4 papers
Autoresearch for Marketplace Catalogs: From Legacy Forms to AI-Native Matching
Kartik Ravisankar, Hojat Abdolanezhad, Daniel Capo +3
Two-sided service marketplaces are moving from deterministic request-form intake to AI-native probabilistic matching, enabled by large language models (LLMs) that infer intent, pre…
Evaluating Enterprise Analytics Agents: An End-to-End, Trace-Backed Methodology
Teja Venkat Kolli, Sang Su Lee, Xueying Yan +5
Enterprise analytics agents are not only text-to-SQL systems. They interpret business intent and choose metric definitions. They select data sources, execute tools, inspect results…
Can you map it to English? The Role of Cross-Lingual Alignment in Multilingual Performance of LLMs
Kartik Ravisankar, Hyojung Han, Sarah Wiegreffe +1
Large language models (LLMs) can answer prompts in many languages, despite being trained predominantly on English; yet, the mechanisms driving this generalization remain poorly und…
Token-level Ensembling of Models with Different Vocabularies
Rachel Wicks, Kartik Ravisankar, Xinchen Yang +2
Model ensembling is a technique to combine the predicted distributions of two or more models, often leading to improved robustness and performance. For ensembling in text generatio…