Can language models discover what users actually want from activity logs?
Users pursue month-long interest journeys that transcend individual item clicks. Can LLMs extract these persistent goals from behavioral patterns, and does this change how we should think about personalization?
Recommender systems predict the next item a user might click on, given their history. But when you ask users what they're actually doing on the platform, they describe something different: persistent, overarching interests — "designing hydroponic systems for small spaces," "learning the ukulele as a beginner," "cooking Italian recipes." These are interest journeys, and they operate at a completely different level of abstraction from next-item prediction.
Survey data shows 66% of respondents recently pursued a valued journey on the platform. Of those, 80% consumed relevant content for more than a month, with half saying some journeys last more than a year. People pursue 1-3 journeys simultaneously.
The semantic gap is real: collaborative filtering captures correlational patterns between items ("people who watched X also watched Y") but cannot reason about the user's underlying goal, need, or interest. Two users both interested in stand-up comedy may pursue completely different aspects — history documentaries vs. SNL skits. The journey is personalized at a granularity collaborative filtering cannot reach.
LLMs can bridge this gap. Through personalized clustering of user activity logs followed by LLM-powered journey naming, the system produces journey descriptions users identify with. But specificity matters — "greenhouse designs for cold climates" was irrelevant for someone pursuing indoor gardening. The right level of abstraction is what the user would actually say to a friend asking about their interests.
This connects to How do personalization granularity levels trade precision against scalability? — interest journeys operate at the user level but require persona-level precision. Since Does chatbot personalization build trust or expose privacy risks?, journey-aware systems that understand your persistent interests will trigger both the trust and privacy dimensions of this dual dynamic.
Inquiring lines that use this note as a source 25
This note is a source for these synthesized inquiries. Follow a line forward into its question, or open it to trace back to all of its sources.
- How does sequential modeling within a session differ from modeling historical purchase sequences?
- How should historical preferences be weighted when users change their stated intent?
- Can aspect-augmentation help when user history is sparse or cold?
- What status categories best represent user goal progress without penalizing external failures?
- How does LLM-PKG compare to mining product relations directly from interaction data?
- What level of abstraction makes interest journeys feel personally relevant to users?
- Can curiosity-driven dialogue incrementally discover user interest journeys in real time?
- How does understanding persistent journeys intensify both trust and privacy concerns?
- Why do abstract semantic memories outperform specific interaction histories for journey discovery?
- How did Netflix's page generation algorithm evolve from rule-based to fully personalized?
- What makes historical user outputs more effective for personalization than semantic similarity?
- Can LLMs infer psychological profiles without explicit user disclosure?
- How do intrinsic motivation mechanisms differ between social proactivity and personalization?
- How much user interaction data is needed for effective AI personalization?
- Why do users experience LLMs as peers rather than statistical tools?
- Why do linear hybrid models fail to capture user-item relationships?
- What structural signals in user language reveal their unstated preferences and context?
- How can we measure whether a user actually understands their own needs?
- Can abstract preference summaries substitute for specific user interaction history?
- How can insert-expansion techniques help users discover their own preferences?
- What data types carry the most privacy risk in personalization systems?
- Does persona attention align with aspect-based explanation in sparse user histories?
- Why does semantic memory abstraction outperform raw episodic recall for personalization?
- What sequential patterns emerge from anonymous single-session data?
- Does temporal preference drift matter more than static user profiles for personalization?
Related concepts in this collection 5
This note in its neighbourhood — explore the map, then jump to a related concept in the list below.
Click a node to walk · click center to open · click Open in graph to see this note in the full knowledge graph
-
How do personalization granularity levels trade precision against scalability?
LLM personalization operates at user, persona, and global levels, each with different tradeoffs. Understanding these tradeoffs helps determine when to invest in individual user data versus broader patterns.
journeys require user-level tracking with persona-level precision
-
Does chatbot personalization build trust or expose privacy risks?
Explores whether personalization features that increase user trust and social connection simultaneously heighten privacy concerns and create rising behavioral expectations over time.
journey awareness intensifies the dual dynamic
-
Can conversations themselves personalize without user profiles?
Can a conversational AI learn about user traits and adapt in real time by rewarding itself for asking insightful questions, rather than relying on pre-collected profiles or historical data?
curiosity reward could discover journeys incrementally
-
Does abstract preference knowledge outperform specific interaction recall?
Explores whether summarized user preferences are more effective for LLM personalization than retrieving individual past interactions. Tests a cognitive dual-memory model against real personalization performance across model scales.
interest journeys are natural semantic memory content: they abstract activity patterns into durable preference narratives rather than recalling individual interactions, which aligns with PRIME's finding that abstract knowledge outperforms episodic recall
-
Do user outputs outperform inputs for LLM personalization?
Does a user's history of outputs (responses, endorsed content) matter more for personalization than their input queries? This explores what actually drives effective personalization in language models.
interest journeys are discoverable from user output patterns (what they consumed, created, engaged with) rather than input queries, confirming that personalization signal lives in outputs not inputs
Related papers in this collection 8
Papers most semantically related to this note, ranked by cosine similarity in the embedding space.
- Large Language Models for User Interest Journeys
- User-LLM: Efficient LLM Contextualization with User Embeddings
- Exploring the Impact of Large Language Models on Recommender Systems: An Extensive Review
- Using Large Language Models to Generate, Validate, and Apply User Intent Taxonomies
- Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations
- Doing Personal LAPS: LLM-Augmented Dialogue Construction for Personalized Multi-Session Conversational Search
- Leveraging Large Language Models in Conversational Recommender Systems
- Personalization of Large Language Models: A Survey
Original note title
LLMs can discover and describe persistent user interest journeys from activity patterns but recommender systems predict next items instead