Aryaman Arora / Acknowledgements

2026

SLIDERS: Systematic Reviews via Automated Evidence Synthesis and Reconciliation
Harshit Joshi, Priyank Shethia, Jadelynn Dao, Monica S. Lam

Learning a Generative Meta-Model of LLM Activations
Grace Luo, Jiahai Feng, Trevor Darrell, Alec Radford, Jacob Steinhardt

Shaping capabilities with token-level data filtering
Neil Rathi, Alec Radford

2025

HyperSteer: Activation Steering at Scale with Hypernetworks
Jiuding Sun, Sidharth Baskaran, Zhengxuan Wu, Michael Sklar, Christopher Potts, Atticus Geiger

AutoMetrics: Approximate Human Judgements with Automatically Generated Evaluators
Michael J. Ryan, Yanzhe Zhang, Amol Salunkhe, Yi Chu, Di Xu, Diyi Yang

Searching for Privacy Risks in LLM Agents via Simulation
Yanzhe Zhang, Diyi Yang

The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideas
Chenglei Si, Tatsunori Hashimoto, Diyi Yang

A Reasoning-Focused Legal Retrieval Benchmark
Lucia Zheng, Neel Guha, Javokhir Arifov, Sarah Zhang, Michal Skreta, Christopher D. Manning, Peter Henderson, Daniel E. Ho

Language Models May Verbatim Complete Text They Were Not Explicitly Trained On
Ken Ziyu Liu, Christopher A. Choquette-Choo, Matthew Jagielski, Peter Kairouz, Sanmi Koyejo, Percy Liang, Nicolas Papernot

In-Context Learning Boosts Speech Recognition via Human-like Adaptation to Speakers and Language Varieties
Nathan Roll, Calbert Graham, Yuka Tatsumi, Kim Tien Nguyen, Meghan Sumner, Dan Jurafsky

Soft production preferences emerge from a bottleneck on memory
Neil Rathi, Richard Futrell, Dan Jurafsky

2024

Self-refining diffusion samplers: Enabling parallelization via parareal iterations
Nikil Roashan Selvam, Amil Merchant, Stefano Ermon

The Semantic Hub Hypothesis: Language models share semantic representations across languages and modalities
Zhaofeng Wu, Xinyan Velocity Yu, Dani Yogatama, Jiasen Lu, Yoon Kim

Attacking vision-language computer agents via pop-ups
Yanzhe Zhang, Tao Yu, Diyi Yang

Mechanistic?
Naomi Saphra, Sarah Wiegreffe

From insights to actions: The impact of interpretability and analysis research on NLP
Marius Mosbach, Vagrant Gautam, Tomás Vergara-Browne, Dietrich Klakow, Mor Geva

Demystifying Verbatim Memorization in Large Language Models
Jing Huang, Diyi Yang, Christopher Potts

Hydragen: High-Throughput LLM Inference with Shared Prefixes
Jordan Juravsky, Bradley Brown, Ryan Ehrlich, Daniel Y. Fu, Christopher Ré, Azalia Mirhoseini

Controllable and reliable knowledge-intensive task-oriented conversational agents with declarative Genie Worksheets
Harshit Joshi, Shicheng Liu, James Chen, Robert Weigle, Monica S. Lam

Representation fine-tuning on vision tasks
Zheng Wang

Sketch2Code: Evaluating vision-language models for interactive web design prototyping
Ryan Li, Yanzhe Zhang, Diyi Yang

Improving access to untranscribed speech corpora using AI
Nay Myo San

Language learning meets Generative AI: Utilizing large language models for metalinguistic explanations
Shabnam Behzad

Can LLMs generate novel research ideas? A large-scale human study with 100+ NLP researchers
Chenglei Si, Diyi Yang, Tatsunori Hashimoto

Machine unlearning in 2024
Ken Ziyu Liu

gzip predicts data-dependent scaling laws
Rohan Pandey

A Universal Dependencies treebank for Gujarati
Mayank Jobanputra, Maitrey Mehta, Çağrı Çöltekin

Connecting language technologies with rich, diverse data sources covering thousands of languages
Daan van Esch, Sandy Ritchie, Sebastian Ruder, Julia Kreutzer, Clara Rivera, Ishank Saxena, Isaac Caswell

Improved neural protoform reconstruction via reflex prediction
Liang Lu, Jingzhi Wang, David R. Mortensen

Design2Code: Benchmarking multimodal code generation for automated front-end engineering
Chenglei Si, Yanzhe Zhang, Zhengyuan Yang, Ruibo Liu, Diyi Yang

ColorSwap: A color and word order dataset for multimodal evaluation
Jirayu Burapacheep, Ishan Gaur, Agam Bhatia, Tristan Thrush

Mission: Impossible Language Models
Julie Kallini, Isabel Papadimitriou, Richard Futrell, Kyle Mahowald, Christopher Potts

I am a Strange Dataset: Metalinguistic tests for language models
Tristan Thrush, Jared Moore, Miguel Monares, Christopher Potts, Douwe Kiela

2023

Human raters cannot distinguish English translations from original English texts
Shira Wein

Verifying annotation agreement without multiple experts: A case study with Gujarati SNACS
Maitrey Mehta, Vivek Srikumar

Semantic composition in visually grounded language models
Rohan Pandey

Syntax-guided neural module distillation to probe compositionality in sentence embeddings
Rohan Pandey

2022

Putting context in SNACS: A 5-Way classification of adpositional pragmatic markers
Yang Janet Liu, Jena D. Hwang, Nathan Schneider, Vivek Srikumar

The Borrowings Kṣuta-/kṣut- (“Inimical”) and Vidumāla- (“Retrograde”) in Sanskrit Astrological Texts and the Representation of Semitic *ʿayn* in Similar Loans
Ola Wikander

2021

Mischievous nominal constructions in Universal Dependencies
Nathan Schneider, Amir Zeldes

Las tecnologías de Reconocimiento Automático de Voz y su incorporación a los métodos de transcripción de lenguas indígenas
Hilaria Cruz

Results of the Second SIGMORPHON Shared Task on Multilingual Grapheme-to-Phoneme Conversion
Lucas F.E. Ashby, ..., Winnie Yan

Draw *mir* a Sheep: A supersense-based analysis of German case and adposition semantics
Jakob Prange, Nathan Schneider

Inverse problems for a class of stochastic ordinary differential equations in a generalized fiducial framework
Samopriya Basu

2014

Sustainability strategies in supply chain management
Amit Arora