Priming, Path-dependence, and Plasticity: Understanding the molding of user-LLM interaction and its implications from (many) chat logs in the wild

• URL: http://arxiv.org/abs/2605.05767v1
• Date: Thu, 07 May 2026 07:00:25 GMT
• Title: Priming, Path-dependence, and Plasticity: Understanding the molding of user-LLM interaction and its implications from (many) chat logs in the wild
• Abstract summary: This work explores a new approach to studying real-world user-LLM interactions through large-scale chat logs from the wild.<n>We demonstrate key patterns in user expressions despite varied tasks.
• Score: 14.896858577447093
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: User interactions with LLMs are shaped by prior experiences and individual exploration, but in-lab studies do not provide system designers with visibility into these in-the-wild factors. This work explores a new approach to studying real-world user-LLM interactions through large-scale chat logs from the wild. Through analysis of 140K chatbot sessions from 7,955 anonymized global users over time, we demonstrate key patterns in user expressions despite varied tasks: (1) LLM users are not tabula rasa, nor are they constantly adapting; rather, interaction patterns form and stabilize rapidly through individual early trajectories; (2) Longitudinal outcomes, such as recurring text patterns and retention rates, are strongly correlated with early exploration; (3) Parallel dynamics are present, including organizing expressions by task types such as emotional support, or in response to model-version updates. These results present an ``agency paradox'': despite LLM input spaces being unconstrained and user-driven, we in fact see less user exploration. We call for design consideration surrounding the molding procedure and its incorporation in future research.

Related papers

• VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions [63.13827503828231]
  We introduce VitaBench 2.0, a benchmark for evaluating personalized and proactive agent behavior in long-term user interactions.<n>Results show that real-world personalization remains highly challenging even for state-of-the-art models.
  arXiv  Detail & Related papers  (2026-05-26T15:07:38Z)
• HumanLM: Simulating Users with State Alignment Beats Response Imitation [84.89761487596844]
  We propose a novel training framework, HumanLM, which builds user simulators that accurately reflect real users.<n>HumanLM generates natural-language latent states that align with ground-truth responses through reinforcement learning.<n>For extensive evaluation, we develop Humanual, a comprehensive benchmark for simulating real users based on public data.
  arXiv  Detail & Related papers  (2026-02-07T20:26:28Z)
• Show or Tell? Modeling the evolution of request-making in Human-LLM conversations [14.896858577447093]
  We create and analyze a dataset of 211k real-world queries based on WildChat.<n>We find significant differences in the language for request-making in the human-LLM scenario.<n>We find that query patterns evolve from early ones emphasizing sole requests to combining more context later on.
  arXiv  Detail & Related papers  (2025-08-02T06:08:37Z)
• Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild [10.23533525266164]
  Large language models (LLMs) are used in complex writing to steer generations to better fit their needs.<n>We conduct a large-scale analysis of this collaborative behavior for users engaged in writing tasks in the wild.<n>We identify prototypical behaviors in how users interact with LLMs in prompts following their original request.
  arXiv  Detail & Related papers  (2025-05-21T21:13:01Z)
• CLEAR-KGQA: Clarification-Enhanced Ambiguity Resolution for Knowledge Graph Question Answering [13.624962763072899]
  KGQA systems typically assume user queries are unambiguous, which is an assumption that rarely holds in real-world applications.<n>We propose a novel framework that dynamically handles both entity ambiguity (e.g., distinguishing between entities with similar names) and intent ambiguity (e.g., clarifying different interpretations of user queries) through interactive clarification.
  arXiv  Detail & Related papers  (2025-04-13T17:34:35Z)
• If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs [55.8331366739144]
  We introduce LIFESTATE-BENCH, a benchmark designed to assess lifelong learning in large language models (LLMs)<n>Our fact checking evaluation probes models' self-awareness, episodic memory retrieval, and relationship tracking, across both parametric and non-parametric approaches.
  arXiv  Detail & Related papers  (2025-03-30T16:50:57Z)
• REALTALK: A 21-Day Real-World Dataset for Long-Term Conversation [51.97224538045096]
  We introduce REALTALK, a 21-day corpus of authentic messaging app dialogues.<n>We compare EI attributes and persona consistency to understand the challenges posed by real-world dialogues.<n>Our findings reveal that models struggle to simulate a user solely from dialogue history, while fine-tuning on specific user chats improves persona emulation.
  arXiv  Detail & Related papers  (2025-02-18T20:29:01Z)
• LLM-based Bi-level Multi-interest Learning Framework for Sequential Recommendation [54.396000434574454]
  We propose a novel multi-interest SR framework combining implicit behavioral and explicit semantic perspectives.<n>It includes two modules: the Implicit Behavioral Interest Module and the Explicit Semantic Interest Module.<n>Experiments on four real-world datasets validate the framework's effectiveness and practicality.
  arXiv  Detail & Related papers  (2024-11-14T13:00:23Z)
• Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models [66.24055500785657]
  Traditional turn-based chat systems prevent users from verbally interacting with system while it is generating responses. To overcome these limitations, we adapt existing LLMs to listen users while generating output and provide users with instant feedback. We build a dataset consisting of alternating time slices of queries and responses as well as covering typical feedback types in instantaneous interactions.
  arXiv  Detail & Related papers  (2024-06-22T03:20:10Z)
• LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendation [58.04939553630209]
  In real-world systems, most users interact with only a handful of items, while the majority of items are seldom consumed. These two issues, known as the long-tail user and long-tail item challenges, often pose difficulties for existing Sequential Recommendation systems. We propose the Large Language Models Enhancement framework for Sequential Recommendation (LLM-ESR) to address these challenges.
  arXiv  Detail & Related papers  (2024-05-31T07:24:42Z)
• On the steerability of large language models toward data-driven personas [98.9138902560793]
  Large language models (LLMs) are known to generate biased responses where the opinions of certain groups and populations are underrepresented. Here, we present a novel approach to achieve controllable generation of specific viewpoints using LLMs.
  arXiv  Detail & Related papers  (2023-11-08T19:01:13Z)
• Learning Large-scale Universal User Representation with Sparse Mixture of Experts [1.2722697496405464]
  We propose SUPERMOE, a generic framework to obtain high quality user representation from multiple tasks. Specifically, the user behaviour sequences are encoded by MoE transformer, and we can thus increase the model capacity to billions of parameters. In order to deal with seesaw phenomenon when learning across multiple tasks, we design a new loss function with task indicators.
  arXiv  Detail & Related papers  (2022-07-11T06:19:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.