Author

S. Khan

h-index 2 View on Semantic Scholar

We have 4 of 8 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

SynthAVE: Scalable Synthetic Labeling for E-Commerce with LLM-Arena Validation

SynthAVE is presented, a large-scale benchmark for attribute-value verification spanning 12,726 products across 229 product types, 792 attributes, and 4 languages and demonstrates that diverse models with varying individual judgments aggregate into highly reliable predictions, enabling cost-effective validation at scal...

Andrea Scarinci, V. Negri, Brayan Impata et al. · arXiv.org · 0 citations

#machine learning Preprint Sep 2026

Positional task conditioning for scalable defect detection across product families in large product catalogs

Positional Task Conditioning (PTC) is introduced, which distills this capability into a single smaller model by reinforcing task identity at structural prompt boundaries by outperforms rationale-based distillation across five models and two architecture families.

Soham Satyadharma, G. Roccabruna, S. Khan · 1 citation

Agentic Prompt Optimization for E-Commerce Catalog Enrichment at Scale

CascadeAgent is introduced, a multi-agent framework that automates prompt adaptation and specialization through error-driven semantic refinement and discusses the evaluation and deployment lessons from this setting, including precision– coverage trade-offs, negative labels for abstention, semantic verification of ambig...

Peng Gao, Athanasios N. Nikolakopoulos, Zhuo Cheng et al. · 1 citation

#artificial intelligence Review Jul 2026

SynthAVE: Scalable Synthetic Labeling for E-Commerce with LLM-Arena Validation

Fine-tuning large language models (LLMs) for e-commerce attribute extraction requires labeled data representative across thousands of product types, attributes, and multiple languages. This combinatorial scale translates to millions of annotations, rendering human labeling prohibitively costly. While recent work has de...

Andrea Scarinci, V. Negri, Brayan Impata et al. · 0 citations