Pith. sign in

REVIEW 2 cited by

Quantifying perturbation impacts 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 2412.00868 v1 pith:KFEPYIT6 submitted 2024-12-01 cs.LG cs.CLmath.STstat.MLstat.TH

classification cs.LGcs.CLmath.STstat.MLstat.TH
keywords perturbationanalysisdbpaimpactscarloframeworkfrequentistinput
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We consider the problem of quantifying how an input perturbation impacts the outputs of large language models (LLMs), a fundamental task for model reliability and post-hoc interpretability. A key obstacle in this domain is disentangling the meaningful changes in model responses from the intrinsic stochasticity of LLM outputs. To overcome this, we introduce Distribution-Based Perturbation Analysis (DBPA), a framework that reformulates LLM perturbation analysis as a frequentist hypothesis testing problem. DBPA constructs empirical null and alternative output distributions within a low-dimensional semantic similarity space via Monte Carlo sampling. Comparisons of Monte Carlo estimates in the reduced dimensionality space enables tractable frequentist inference without relying on restrictive distributional assumptions. The framework is model-agnostic, supports the evaluation of arbitrary input perturbations on any black-box LLM, yields interpretable p-values, supports multiple perturbation testing via controlled error rates, and provides scalar effect sizes for any chosen similarity or distance metric. We demonstrate the effectiveness of DBPA in evaluating perturbation impacts, showing its versatility for perturbation analysis.

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Large Language Models for Statistical Inference: Context Augmentation with Applications to the Two-Sample Problem and Regression

    stat.ME 2025-06 conditional novelty 7.0 of 10

    Context augmentation uses LLM-generated contexts as latent variables to enable frequentist two-sample tests and text-on-text regression with claimed asymptotic guarantees.

  2. "GenAI Defaults to Bias!" Gamify AI Literacy Through Reflections on Prompts

    cs.HC 2025-09 conditional novelty 5.0 of 10

    Playing ImaginAItion, a prompt-minimization party game, helped 30 adults recognize GenAI default biases and adjust their prompting strategies, according to pre-post survey coding.

Pith tools