Beyond the Click: A Framework for Inferring Cognitive Traces in Search

• URL: http://arxiv.org/abs/2602.24265v1
• Date: Fri, 27 Feb 2026 18:32:59 GMT
• Title: Beyond the Click: A Framework for Inferring Cognitive Traces in Search
• Authors: Saber Zerhoudi, Michael Granitzer,
• Abstract summary: We present a framework to infer cognitive traces from behavior logs.<n>These traces improve model performance on tasks like forecasting session outcomes and user struggle recovery.<n>This work provides the tools and data needed to build more human-like user simulators.
• Score: 2.50369129460887
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: User simulators are essential for evaluating search systems, but they primarily copy user actions without understanding the underlying thought process. This gap exists since large-scale interaction logs record what users do, but not what they might be thinking or feeling, such as confusion or satisfaction. To solve this problem, we present a framework to infer cognitive traces from behavior logs. Our method uses a multi-agent system grounded in Information Foraging Theory (IFT) and human expert judgment. These traces improve model performance on tasks like forecasting session outcomes and user struggle recovery. We release a collection of annotations for several public datasets, including AOL and Stack Overflow, and an open-source tool that allows researchers to apply our method to their own data. This work provides the tools and data needed to build more human-like user simulators and to assess retrieval systems on user-oriented dimensions of performance.

Related papers

• Understanding Usage and Engagement in AI-Powered Scientific Research Tools: The Asta Interaction Dataset [47.98539809308384]
  We analyze the Asta Interaction dataset, a large-scale resource comprising over 200,000 user queries and interaction logs.<n>We characterize query patterns, engagement behaviors, and how usage evolves with experience.<n>We release the anonymized dataset and analysis with a new query taxonomy to inform future designs of real-world AI research assistants.
  arXiv  Detail & Related papers  (2026-02-26T18:40:28Z)
• SessionIntentBench: A Multi-task Inter-session Intention-shift Modeling Benchmark for E-commerce Customer Behavior Understanding [64.45047674586671]
  We introduce the concept of an intention tree and propose a dataset curation pipeline.<n>We construct a sibling multimodal benchmark, SessionIntentBench, that evaluates L(V)LMs' capability on understanding inter-session intention shift.<n>With 1,952,177 intention entries, 1,132,145 session intention trajectories, and 13,003,664 available tasks mined using 10,905 sessions, we provide a scalable way to exploit the existing session data.
  arXiv  Detail & Related papers  (2025-07-27T09:04:17Z)
• Capturing and Anticipating User Intents in Data Analytics via Knowledge Graphs [0.061446808540639365]
  This work explores the usage of Knowledge Graphs (KG) as a basic framework for capturing a human-centered manner complex analytics. The data stored in the generated KG can then be exploited to provide assistance (e.g., recommendations) to the users interacting with these systems.
  arXiv  Detail & Related papers  (2024-11-01T20:45:23Z)
• On Generative Agents in Recommendation [58.42840923200071]
  Agent4Rec is a user simulator in recommendation based on Large Language Models. Each agent interacts with personalized recommender models in a page-by-page manner.
  arXiv  Detail & Related papers  (2023-10-16T06:41:16Z)
• User Behavior Simulation with Large Language Model based Agents [116.74368915420065]
  We propose an LLM-based agent framework and design a sandbox environment to simulate real user behaviors. Based on extensive experiments, we find that the simulated behaviors of our method are very close to the ones of real humans.
  arXiv  Detail & Related papers  (2023-06-05T02:58:35Z)
• Learn to Explore: on Bootstrapping Interactive Data Exploration with Meta-learning [8.92180350317399]
  We propose a learning-to-explore framework, based on meta-learning, which learns how to learn a classifier with automatically generated meta-tasks. Our proposal outperforms existing explore-by-example solutions in terms of accuracy and efficiency.
  arXiv  Detail & Related papers  (2022-12-07T03:12:41Z)
• A Unified Comparison of User Modeling Techniques for Predicting Data Interaction and Detecting Exploration Bias [17.518601254380275]
  We compare and rank eight user modeling algorithms based on their performance on a diverse set of four user study datasets. Based on our findings, we highlight open challenges and new directions for analyzing user interactions and visualization provenance.
  arXiv  Detail & Related papers  (2022-08-09T19:51:10Z)
• Causal Scene BERT: Improving object detection by searching for challenging groups of data [125.40669814080047]
  Computer vision applications rely on learning-based perception modules parameterized with neural networks for tasks like object detection. These modules frequently have low expected error overall but high error on atypical groups of data due to biases inherent in the training process. Our main contribution is a pseudo-automatic method to discover such groups in foresight by performing causal interventions on simulated scenes.
  arXiv  Detail & Related papers  (2022-02-08T05:14:16Z)
• Combining Feature and Instance Attribution to Detect Artifacts [62.63504976810927]
  We propose methods to facilitate identification of training data artifacts. We show that this proposed training-feature attribution approach can be used to uncover artifacts in training data. We execute a small user study to evaluate whether these methods are useful to NLP researchers in practice.
  arXiv  Detail & Related papers  (2021-07-01T09:26:13Z)
• AutoOD: Automated Outlier Detection via Curiosity-guided Search and Self-imitation Learning [72.99415402575886]
  Outlier detection is an important data mining task with numerous practical applications. We propose AutoOD, an automated outlier detection framework, which aims to search for an optimal neural network model. Experimental results on various real-world benchmark datasets demonstrate that the deep model identified by AutoOD achieves the best performance.
  arXiv  Detail & Related papers  (2020-06-19T18:57:51Z)
• Large-scale Hybrid Approach for Predicting User Satisfaction with Conversational Agents [28.668681892786264]
  Measuring user satisfaction level is a challenging task, and a critical component in developing large-scale conversational agent systems. Human annotation based approaches are easier to control, but hard to scale. A novel alternative approach is to collect user's direct feedback via a feedback elicitation system embedded to the conversational agent system.
  arXiv  Detail & Related papers  (2020-05-29T16:29:09Z)

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.