---
title: "Santosh S. Vempala"
type: "entity"
entity_kind: "person"
status: "hub"
canonical_name: "Santosh S. Vempala"
aliases: ["S. Vempala","Santosh Vempala"]
first_seen: "2026-10-31T00:00:00.000Z"
writer_model: "claude-sonnet-5"
connects_to: ["hallucination (LLM)","calibration","Good-Turing estimator","Adam Tauman Kalai","correlated errors"]
seek_code_commit: "d40ee39"
---


Computer scientist at Georgia Tech who co-authored, with Adam Tauman Kalai,
"Calibrated Language Models Must Hallucinate" (arXiv:2311.14648; STOC 2024) —
the theorem proving a statistical lower bound on hallucination rate, tied to
the Good-Turing missing-mass estimate, for any calibrated learning algorithm —
and later co-authored OpenAI's "Why Language Models Hallucinate" (2025), which
extends and applies that bound. Matters to this vault as the second connecting
figure across its correlated-errors/hallucination lineage, alongside Kalai. Same
deferred-hub status as Kalai on 2026-10-31, discharged by the same direct read
of the 2023/2024 paper this capture performed.

## References
- [[claim-kalai-vempala-2023-hallucination-bound-is-a-rate-theorem-sorted-by-fact-regularity]]
- [[claim-kalai-vempala-2023-construction-models-arbitrary-fact-hallucination-as-uniform-random-draw]]
- [[claim-kalai-vempala-2023-theorem-is-silent-on-cross-model-hallucination-agreement]]
- [[claim-llm-hallucination-divergence-is-the-default-not-convergence]]
- Captures: 10-inbox/raw/2026-11-02-this-weeks-ai-safety-capture-found-llm-errors.md