Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse domains, yet personalizing their outputs to individual users remains an open challenge.

The gap

Consensus across the literature

Supporting evidence — 4 representative gaps

• Generalizable and scalable multistage biomedical concept normalization leveraging large language models (2025) · doi

  Large Language Models (LLMs), in turn, have shown great potential and high performance in a variety of natural language processing (NLP) tasks, but their application for normalization remains understudied.

  Keywords: language large models llms turn great potential high performance variety natural processing tasks application normalization
• Beyond Isolated Behaviors: Hierarchical User Modeling for LLM Personalization (2026)

  Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse domains, yet personalizing their outputs to individual users remains an open challenge.

  Keywords: large language models llms remarkable capabilities across diverse domains personalizing outputs individual users remains open
• Large language model-based paper classification framework with key-insight extraction and confidence-weighted voting (2026) · doi

  While large language models (LLMs) present new opportunities for automation, limited research has examined whether they can achieve classification performance comparable to human reviewers in large-scale, multi-class settings.

  Keywords: large language models llms present opportunities automation limited examined whether achieve classification performance comparable human
• LLM-as-a-Reviewer: Benchmarking Their Ability, Divergence, and Prompt Injection Resistance as Paper Reviewers (2026)

  Large language models (LLMs) are increasingly used in academic peer review, yet their reliability, alignment with human judgment, and robustness to adversarial attacks remain poorly understood.

  Keywords: large language models llms increasingly used academic peer review reliability alignment human judgment robustness adversarial