Pith. sign in

GPT-3.5-turbo (Brown et al., 2020) This model is part of OpenAI’s well-known GPT series

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CL 1

years

2024 1

verdicts

CONDITIONAL 1

representative citing papers

Fact-Level Confidence Calibration and Self-Correction

cs.CL · 2024-11-20 · conditional · novelty 6.0

The paper measures LLM confidence per atomic fact, weights correctness by relevance, and uses high-confidence facts from the same response to correct low-confidence facts.

citing papers explorer

Showing 1 of 1 citing paper.

  • Fact-Level Confidence Calibration and Self-Correction cs.CL · 2024-11-20 · conditional · none · ref 4

    The paper measures LLM confidence per atomic fact, weights correctness by relevance, and uses high-confidence facts from the same response to correct low-confidence facts.