custom Link

Kanishka Misra, Hemanth Devarapalli, Julia Taylor Rayz (2019). L1 Influence on Content Word errors in Learner English Corpora: Insights from Distributed Representation of Words. In CogSci 2019.

Poster Custom Link

Kanishka Misra, Hemanth Devarapalli, Julia Taylor Rayz (2019). Measuring the Influence of L1 on Learner English Errors in Content Words within Word Embedding Models. In ICCM 2019.

PDF Slides Custom Link

Tatiana Ringenberg, Kanishka Misra, Kathryn C. Seigfried-Spellar, Julia Taylor Rayz (2019). Exploring Automatic Identification of Fantasy-Driven and Contact-Driven Sexual Solicitors. In IEEE IRC 2019.

PDF DOI Custom Link

Kathryn C. Seigfried-Spellar, Marcus K. Rogers, Julia Taylor Rayz, Shih-Feng Yang, Kanishka Misra, Tatiana Ringenberg (2019). Chat Analysis Triage Tool: Differentiating contact-driven vs. fantasy-driven child sex offenders. In Forensic Science International.

PDF DOI Custom Link