Individual Text Corpora Predict User-Specific Knowledge: Benchmarks of Individualized Knowledge Simulation

• URL: http://arxiv.org/abs/2609.08532v1
• Date: Tue, 08 Sep 2026 10:19:28 GMT
• Title: Individual Text Corpora Predict User-Specific Knowledge: Benchmarks of Individualized Knowledge Simulation
• Abstract summary: This study examines whether individual text corpora (ICs) from search histories can be used to simulate individual knowledge.<n>We collected ICs from 316 adults, who answered 36 multiple-choice knowledge items, and compared several large language models (LLMs) on this task.<n>After task-specific fine-tuning via Low-Rank Adaptation (LoRA), Qwen3-1.7B outperformed both participants and a representative German norm sample on publicly available items.
• Score: 37.90336748891877
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This study examines whether individual text corpora (ICs) from search histories can be used to simulate individual knowledge. We collected ICs from 316 adults, who answered 36 multiple-choice knowledge items, and compared several large language models (LLMs) on this task, of which only Qwen3-1.7B proved viable. After task-specific fine-tuning via Low-Rank Adaptation (LoRA), Qwen3-1.7B outperformed both participants and a representative German norm sample on publicly available items. On non-public questions, however, the LLM performed worse than our participants, suggesting possible training data contamination for the public questions. When integrating ICs into retrieval-augmented generation to predict individual responses, LLM-participant Match accuracies significantly exceeded chance, which demonstrates a detectable individual knowledge signal. The probabilities assigned to the participants' answers were, however, low and far below the probability of correct answers, indicating poor calibration toward individual response patterns. Knowledge-gap prediction was sub-optimal, though it improved for corpora exceeding five million tokens. We discuss our entropy based evaluation benchmarks as calibration indices for individualized knowledge simulation.

Related papers

• Rethinking the Evaluation and Optimization of LLM-Based Social Simulation [56.18577997572273]
  We use the subjectivity coefficient to analyze how accuracy-based evaluation and hard-label training fail as subjectivity grows.<n>We construct SUBJSIM, a benchmark of 19,300 contexts covering 193 annotators and 100 subjective questions.<n>Results on SUBJSIM demonstrate the advantages of our method.
  arXiv  Detail & Related papers  (2026-08-20T06:26:03Z)
• Boosting Self-Consistency with Ranking [56.38798757709555]
  Self-consistency improves large language models by sampling multiple reasoning paths and selecting the most frequent answer.<n>We address this limitation with Ranking-Improved Self-Consistency (RISC), which reformulates answer selection in self-consistency as a ranking problem.
  arXiv  Detail & Related papers  (2026-06-03T16:12:30Z)
• When Can Digital Personas Reliably Approximate Human Survey Findings? [0.8411771830145969]
  Digital personas powered by Large Language Models (LLMs) are increasingly proposed as substitutes for human survey respondents.<n>It remains unclear when they can reliably approximate human survey findings.<n>We construct personas from respondents' background variables and pre-2023 survey histories, then testing them against the same respondents' held-out post-cutoff answers.
  arXiv  Detail & Related papers  (2026-05-11T14:41:11Z)
• Rectification Difficulty and Optimal Sample Allocation in LLM-Augmented Surveys [0.0]
  Large Language Models can generate synthetic survey responses at low cost, but their accuracy varies unpredictably across questions.<n>We study the design problem of allocating a fixed budget of human respondents across estimation tasks when cheap LLM predictions are available for every task.<n>Our framework combines three components. First, building on Prediction-Powered Inference, we characterize a question-specific rectification difficulty that governs how quickly the estimator's variance decreases with human sample size.<n>Second, we derive a closed-form optimal allocation rule that directs more human labels to tasks where the LLM is least reliable.
  arXiv  Detail & Related papers  (2026-04-19T05:45:37Z)
• Individual Turing Test: A Case Study of LLM-based Simulation Using Longitudinal Personal Data [54.145424717168794]
  Large Language Models (LLMs) have demonstrated remarkable human-like capabilities, yet their ability to replicate a specific individual remains under-explored.<n>This paper presents a case study to investigate LLM-based individual simulation with a volunteer-contributed archive of private messaging history spanning over ten years.<n>We propose the "Individual Turing Test" to evaluate whether acquaintances of the volunteer can correctly identify which response in a multi-candidate pool most plausibly comes from the volunteer.
  arXiv  Detail & Related papers  (2026-03-01T21:46:27Z)
• Pathways of Thoughts: Multi-Directional Thinking for Long-form Personalized Question Answering [57.12316804290369]
  Personalization is essential for adapting question answering systems to user-specific information needs.<n>We propose Pathways of Thoughts (PoT), an inference-stage method that applies to any large language model (LLM) without requiring task-specific fine-tuning.<n>PoT consistently outperforms competitive baselines, achieving up to a 13.1% relative improvement.
  arXiv  Detail & Related papers  (2025-09-23T14:44:46Z)
• Emulating Public Opinion: A Proof-of-Concept of AI-Generated Synthetic Survey Responses for the Chilean Case [0.0]
  Large Language Models (LLMs) offer promising avenues for methodological and applied innovations in survey research.<n>We evaluate the reliability of LLM-generated synthetic survey responses against ground-truth human responses from a Chilean public opinion probabilistic survey.
  arXiv  Detail & Related papers  (2025-09-11T21:43:59Z)
• Ranking Generated Answers: On the Agreement of Retrieval Models with Humans on Consumer Health Questions [25.158868133182025]
  We present a method for evaluating the output of generative large language models (LLMs)<n>We use ranking models trained on annotated document collections as a substitute for explicit relevance.<n>In a user study, our method correlates with the preferences of a human expert.
  arXiv  Detail & Related papers  (2024-08-19T09:27:45Z)
• Individual Text Corpora Predict Openness, Interests, Knowledge and Level of Education [0.5825410941577593]
  Personality dimension of openness to experience can be predicted from the individual google search history. Individual text corpora (ICs) were generated from 214 participants with a mean number of 5 million word tokens.
  arXiv  Detail & Related papers  (2024-03-29T21:44:24Z)
• Can ChatGPT Assess Human Personalities? A General Evaluation Framework [70.90142717649785]
  Large Language Models (LLMs) have produced impressive results in various areas, but their potential human-like psychology is still largely unexplored. This paper presents a generic evaluation framework for LLMs to assess human personalities based on Myers Briggs Type Indicator (MBTI) tests.
  arXiv  Detail & Related papers  (2023-03-01T06:16:14Z)

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.