← Search

Sangam Lee

2 accepted papers

2026

BESPOKE: Benchmark for Search-Augmented Large Language Model Personalization via Diagnostic Feedback

ICML 2026poster

Search-augmented large language models (LLMs) remain insufficient for fully addressing diverse user needs, which requires recognizing how the same query can reflect different intents across users and delivering information in preferred forms. While recent systems such as ChatGPT and Gemini attempt p…

Cited by 0SourceScholar
2026

Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User History

ICML 2026poster

Large language models have advanced web agents, yet current agents lack personalization capabilities. Since users rarely specify every detail of their intent, practical web agents must be able to interpret ambiguous queries by inferring user preferences and contexts. To address this challenge, we pr…

Cited by 0SourceScholar