Skip to content

Author

Deepa Tilwani

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint May 2024

Abstention vs. Hallucination: Benchmarking LLM Source Attribution for Scientific Citations

A dual-metric framework consisting of Abstention Rate (AR) and Hallucination Rate (HR) is proposed to characterize the trade-off between reliability and responsiveness to demonstrate that citation attribution systems should be evaluated not only for correctness but also for their ability to abstain appropriately under...

Deepa Tilwani, Yash Saxena, Seyedali Mohammadi et al. · 11 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.