Trying to justify excluded experiments in *ACL short papers always reminds me of the Jewish joke about the mother who gifts her son two neckties for his birthday. The next day, seeing him wearing one of the new ties, she asks "what, you didn't like the other tie?"

Excited to present my paper with Rachel Rudinger and Balaji Vasan Srinivasan at #AAAI2022 which introduces a new task of entailment relation-aware paraphrase generation. Paper: aaai.org/AAAI22Papers/A… If you are attending #AAAI22, please stop by at our poster sessions on Feb 26 and 27.

We want your input on a policy for paper awards at *ACL conferences! (under review by the exec) Key points: - Improve consistency - Highlight more papers and a wider range of contributions - Judge the camera-ready Policy: web.eecs.umich.edu/~jkummerf/draf… Feedback: forms.gle/9QketBEHraYzfu…

While current bias-detection algorithms require a list of pre-designed stereotypes, we propose an open-ended framework to uncover social biases in models. Our work will be presented at #EACL2023 (arxiv.org/abs/2210.07269). Many thanks to Rachel Rudinger Jieyu Zhao and Zongxia!

My first paper and my first Ph.D. work has been accepted to the Findings of ACL 2023! 🎇🎇 Work done with Rachel Rudinger at UMD CLIP Lab. Paper and details to follow soon. #NLProc #ACL2023NLP #ACL2023Toronto

Paper Alert!! 📜🧨 #ACL2023NLP #NLProc FORK: A Bite-Sized Test Set for Probing Culinary Cultural Biases in Commonsense Reasoning Models. Work done with Rachel Rudinger at UMD CLIP Lab Details in 🧵(1/n) :

Excited to be speaking at this event!

Some good news that I'm excited to share today: I've received an NSF CAREER award! This award will support my group's research on robust, fair, and culturally aware commonsense reasoning in natural language. Feeling grateful to my students & the many people who have supported me!

Big congrats to Nishant Balepur for winning a best paper award at MASC-SLL 2024! 🥳

Great news to wrap up the first year of my PhD—two papers (1 main, 1 findings) on LLM reasoning capabilities in multiple-choice question answering accepted to ACL 2024! 🥳 Super grateful for my collaborators and advisors Jordan Boyd-Graber Rachel Rudinger for their support this year 🥹

Postering today at #NAACL2024 🇲🇽 with Neha Srikanth: Pragmatic Awareness in Maternal Health QA When humans ask questions that explicitly or implicitly signal false beliefs, an expert answer will likely start by correcting that belief. But to what extent do QA systems do that?

Presenting this today with Rupak (co-first author) at #NAACL2024 Poster Session 2 @ 2pm✨ We show that considering false presuppositions and implicatures can make answers about maternal health questions much more complete! 🔗Paper: arxiv.org/abs/2311.09542

"Call me by your name and I'll call you by mine." 🌈👩‍❤️‍👨👨‍❤️‍👨 Excited to share our new paper: "On the Influence of Gender and Race in Romantic Relationship Prediction from Large Language Models" with Abhilasha Sancheti and Rachel Rudinger ! arxiv.org/abs/2410.03996

Excited to share our new paper (to appear EMNLP 2025 ) on "heteronormitivity and iterracial biases in LLMs" with Haozhe An and Rachel Rudinger One of the projects that I really enjoyed working on 😀

🚨 New Reasoning Paper 🚨 Want to test if your LLM can truly do abductive reasoning? 🧪 Try our new task of Reverse Question Answering, where models must generate an accurate question for an input answer! Strong LLMs like GPT-4 + Claude-Opus struggle to do this with numbers 🫠

I will be presenting this paper tomorrow at EMNLP 2025 at Poster Session F (Riverfront Hall) at 10:30 AM! Come check it out 😁! Paper link: aclanthology.org/2024.findings-… #EMNLP2024 #NLProc

1/ Are two #LLMs better than one for equitable cultural alignment? 🌍 We introduce a Multi-Agent Debate framework — where two LLM agents debate the cultural adaptability of a given scenario. #ACL2025 🧵👇

I'm presenting two papers at #ACL2025!! Let's chat about alignment, evals, NLP+edu, or any other fun research idea :)

I'm really excited about this new line of work with my collaborators at UMD and ARL on detecting common ground misalignments (basically, misunderstandings) in human goal-oriented conversations. Great summary below, or come to Philip Resnik's talk today at #ACL2025NLP! 2pm Hall N.1

When questions are poorly posed, how do humans vs. models handle them? Our #ACL2025 paper explores this + introduces a framework for detecting and analyzing poorly-posed information-seeking questions! Joint work with Jordan Boyd-Gräber befindet sich in Wien (ACL2025) & Rachel Rudinger! 🔗 aclanthology.org/2025.acl-long.…