SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2506.01262 · ACL · 2025

Exploring the Potential of LLMs as Personalized Assistants: Dataset, Evaluation, and Analysis

Sungroh Yoon, Jisoo Mok, Sangkwon Park, Ik-Hwan Kim, Salvador Dali

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 6 functions out of this paper's own repositories and ran 5 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
12kimih/HiCUPID canonical 5 of 6
FunctionStatusWhere it lives
build_dialogue Ran 12kimih/HiCUPID/src/train_dpo.py
code served (permissive licence) · get_code("294b85875c0758d0")
build_messages Ran 12kimih/HiCUPID/src/train_dpo.py
code served (permissive licence) · get_code("a8cb09c73a473dbb")
build_messages Ran 12kimih/HiCUPID/src/train_sft.py
code served (permissive licence) · get_code("5f8f8198f02dec22")
compute_metric Ran 12kimih/HiCUPID/src/bleu_rouge.py
code served (permissive licence) · get_code("0bbec0695520ec07")
should_retry Ran 12kimih/HiCUPID/src/download_hf.py
code served (permissive licence) · get_code("2055b1e599b445a9")
build_history Not yet run 12kimih/HiCUPID/src/train_dpo.py
code served (permissive licence) · get_code("9e4e968bde8383ed")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Personalized AI assistants, a hallmark of the human-like capabilities of Large Language Models (LLMs), are a challenging application that intertwines multiple problems in LLM research. Despite the growing interest in the development of personalized assistants, the lack of an open-source conversational dataset tailored for personalization remains a significant obstacle for researchers in the field. To address this research gap, we introduce HiCU-PID, a new benchmark to probe and unleash the potential of LLMs to deliver personalized responses. Alongside a conversational dataset, HiCUPID provides a Llama-3.2-based automated evaluation model whose assessment closely mirrors human preferences. We release our dataset, evaluation model, and code at https://github.com/12kimih/HiCUPID.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2506.01262")
get_code_for_paper("2506.01262")
have("2506.01262")

Connect an agent — have() is free.