Sanjana Ramprasad

Ph.D. Candidate, Northeastern University

Publications

Conference Proceedings

01

Do automatic factuality metrics measure factuality? a critical evaluation

S. Ramprasad and B. C. Wallace

Advances in Neural Information Processing Systems (NeurIPS), 2025

Paper →
02

Analyzing LLM behavior in dialogue summarization: Unveiling circumstantial hallucination trends

S. Ramprasad, E. Ferracane, and Z. Lipton

Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL), 2024

Paper →
03

Evaluating the factuality of zero-shot summarizers across varied domains

S. Ramprasad, K. Krishna, Z. Lipton, and B. Wallace

Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2024

Paper →
04

USB: A unified summarization benchmark across tasks and domains

K. Krishna, P. Gupta, S. Ramprasad, B. C. Wallace, J. P. Bigham, and Z. C. Lipton

Findings of the Association for Computational Linguistics: EMNLP, 2023

Paper →
05

Generating more faithful and consistent soap notes using attribute-specific parameters

S. Ramprasad, E. Ferracane, and S. P. Selvaraj

Machine Learning for Healthcare Conference (MLHC), 2023

Paper →
06

Automatically summarizing evidence from clinical trials: A prototype highlighting current challenges

S. Ramprasad, J. McInerney, I. Marshall, and B. C. Wallace

Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations (EACL), 2023

Paper →

Preprints & Under Review

01

More benign errors are better than a few severe ones: Evaluating hallucination severity

S. Ramprasad, P. Mani, C. Tan, E. Ferracane, B. C. Wallace, and Z. Lipton

Under review, 2025

02

GenAudit: Fixing factual errors in language model outputs with evidence

K. Krishna, S. Ramprasad, P. Gupta, B. C. Wallace, Z. C. Lipton, and J. P. Bigham

arXiv preprint arXiv:2402.12566, 2024

Paper →