user-modeling

Tag

Cards List
#user-modeling

Toward Personal Intelligence Through Cooperative Observation

arXiv cs.AI · 2026-08-19 Cached

This paper proposes 'cooperative observation' as a framework for personal intelligence, emphasizing a feedback loop between AI systems and users to improve assistance, trust, and privacy. It reports on a preliminary case study from the Organizm prototype used over six months and outlines evaluation directions.

0 favorites 0 likes
#user-modeling

Inverse Theory of Mind Modeling for Content Recommendation: From Web Browsing to Dynamic Intelligent Interfaces

arXiv cs.AI · 2026-08-13 Cached

The paper proposes an Inverse Theory of Mind (IToM) pipeline that infers user beliefs, preferences, and decision-making traits from observed interactions, using LLM-driven counterfactual reasoning to synthesize structured user personas for adaptive content recommendation across modalities, including a VisionOS spatial banking app.

0 favorites 0 likes
#user-modeling

SERUM: State Extraction and Refinement for User Modeling

arXiv cs.LG · 2026-08-03 Cached

Presents SERUM, a multi-pass framework that extracts structured behavioral models of user actions and intents from raw egocentric video using hierarchical VLM annotation, reducing hallucinations and producing interpretable process models without manual annotation.

0 favorites 0 likes
#user-modeling

Learning Dynamic User Personas from Implicit Interaction Streams via Iterative Refinement

arXiv cs.LG · 2026-07-30 Cached

Introduces IRIS, a framework that learns dynamic user personas from implicit interaction streams without explicit feedback, outperforming static and memory-only baselines on decision prediction.

0 favorites 0 likes
#user-modeling

Beyond expert users: agents should help users construct preferences, not just elicit them

arXiv cs.AI · 2026-07-01 Cached

This paper argues that agents should help users construct preferences rather than assuming well-formed ones, proposing the CoPref model and CoShop benchmark. Evaluations show even frontier models achieve only 56% accuracy due to poor preference expansion.

0 favorites 0 likes
#user-modeling

ScaleToT: Generalizing Structured LLM Reasoning for Billion-Scale Low-Activity User Modeling

arXiv cs.AI · 2026-06-24 Cached

ScaleToT proposes a method to generalize structured LLM reasoning for low-activity user modeling at billion scale, using tree-of-thought refinement and training a student model to reduce cost. An online A/B test in advertising deployment showed a 6.738% increase in LT30.

0 favorites 0 likes
#user-modeling

ThoughtTrace: Understanding User Thoughts in Real-World LLM Interactions

Hugging Face Daily Papers · 2026-05-19 Cached

ThoughtTrace introduces a large-scale dataset pairing real-world multi-turn human-AI conversations with users' self-reported thoughts, enabling improved user behavior prediction and personalized assistant training through thought-guided rewrites.

0 favorites 0 likes
#user-modeling

IPQA: A Benchmark for Core Intent Identification in Personalized Question Answering

arXiv cs.CL · 2026-04-20 Cached

IPQA introduces a benchmark for evaluating core intent identification in personalized question answering, addressing a gap in existing metrics that focus on response quality rather than intent understanding. The paper presents a dataset construction methodology grounded in bounded rationality and demonstrates that state-of-the-art language models struggle with identifying user-prioritized intents from answer selection patterns.

0 favorites 0 likes
← Back to home

Submit Feedback