Pith. sign in

REVIEW 5 cited by

Calibrating Verbalized Probabilities for Large Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.06707 v1 pith:RW7E2CWB submitted 2024-10-09 cs.CL cs.AI

Calibrating Verbalized Probabilities for Large Language Models

classification cs.CL cs.AI
keywords verbalizedllmsprobabilitiesdistributionsscalingcalibratingcalibrationcapability
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Calibrating verbalized probabilities presents a novel approach for reliably assessing and leveraging outputs from black-box Large Language Models (LLMs). Recent methods have demonstrated improved calibration by applying techniques like Platt scaling or temperature scaling to the confidence scores generated by LLMs. In this paper, we explore the calibration of verbalized probability distributions for discriminative tasks. First, we investigate the capability of LLMs to generate probability distributions over categorical labels. We theoretically and empirically identify the issue of re-softmax arising from the scaling of verbalized probabilities, and propose using the invert softmax trick to approximate the "logit" by inverting verbalized probabilities. Through extensive evaluation on three public datasets, we demonstrate: (1) the robust capability of LLMs in generating class distributions, and (2) the effectiveness of the invert softmax trick in estimating logits, which, in turn, facilitates post-calibration adjustments.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Aligning Language Models with Selective Prediction

    cs.LG 2026-07 accept novelty 7.0

    RLSR aligns LLMs via a lifted AURC reward and batch ranking inside GRPO, producing better risk-coverage curves than accuracy- or calibration-based RL on in- and out-of-domain tasks.

  2. Process Supervision of Confidence Margin for Calibrated LLM Reasoning

    cs.LG 2026-04 unverdicted novelty 6.0

    RLCM trains LLMs with a margin-enhanced process reward that widens the gap between correct and incorrect reasoning steps, improving calibration on math, code, logic, and science tasks without hurting accuracy.

  3. RePrompT: Recurrent Prompt Tuning for Integrating Structured EHR Encoders with Large Language Models

    cs.CL 2026-04 unverdicted novelty 6.0

    RePrompT uses recurrent prompt tuning to inject prior-visit latent states and cohort-derived population prompt tokens into LLMs, yielding better performance than pure EHR or pure LLM baselines on MIMIC clinical predic...

  4. Speaking in Self-Assessing Tongues: On the Verbalized Confidence of LLMs in Machine Translation

    cs.CL 2026-06 unverdicted novelty 5.0

    Empirical study finds verbalized per-token confidence methods in LLMs for MT perform similarly to internal signals on error detection and calibration but show little correlation.

  5. Confidence Calibration for Multimodal LLMs: An Empirical Study through Medical VQA

    cs.CV 2026-06 unverdicted novelty 4.0

    A multi-strategy interrogation method with auxiliary expert assessment reduces expected calibration error by 40% on average across three medical VQA datasets for MLLMs.