perturbation-analysis

Tag

Cards List
#perturbation-analysis

Perturbation-Based Data Selection for Medical Question Answering

arXiv cs.CL ↗ · 2026-10-27 Cached

This paper investigates perturbation-based data selection methods (RSP and RSP-Drop) for adapting medical language models, showing improved Macro-F1 scores over random selection when evaluated with MedGemma-4B on five medical QA datasets.

0 favorites 0 likes
#perturbation-analysis

PROOF: Profiling Reliability of Object-Level Facts in Large Language Models

arXiv cs.CL ↗ · 2026-09-25 Cached

PROOF is a profile-oriented benchmark that evaluates factual reliability in large language models using Wikidata-based multiple-choice questions with controlled interventions, revealing domain-specific coverage and stability under perturbations.

0 favorites 0 likes
#perturbation-analysis

MAWILE: Multi-Axis Workbench for Inspecting LLM Evaluators

arXiv cs.AI ↗ · 2026-09-23 Cached

MAWILE is a developer workbench for auditing the sensitivity of LLM judges to perturbations across prompts, rubrics, inputs, and outputs, ensuring robust and meaningful evaluations.

0 favorites 0 likes
#perturbation-analysis

How Perturbations Propagate: A Multi-Level Analysis of Robustness in Large Language Models

arXiv cs.CL ↗ · 2026-09-04 Cached

This paper conducts a multi-level analysis of how input perturbations propagate through decoder-only language models, assessing robustness via output behavior, hidden-state geometry, and attention-head function across models like GPT-2 and Qwen2.5.

0 favorites 0 likes
← Back to home

Submit Feedback