# SocialPersona: Benchmarking Personalized Profiling and Response with Multimodal Social-Media Context

arXiv: https://arxiv.org/abs/2606.26654 · HTML: https://mlsanity.com/paper/2606.26654/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 129 references that are in the map.
- First posted on arXiv 25 Jun 2026.

## Builds on (most cited first, 24 of 24)

- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [FakeNewsNet: A Data Repository with News Content, Social Context and Spatialtemporal Information for Studying Fake News on Social Media](https://mlsanity.com/paper/1809.01286/) (2018)
- [Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale](https://mlsanity.com/paper/2504.14225/) (2025)
- [Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs](https://mlsanity.com/paper/2502.09597/) (2025)
- [End-to-End Multimodal Fact-Checking and Explanation Generation: A Challenging Dataset and Models](https://mlsanity.com/paper/2205.12487/) (2022)
- [CrisisMMD: Multimodal Twitter Datasets from Natural Disasters](https://mlsanity.com/paper/1805.00713/) (2018)
- [PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory](https://mlsanity.com/paper/2512.06688/) (2025)
- [SemEval-2020 Task 8: Memotion Analysis -- The Visuo-Lingual Metaphor!](https://mlsanity.com/paper/2008.03781/) (2020)
- [A Survey of Personalized Large Language Models: Progress and Future Directions](https://mlsanity.com/paper/2502.11528/) (2025)
- [Large Language Models Empowered Personalized Web Agents](https://mlsanity.com/paper/2410.17236/) (2024)
- [MuMiN: A Large-Scale Multilingual Multimodal Fact-Checked Misinformation Social Network Dataset](https://mlsanity.com/paper/2202.11684/) (2022)
- [GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse](https://mlsanity.com/paper/2401.01523/) (2024)
- [PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI Assistants](https://mlsanity.com/paper/2506.09902/) (2025)
- [User Modeling and User Profiling: A Comprehensive Survey](https://mlsanity.com/paper/2402.09660/) (2024)
- [A Survey on User Behavior Modeling in Recommender Systems](https://mlsanity.com/paper/2302.11087/) (2023)
- [KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluation](https://mlsanity.com/paper/2604.08455/) (2026)
- [FingerTip 20K: A Benchmark for Proactive and Personalized Mobile LLM Agents](https://mlsanity.com/paper/2507.21071/) (2025)
- [Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User History](https://mlsanity.com/paper/2602.17003/) (2026)
- [SoMeLVLM: A Large Vision Language Model for Social Media Processing](https://mlsanity.com/paper/2402.13022/) (2024)
- [Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction](https://mlsanity.com/paper/2511.13410/) (2025)
- [BESPOKE: Benchmark for Search-Augmented Large Language Model Personalization via Diagnostic Feedback](https://mlsanity.com/paper/2509.21106/) (2025)
- [GISTBench: Evaluating LLM User Understanding via Evidence-Based Interest Verification](https://mlsanity.com/paper/2603.29112/) (2026)
- [Follower--Followee Ratio Category and User Vector for Analyzing Following Behavior](https://mlsanity.com/paper/2210.13874/) (2022)

## Abstract (arXiv)

Personalized language-model assistants are often evaluated through a memory lens: can a model recall preferences users have explicitly stated in dialogue? More comprehensive personalization demands a harder capability -- inferring what users care about from the multimodal traces they naturally leave behind. We introduce SocialPersona, a benchmark for evaluating whether multimodal large language models (MLLMs) can recover revealed preferences from longitudinal social-media timelines and use them in dialogue. Built from longitudinal timelines of 171 everyday, non-promotional social-media users, SocialPersona contains text, images, timestamps, and 2,597 human-verified preference tags across seven interest domains, separating stable interests from recent interests. It supports two tasks: constructing structured user profiles from multimodal context and generating responses aligned with inferred profiles. Experiments with proprietary and open-weight MLLMs show that models can identify broad interest domains, yet their performance drops on fine-grained and recent interests and degrades further when inferred profiles must be used to personalize dialogue. Together with evidence that text and images provide complementary preference signals, these results indicate that robust cross-modal, long-horizon user modeling remains a key challenge, and that SocialPersona can help measure and advance progress toward assistants that infer and act on revealed preferences.