← Search

Hen Davidov

2 accepted papers

2026

Knowing When to Quit: A Principled Framework for Dynamic Abstention in LLM Reasoning

ICML 2026poster

Large language models (LLMs) using chain-of-thought reasoning often waste substantial compute by producing long, incorrect responses. Abstention can mitigate this by withholding outputs unlikely to be correct. While most abstention methods decide to withhold outputs before or after generation, dynam…

Cited by 3SourceScholar
2025

Conformalized Survival Analysis for General Right-Censored Data

ICLR 2025poster

We develop a framework to quantify predictive uncertainty in survival analysis, providing a reliable lower predictive bound (LPB) for the true, unknown patient survival time. Recently, conformal prediction has been used to construct such valid LPBs for *type-I right-censored data*, with the guarante…

Cited by 0SourcePDFScholar