Publications

This section contains publications published by ISI over the past several decades.

2025

STEER-BENCH: A Benchmark for Evaluating the Steerability of Large Language Models

Kai Chen, Zihao He, Taiwei Shi, Kristina Lerman
arXiv preprint arXiv:2505.20645,  2025

Community Moderation and the New Epistemology of Fact Checking on Social Media

Isabelle Augenstein, Michiel Bakker, Tanmoy Chakraborty, David Corney, Emilio Ferrara, Iryna Gurevych, Scott Hale, Eduard Hovy, Heng Ji, Irene Larraz, Filippo Menczer, Preslav Nakov, Paolo Papotti, Dhruv Sahnan, Greta Warren, Giovanni Zagni
arXiv preprint arXiv:2505.20067,  2025

Demonstration of Tunable and Reconfigurable All-Optical Matrix-Vector Multiplication Using Nonlinear Wave Mixing

Wing Ko, Abdulrahman Alhaddad, Amir Minoofar, Hongkun Lian, Huibin Zhou, Muralekrishnan Ramakrishnan, Zile Jiang, Xinzhou Su, Moshe Tur, Jonathan L Habif, Alan E Willner
Optical Fiber Communication Conference, W4D. 3,  2025

Large Language Models Do Multi-Label Classification Differently

Marcus Ma, Georgios Chochlakis, Niyantha Maruthu Pandiyan, Jesse Thomason, Shrikanth Narayanan
arXiv preprint arXiv:2505.17510,  2025

Humans Hallucinate Too: Language Models Identify and Correct Subjective Annotation Errors With Label-in-a-Haystack Prompts

Georgios Chochlakis, Peter Wu, Arjun Bedi, Marcus Ma, Kristina Lerman, Shrikanth Narayanan
arXiv preprint arXiv:2505.17222,  2025

Commonsense AI in the History of the Web

Mayank Kejriwal, Deborah L McGuinness, Henry Lieberman
Companion Proceedings of the ACM on Web Conference 2025, 837-840,  2025

Amulet: Putting Complex Multi-Turn Conversations on the Stand with LLM Juries

Sahana Ramnath, Anurag Mudgil, Brihi Joshi, Skyler Hallinan, Xiang Ren
arXiv preprint arXiv:2505.20451,  2025

Bridging the Narrative Divide: Cross-Platform Discourse Networks in Fragmented Ecosystems

Patrick Gerard, Hans WA Hanley, Luca Luceri, Emilio Ferrara
arXiv preprint arXiv:2505.21729,  2025

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings

Jingqi Xu, Chenghao Li, Yuke Zhang, Peter A Beerel
arXiv preprint arXiv:2505.21848,  2025

Evaluating the Efficacy of LLM-Based Reasoning for Multiobjective HPC Job Scheduling

Prachi Jadhav, Hongwei Jin, Ewa Deelman, Prasanna Balaprakash
arXiv preprint arXiv:2506.02025,  2025

Mamba Drafters for Speculative Decoding

Daewon Choi, Seunghyuk Oh, Saket Dingliwal, Jihoon Tack, Kyuyoung Kim, Woomin Song, Seojin Kim, Insu Han, Jinwoo Shin, Aram Galstyan, Shubham Katiyar, Sravan Babu Bodapati
arXiv preprint arXiv:2506.01206,  2025

Compress, Gather, and Recompute: REFORMing Long-Context Processing in Transformers

Woomin Song, Sai Muralidhar Jayanthi, Srikanth Ronanki, Kanthashree Mysore Sathyendra, Jinwoo Shin, Aram Galstyan, Shubham Katiyar, Sravan Babu Bodapati
arXiv preprint arXiv:2506.01215,  2025

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation

Tharindu Kumarage, Ninareh Mehrabi, Anil Ramakrishna, Xinyan Zhao, Richard Zemel, Kai-Wei Chang, Aram Galstyan, Rahul Gupta, Charith Peris
arXiv preprint arXiv:2505.21784,  2025

Medical school ranking and neighborhood characteristics of initial practice location among physicians

Navapat Nananukul, Mayank Kejriwal
JAMA Network Open 8 (5), e2512474-e2512474,  2025

Data Flows in You: Benchmarking and Improving Static Data-flow Analysis on Binary Executables

Nicolaas Weideman, Sima Arasteh, Mukund Raghothaman, Jelena Mirkovic, Christophe Hauser
arXiv preprint arXiv:2506.00313,  2025

CapSpeech: Enabling Downstream Applications in Style-Captioned Text-to-Speech

Helin Wang, Jiarui Hai, Dading Chong, Karan Thakkar, Tiantian Feng, Dongchao Yang, Junhyeok Lee, Laureano Moro Velazquez, Jesus Villalba, Zengyi Qin, Shrikanth Narayanan, Mounya Elhiali, Najim Dehak
arXiv preprint arXiv:2506.02863,  2025

MOOSE: Pay Attention to Temporal Dynamics for Video Understanding via Optical Flows

Hong Nguyen, Dung Tran, Hieu Hoang, Phong Nguyen, Shrikanth Narayanan
arXiv preprint arXiv:2506.01119,  2025

Towards disentangling the contributions of articulation and acoustics in multimodal phoneme recognition

Sean Foley, Hong Nguyen, Jihwan Lee, Sudarsana Reddy Kadiri, Dani Byrd, Louis Goldstein, Shrikanth Narayanan
arXiv preprint arXiv:2505.24059,  2025