Image de couverture de livre

Metadata Predictability Is Not Evidence Dependence: An Intervention-Based Audit for Weak-Label Benchmarks

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Shao, Kan
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Cross-Environment Neural Reranking for Sample-Efficient Action Selection in Text-Based Agents
par: Shao, Kan
Publié: (2026)

Textless Dependency Parsing by Labeled Sequence Prediction
par: Kando, Shunsuke, et autres
Publié: (2024)

Claim-Selective Certification for High-Risk Medical Retrieval-Augmented Generation
par: Kan, Shao
Publié: (2026)

Label Dependencies-aware Set Prediction Networks for Multi-label Text Classification
par: Xinkai, Du, et autres
Publié: (2023)

Auditing LLM Benchmarks with Item Response Theory
par: Land, Sander, et autres
Publié: (2026)

SciAnnotate: A Tool for Integrating Weak Labeling Sources for Sequence Labeling
par: Liu, Mengyang, et autres
Publié: (2022)

Dependency Graph Parsing as Sequence Labeling
par: Ezquerro, Ana, et autres
Publié: (2024)

Automated Benchmark Auditing for AI Agents and Large Language Models
par: Wang, Junlin, et autres
Publié: (2026)

AuditGPT: Auditing Smart Contracts with ChatGPT
par: Xia, Shihao, et autres
Publié: (2024)

Keeping Up with the Language Models: Systematic Benchmark Extension for Bias Auditing
par: Baldini, Ioana, et autres
Publié: (2023)

Predicting Microbial Ontology and Pathogen Risk from Environmental Metadata with Large Language Models
par: Yoo, Hyunwoo, et autres
Publié: (2025)

MIRA: A Bilingual Benchmark for Medical Information Response Audit
par: Xu, Mengyu, et autres
Publié: (2026)

Metric-Dependent Annotation Saturation for Learning from Label Distributions
par: Kohli, Guneet
Publié: (2026)

Position: LLM Unlearning Benchmarks are Weak Measures of Progress
par: Thaker, Pratiksha, et autres
Publié: (2024)

EviSearch: A Human in the Loop System for Extracting and Auditing Clinical Evidence for Systematic Reviews
par: Ahuja, Naman, et autres
Publié: (2026)

GenAudit: Fixing Factual Errors in Language Model Outputs with Evidence
par: Krishna, Kundan, et autres
Publié: (2024)

RW-Post: Auditable Evidence-Grounded Multimodal Fact-Checking in the Wild
par: Xu, Danni, et autres
Publié: (2025)

Metadata Conditioned Large Language Models for Localization
par: Mukherjee, Anjishnu, et autres
Publié: (2026)

QQ: A Toolkit for Language Identifiers and Metadata
par: Poelman, Wessel, et autres
Publié: (2026)

Talk is (Not) Cheap: A Taxonomy and Benchmark Coverage Audit for LLM Attacks
par: Iyer, Karthik Raghu, et autres
Publié: (2026)

DependEval: Benchmarking LLMs for Repository Dependency Understanding
par: Du, Junjia, et autres
Publié: (2025)

BenchGuard: Who Guards the Benchmarks? Automated Auditing of LLM Agent Benchmarks
par: Tu, Xinming, et autres
Publié: (2026)

Revisiting Semantic Role Labeling: Efficient Structured Inference with Dependency-Informed Analysis
par: Youm, Sangpil, et autres
Publié: (2026)

Appear2Meaning: A Cross-Cultural Benchmark for Structured Cultural Metadata Inference from Images
par: Jiang, Yuechen, et autres
Publié: (2026)

EvidenceBench: A Benchmark for Extracting Evidence from Biomedical Papers
par: Wang, Jianyou, et autres
Publié: (2025)

Better Benchmarking LLMs for Zero-Shot Dependency Parsing
par: Ezquerro, Ana, et autres
Publié: (2025)

AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviors
par: Sheshadri, Abhay, et autres
Publié: (2026)

Metadata Conditioning Accelerates Language Model Pre-training
par: Gao, Tianyu, et autres
Publié: (2025)

From Chaos to Clarity: Schema-Constrained AI for Auditable Biomedical Evidence Extraction from Full-Text PDFs
par: Mortezaagha, Pouria, et autres
Publié: (2025)

LLM Spirals of Delusion: A Benchmarking Audit Study of AI Chatbot Interfaces
par: Kirgis, Peter, et autres
Publié: (2026)

ECBD: Evidence-Centered Benchmark Design for NLP
par: Liu, Yu Lu, et autres
Publié: (2024)

Contextual Label Projection for Cross-Lingual Structured Prediction
par: Parekh, Tanmay, et autres
Publié: (2023)

MOLE: Metadata Extraction and Validation in Scientific Papers Using LLMs
par: Alyafeai, Zaid, et autres
Publié: (2025)

Question Suggestion for Conversational Shopping Assistants Using Product Metadata
par: Vedula, Nikhita, et autres
Publié: (2024)

BengaliMoralBench: A Benchmark for Auditing Moral Reasoning in Large Language Models within Bengali Language and Culture
par: Ridoy, Shahriyar Zaman, et autres
Publié: (2025)

SPOT: An Annotated French Corpus and Benchmark for Detecting Critical Interventions in Online Conversations
par: Berriche, Manon, et autres
Publié: (2025)

A Multi-Probe Audit of Clinical-Interview Depression Detection Benchmarks
par: Ishikawa, Takehiro, et autres
Publié: (2026)

Constructing Benchmarks and Interventions for Combating Hallucinations in LLMs
par: Simhi, Adi, et autres
Publié: (2024)

DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence
par: Venkit, Pranav Narayanan, et autres
Publié: (2025)

Interpreting Predictive Probabilities: Model Confidence or Human Label Variation?
par: Baan, Joris, et autres
Publié: (2024)